Search

In the field of object detection, small object detection in remote sensing images is an important and challenging task. Due to limitations in size and resolution, most existing methods often suffer from localization blurring. To address the above problem, this paper proposes a remote sensing small object detection network based on adaptive channel attention and large kernel adaptation. This approach aims to enhance multi-channel information mining and multi-scale feature extraction to alleviate the problem of localization blurring. To enhance the model's focus on the features of small objects in remote sensing at varying scales, this paper introduces an adaptive channel attention block. This block applies adaptive attention weighting based on the input feature dimensions, guiding the model to better focus on local information. To mitigate the loss of local information by large kernel convolutions, a large kernel adaptive block is designed. The block dynamically adjusts the surrounding spatial receptive field based on the context around the detection area, improving the model's ability to extract information around remote sensing small objects. To address the recognition confusion during the sample classification process, a layer batch normalization method is proposed. This method enhances the consistency analysis capabilities of adaptive learning, thereby reducing the decline in the model's classification accuracy caused by sample misclassification. Experiments on the DOTA-v2.0, SODA-A and VisDrone datasets show that the proposed method achieves state-of-the-art performance. [ABSTRACT FROM AUTHOR]

Mobile LiDAR technology is a powerful tool that accurately captures spatial information about typical static objects in road scenes. However, the precise extraction and classification of these objects pose persistent technical challenges. In this paper, we employ a deep learning approach to tackle the point cloud classification problem. Despite the popularity of the PointNet++ network for direct point cloud processing, it encounters issues related to insufficient feature learning and low accuracy. To address these limitations, we introduce a novel layer-wise optimization network, LO-Net. Initially, LO-Net utilizes the set abstraction module from PointNet++ to extract initial local features. It further enhances these features through the edge convolution capabilities of GraphConv and optimizes them using the "Unite_module" for semantic enhancement. Finally, it employs a point cloud spatial pyramid joint pooling module, developed by the authors, for the multiscale pooling of final low-level local features. Combining three layers of local features, LO-Net sends them to the fully connected layer for accurate point cloud classification. Considering real-world scenarios, road scene data often consist of incomplete point cloud data due to factors such as occlusion. In contrast, models in public datasets are typically more complete but may not accurately reflect real-world conditions. To bridge this gap, we transformed road point cloud data collected by mobile LiDAR into a dataset suitable for network training. This dataset encompasses nine common road scene features; hence, we named it the Road9 dataset and conducted classification research based on this dataset. The experimental analysis demonstrates that the proposed algorithm model yielded favorable results on the public datasets ModelNet40, ModelNet10, and the Sydney Urban Objects Dataset, achieving accuracies of 91.2%, 94.2%, and 79.5%, respectively. On the custom road scene dataset, Road9, the algorithm model proposed in this paper demonstrated outstanding classification performance, achieving a classification accuracy of 98.5%. [ABSTRACT FROM AUTHOR]

When it comes to forest management and protection, knowledge is key. Therefore, forest mapping is crucial to obtain the required knowledge towards profitable resource exploitation and increased resilience against wildfires. Within this context, this paper presents a literature review on tree classification and segmentation using data acquired by unmanned aerial vehicles, with special focus on the last decade (2013–2023). The latest research trends in this field are presented and analyzed in two main vectors, namely: (1) data, where used sensors and data structures are resumed; and (2) methods, where remote sensing and data analysis methods are described, with particular focus on machine learning approaches. The study and review methodology filtered 979 papers, which were then screened, resulting in the 144 works included in this paper. These are systematically analyzed and organized by year, keywords, purpose, sensors, and methods used, easily allowing the readers to have a wide, but at the same time detailed, view of the latest trends in automatic tree classification and segmentation using unmanned aerial vehicles. This review shows that image processing and machine learning techniques applied to forestry and segmentation and classification tasks are focused on improving the accuracy and interpretability of the results by using multi-modal data, 3D information, and AI methods. Most works use RGB or multispectral cameras, or LiDAR scanners, individually. Classification is mostly carried out using supervised methods, while segmentation mostly uses unsupervised machine learning techniques. [ABSTRACT FROM AUTHOR]

The identification of wetland vegetation is essential for environmental protection and management as well as for monitoring wetlands' health and assessing ecosystem services. However, some limitations on vegetation classification may be related to remote sensing technology, confusion between plant species, and challenges related to inadequate data accuracy. In this paper, vegetation classification in the Yancheng Coastal Wetlands is studied and evaluated from Sentinel-2 images based on a random forest algorithm. Based on consistent time series from remote sensing observations, the characteristic patterns of the Yancheng Coastal Wetlands were better captured. Firstly, the spectral features, vegetation indices, and phenological characteristics were extracted from remote sensing images, and classification products were obtained by constructing a dense time series using a dataset based on Sentinel-2 images in Google Earth Engine (GEE). Then, remote sensing classification products based on the random forest machine learning algorithm were obtained, with an overall accuracy of 95.64% and kappa coefficient of 0.94. Four indicators (POP, SOS, NDVIre, and B12) were the main contributors to the importance of the weight analysis for all features. Comparative experiments were conducted with different classification features. The results show that the method proposed in this paper has better classification. [ABSTRACT FROM AUTHOR]

With the development and popularization of LiDAR technology, point clouds are becoming widely used in multiple fields. Point cloud classification plays an important role in segmentation, geometric analysis, and vegetation description. However, existing point cloud classification algorithms have problems such as high computational complexity, a lack of feature optimization, and low classification accuracy. This paper proposes an efficient point cloud classification algorithm based on dynamic spatial–spectral feature optimization. It can eliminate redundant features, optimize features, reduce computational costs, and improve classification accuracy. It achieves feature optimization through three key steps. First, the proposed method extracts spatial, geometric, spectral, and other features from point cloud data. Then, the Gini index and Fisher score are used to calculate the importance and relevance of features, and redundant features are filtered. Finally, feature importance factors are used to dynamically enhance the discriminative power of highly distinguishable features to strengthen their contribution to point cloud classification. Four real-scene datasets from STPLS3D are utilized for experimentation. Compared to the other five algorithms, the proposed algorithm achieves at least a 37.97% improvement in mean intersection over union (mIoU). Meanwhile, the results indicate that the proposed algorithm can achieve high-precision point cloud classification with low computational complexity. [ABSTRACT FROM AUTHOR]

Earth observation missions such as Sentinel and Landsat support the large-scale identification of agricultural crops by providing free radar and multispectral satellite images. The extraction of representative image information as well as the combination of different image sources for improved feature selection still represent a major challenge in the field of remote sensing. In this paper, we propose a novel three-dimensional (3D) deep learning U-Net model to fuse multi-level image features from multispectral and synthetic aperture radar (SAR) time series data for seasonal crop-type mapping at a regional scale. For this purpose, we used a dual-stream U-Net with a 3D squeeze-and-excitation fusion module applied at multiple stages in the network to progressively extract and combine multispectral and SAR image features. Additionally, we introduced a distinctive method for generating patch-based multitemporal multispectral composites by selective image sampling within a 14-day window, prioritizing those with minimal cloud cover. The classification results showed that the proposed network provided the best overall accuracy (94.5%) compared to conventional two-dimensional (2D) and three-dimensional U-Net models (2D: 92.6% and 3D: 94.2%). Our network successfully learned multi-modal dependencies between the multispectral and SAR satellite images, leading to improved field mapping of spectrally similar and heterogeneous classes while mitigating the limitations imposed by persistent cloud coverage. Additionally, the feature representations extracted by the proposed network demonstrated their transferability to a new cropping season, providing a reliable mapping of spatio-temporal crop type patterns. [ABSTRACT FROM AUTHOR]

Self-supervised learning has made significant progress in point cloud processing. Currently, the primary tasks of self-supervised learning, which include point cloud reconstruction and representation learning, are trained separately due to their structural differences. This separation inevitably leads to increased training costs and neglects the potential for mutual assistance between tasks. In this paper, a self-supervised method named PointUR-RL is introduced, which integrates point cloud reconstruction and representation learning. The method features two key components: a variable masked autoencoder (VMAE) and contrastive learning (CL). The VMAE is capable of processing input point cloud blocks with varying masking ratios, ensuring seamless adaptation to both tasks. Furthermore, CL is utilized to enhance the representation learning capabilities and improve the separability of the learned representations. Experimental results confirm the effectiveness of the method in training and its strong generalization ability for downstream tasks. Notably, high-accuracy classification and high-quality reconstruction have been achieved with the public datasets ModelNet and ShapeNet, with competitive results also obtained with the ScanObjectNN real-world dataset. [ABSTRACT FROM AUTHOR]

Reducing the lag in the accuracy assessment of multi-temporal land-cover products has been a hot research topic. By identifying the changed strata, the annual accuracy in multi-temporal products can be quickly evaluated. However, there are still two limitations in the accuracy assessment of multi-temporal products. Firstly, the setting of the parameters (e.g., the total sample size, allocation of samples in the changed strata, etc.) in the fundamental sampling design is not based on specific setting criteria. Therefore, this evaluation method is not always applicable when the product or research area changes. Secondly, the accuracy evaluation of multi-temporal products does not consider the influence of misclassification. This can lead to an overestimation of the accuracy of changed strata in single-year evaluations. In this paper, we describe how the total sample and the assignment of samples in every stratum can be adjusted according to the characteristics of the land-cover product, which improves the applicability of the evaluation. The samples in the changed strata that propagate misclassification are essentially pixels that have not undergone any land-cover change. Therefore, in order to eliminate the propagation of this inter-annual classification error, the misclassified samples are reclassified as unchanged strata. This method was used in the multi-temporal ESA CCI land-cover product. The experimental results indicate that the single-year accuracy, considering classification error, is closer to the traditional evaluation accuracy of single-temporal data. For the categories with a small ratio of unchanged strata samples to changed strata samples, the accuracy improvement, after eliminating the classification errors, is more obvious. For the urban class, in particular, the misclassification affects its estimated accuracy by 9.72%. [ABSTRACT FROM AUTHOR]

Transformers have shown remarkable success in modeling sequential data and capturing intricate patterns over long distances. Their self-attention mechanism allows for efficient parallel processing and scalability, making them well-suited for the high-dimensional data in hyperspectral and LiDAR imagery. However, further research is needed on how to more deeply integrate the features of two modalities in attention mechanisms. In this paper, we propose a novel Multi-Feature Cross Attention-Induced Transformer Network (MCAITN) designed to enhance the classification accuracy of hyperspectral and LiDAR data. The MCAITN integrates the strengths of both data modalities by leveraging a cross-attention mechanism that effectively captures the complementary information between hyperspectral and LiDAR features. By utilizing a transformer-based architecture, the network is capable of learning complex spatial-spectral relationships and long-range dependencies. The cross-attention module facilitates the fusion of multi-source data, improving the network's ability to discriminate between different land cover types. Extensive experiments conducted on benchmark datasets demonstrate that the MCAITN outperforms state-of-the-art methods in terms of classification accuracy and robustness. [ABSTRACT FROM AUTHOR]

With the increasing frequency of natural disasters becoming, it is very important to classify and identify disasters. We propose a lightweight disaster classification model, which has lower computation and parameter quantities and a higher accuracy than other classification models. For this purpose, this paper specially proposes the SDS-Network algorithm, which is optimized on ResNet, to deal with the above problems of remote sensing images. First, it implements the spatial attention mechanism to improve the accuracy of the algorithm; then, the depth separable convolution is introduced to reduce the number of model calculations and parameters while ensuring the accuracy of the algorithm; finally, the effect of the model is increased by adjusting some hyperparameters. The experimental results show that, compared with the classic AlexNet, ResNet18, VGG16, VGG19, and Densenet121 classification models, the SDS-Network algorithm in this paper has a higher accuracy, and when compared with the lightweight models mobilenet series, shufflenet series, squeezenet series, and mnasnet series, it has lower model complexity and a higher accuracy rate. According to a comprehensive performance comparison of the charts made in this article, it is found that the SDS-Network algorithm is still better than the regnet series algorithm. Furthermore, after verification with a public data set, the SDS-Network algorithm in this paper is found to have a good generalization ability. Thus, we can conclude that the SDS-Network classification model of the algorithm in this paper has a good classification effect, and it is suitable for disaster classification tasks. Finally, it is verified on public data sets that the proposed SDS-Network has good generalization ability and portability. [ABSTRACT FROM AUTHOR]

With the advancement of 3D sensing technologies, point clouds are gradually becoming the main type of data representation in applications such as autonomous driving, robotics, and augmented reality. Nevertheless, the irregularity inherent in point clouds presents numerous challenges for traditional deep learning frameworks. Graph neural networks (GNNs) have demonstrated their tremendous potential in processing graph-structured data and are widely applied in various domains including social media data analysis, molecular structure calculation, and computer vision. GNNs, with their capability to handle non-Euclidean data, offer a novel approach for addressing these challenges. Additionally, drawing inspiration from the achievements of transformers in natural language processing, graph transformers have propelled models towards global awareness, overcoming the limitations of local aggregation mechanisms inherent in early GNN architectures. This paper provides a comprehensive review of GNNs and graph-based methods in point cloud applications, adopting a task-oriented perspective to analyze this field. We categorize GNN methods for point clouds based on fundamental tasks, such as segmentation, classification, object detection, registration, and other related tasks. For each category, we summarize the existing mainstream methods, conduct a comprehensive analysis of their performance on various datasets, and discuss the development trends and future prospects of graph-based methods. [ABSTRACT FROM AUTHOR]

In this paper, we leverage multimodal data to classify minerals using a multi-stream neural network. In a previous study on the Tinto dataset, which consisted of a 3D hyperspectral point cloud from the open-pit mine Corta Atalaya in Spain, we successfully identified mineral classes by employing various deep learning models. However, this prior work solely relied on hyperspectral data as input for the deep learning models. In this study, we aim to enhance accuracy by incorporating multimodal data, which includes hyperspectral images, RGB images, and a 3D point cloud. To achieve this, we have adopted a graph-based neural network, known for its efficiency in aggregating local information, based on our past observations where it consistently performed well across different hyperspectral sensors. Subsequently, we constructed a multi-stream neural network tailored to handle multimodality. Additionally, we employed a channel attention module on the hyperspectral stream to fully exploit the spectral information within the hyperspectral data. Through the integration of multimodal data and a multi-stream neural network, we achieved a notable improvement in mineral classification accuracy: 19.2%, 4.4%, and 5.6% on the LWIR, SWIR, and VNIR datasets, respectively. [ABSTRACT FROM AUTHOR]

Target recognition and fine-grained ship classification in remote sensing face challenges of high inter-class similarity and sample scarcity. A transfer fusion-based ship image harmonization algorithm is proposed to overcome these challenges. This algorithm designs a feature transfer fusion strategy based on the combination of a region-aware instantiation and attention mechanism. Adversarial learning is implemented through an image harmony generator and discriminator module to generate realistic remote sensing ship harmony images. Furthermore, the domain encoder and domain discriminator modules are responsible for extracting feature representations of the foreground and background, and further align the ship foreground with remote sensing ocean background features through feature discrimination. Compared with other advanced image conversion techniques, our algorithm delivers more realistic visuals, improving classification accuracy for six ship types by 3% and twelve types by 2.94%, outperforming Sim2RealNet. Finally, a mixed dataset containing data augmentation and harmonizing samples and real data was proposed for the fine-grained classification task of remote sensing ships. Evaluation experiments were conducted on eight typical fine-grained classification algorithms, and the accuracy of the fine-grained classification for all categories of ships was analyzed. The experimental results show that the mixed dataset proposed in this paper effectively alleviates the long-tail problem in real datasets, and the proposed remote sensing ship data augmentation framework performs better than state-of-the-art data augmentation methods in fine-grained ship classification tasks. [ABSTRACT FROM AUTHOR]

With the continuous maturity of hyperspectral remote sensing imaging technology, it has been widely adopted by scholars to improve the performance of feature classification. However, due to the challenges in acquiring hyperspectral images and producing training samples, the limited training sample is a common problem that researchers often face. Furthermore, efficient algorithms are necessary to excavate the spatial and spectral information from these images, and then, make full use of this information with limited training samples. To solve this problem, a novel two-branch deep learning network model is proposed for extracting hyperspectral remote sensing features in this paper. In this model, one branch focuses on extracting spectral features using multi-scale convolution and a normalization-based attention module, while the other branch captures spatial features through small-scale dilation convolution and Euclidean Similarity Attention. Subsequently, pooling and layering techniques are employed to further extract abstract features after feature fusion. In the experiments conducted on two public datasets, namely, IP and UP, as well as our own labeled dataset, namely, YRE, the proposed DMAN achieves the best classification results, with overall accuracies of 96.74%, 97.4%, and 98.08%, respectively. Compared to the sub-optimal state-of-the-art methods, the overall accuracies are improved by 1.05, 0.42, and 0.51 percentage points, respectively. The advantage of this network structure is particularly evident in unbalanced sample environments. Additionally, we introduce a new strategy based on the RPNet, which utilizes a small number of principal components for feature classification after dimensionality reduction. The results demonstrate its effectiveness in uncovering compressed feature information, with an overall accuracy improvement of 0.68 percentage points. Consequently, our model helps mitigate the impact of data scarcity on model performance, thereby contributing positively to the advancement of hyperspectral remote sensing technology in practical applications. [ABSTRACT FROM AUTHOR]

Cross-scene classification focuses on setting up an effective domain adaptation (DA) way to transfer the learnable knowledge from source to target domain, which can be reasonably achieved through the pseudo-label propagation procedure. However, it is hard to bridge the objective existing severe domain discrepancy between source and target domains, and thus, there are several unreliable pseudo-labels generated in target domain and involved into pseudo-label propagation procedure, which would lead to unreliable error accumulation to deteriorate the performance of cross-scene classification. Therefore, in this paper, a novel Masked Image Modeling Auxiliary Pseudo-Label Propagation called MIM-AP 2 with clustering central rectification strategy is proposed to improve the quality of pseudo-label propagation for cross-scene classification. First, in order to gracefully bridge the domain discrepancy and improve DA representation ability in-domain, a supervised class-token contrastive learning is designed to find the more consistent contextual clues to achieve knowledge transfer learning from source to target domain. At the same time, it is also incorporated with a self-supervised MIM mechanism according to a low random masking ratio to capture domain-specific information for improving the discriminability in-domain, which can lay a solid foundation for high-quality pseudo-label generation. Second, aiming to alleviate the impact of unreliable error accumulation, a clustering central rectification strategy is designed to adaptively update robustness clustering central representations to assist in rectifying unreliable pseudo-labels and learning a superior target domain specific classifier for cross-scene classification. Finally, extensive experiments are conducted on six cross-scene classification benchmarks, and the results are superior to other DA methods. The average accuracy reached 95.79%, which represents a 21.87% improvement over the baseline. This demonstrates that the proposed MIM-AP 2 can provide significantly improved performance. [ABSTRACT FROM AUTHOR]

This paper investigates remote sensing data recognition and classification with multimodal data fusion. Aiming at the problems of low recognition and classification accuracy and the difficulty in integrating multimodal features in existing methods, a multimodal remote sensing data recognition and classification model based on a heatmap and Hirschfeld–Gebelein–Rényi (HGR) correlation pooling fusion operation is proposed. A novel HGR correlation pooling fusion algorithm is developed by combining a feature fusion method and an HGR maximum correlation algorithm. This method enables the restoration of the original signal without changing the value of transmitted information by performing reverse operations on the sample data. This enhances feature learning for images and improves performance in specific tasks of interpretation by efficiently using multi-modal information with varying degrees of relevance. Ship recognition experiments conducted on the QXS-SROPT dataset demonstrate that the proposed method surpasses existing remote sensing data recognition methods. Furthermore, land cover classification experiments conducted on the Houston 2013 and MUUFL datasets confirm the generalizability of the proposed method. The experimental results fully validate the effectiveness and significant superiority of the proposed method in the recognition and classification of multimodal remote sensing data. [ABSTRACT FROM AUTHOR]

Polarimetric features extracted from polarimetric synthetic aperture radar (PolSAR) images contain abundant back-scattering information about objects. Utilizing this information for PolSAR image classification can improve accuracy and enhance object monitoring. In this paper, a deep learning classification method based on polarimetric channel power features for PolSAR is proposed. The distinctive characteristic of this method is that the polarimetric features input into the deep learning network are the power values of polarimetric channels and contain complete polarimetric information. The other two input data schemes are designed to compare the proposed method. The neural network can utilize the extracted polarimetric features to classify images, and the classification accuracy analysis is employed to compare the strengths and weaknesses of the power-based scheme. It is worth mentioning that the polarized characteristics of the data input scheme mentioned in this article have been derived through rigorous mathematical deduction, and each polarimetric feature has a clear physical meaning. By testing different data input schemes on the Gaofen-3 (GF-3) PolSAR image, the experimental results show that the method proposed in this article outperforms existing methods and can improve the accuracy of classification to a certain extent, validating the effectiveness of this method in large-scale area classification. [ABSTRACT FROM AUTHOR]

Synthetic Aperture Radar (SAR) has the advantage of continuous observation throughout the day and in all weather conditions, and is used in a wide range of military and civil applications. Among these, the detection of ships at sea is an important research topic. Ships in SAR images are characterized by dense alignment, an arbitrary orientation and multiple scales. The existing detection algorithms are unable to solve these problems effectively. To address these issues, A YOLOV8-based oriented ship detection and classification method using SAR imaging with lightweight receptor field feature convolution, bottleneck transformers and a probabilistic intersection-over-union network (R-LRBPNet) is proposed in this paper. First, a CSP bottleneck with two bottleneck transformer (C2fBT) modules based on bottleneck transformers is proposed; this is an improved feature fusion module that integrates the global spatial features of bottleneck transformers and the rich channel features of C2f. This effectively reduces the negative impact of densely arranged scenarios. Second, we propose an angle decoupling module. This module uses probabilistic intersection-over-union (ProbIoU) and distribution focal loss (DFL) methods to compute the rotated intersection-over-union (RIoU), which effectively alleviates the problem of angle regression and the imbalance between angle regression and other regression tasks. Third, the lightweight receptive field feature convolution (LRFConv) is designed to replace the conventional convolution in the neck. This module can dynamically adjust the receptive field according to the target scale and calculate the feature pixel weights based on the input feature map. Through this module, the network can efficiently extract details and important information about ships to improve the classification performance of the ship. We conducted extensive experiments on the complex scene SAR dataset SRSDD and SSDD+. The experimental results show that R-LRBPNet has only 6.8 MB of model memory, which can achieve 78.2% detection accuracy, 64.2% recall, a 70.51 F1-Score and 71.85% mAP on the SRSDD dataset. [ABSTRACT FROM AUTHOR]

In this paper, we propose a method for efficient target classification based on the spatial features of the point cloud generated by using a high-resolution radar sensor. The frequency-modulated continuous wave radar sensor can estimate the distance and velocity of a target. In addition, the azimuth and elevation angle of the target can be estimated by using a multiple-input and multiple-output antenna system. Using the estimated distance, velocity, and angle, the 3D point cloud of target can be generated. From the generated point cloud, we extract the point cloud for each individual target using the density-based spatial clustering of application with noise method and a camera mounted on the radar sensor. Then, we define the convex hull boundaries that enclose these point clouds in both 3D and 2D spaces obtained by orthogonally projecting onto the x y , y z , and z x planes. Using the vertices of convex hull, we calculate the volume of the targets and the areas in 2D spaces. Several feature points, including the calculated spatial information, are numerized and configured into feature vectors. We design an uncomplicated deep neural network classifier based on minimal input information to achieve fast and efficient classification performance. As a result, the proposed method achieved an average accuracy of 97.1%, and the time required for training was reduced compared to the method using only point cloud data and the convolutional neural network-based method. [ABSTRACT FROM AUTHOR]

Machine learning models are used to identify crops in satellite data, which achieve high classification accuracy but do not necessarily have a high degree of transferability to new regions. This paper investigates the use of machine learning models for crop classification using Sentinel-2 imagery. It proposes a new testing methodology that systematically analyzes the quality of the spatial transfer of trained models. In this study, the classification results of Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Stochastic Gradient Descent (SGD), Multilayer Perceptron (MLP), Support Vector Machines (SVM), and a Majority Voting of all models and their spatial transferability are assessed. The proposed testing methodology comprises 18 test scenarios to investigate phenological, temporal, spatial, and quantitative (quantitative regarding available training data) influences. Results show that the model accuracies tend to decrease with increasing time due to the differences in phenological phases in different regions, with a combined F1-score of 82% (XGBoost) when trained on a single day, 72% (XGBoost) when trained on the half-season, and 61% when trained over the entire growing season (Majority Voting). [ABSTRACT FROM AUTHOR]

Sea ice is a significant factor in influencing environmental change on Earth. Monitoring sea ice is of major importance, and one of the main objectives of this monitoring is sea ice classification. Currently, synthetic aperture radar (SAR) data are primarily used for sea ice classification, with a single polarization band or simple combinations of polarization bands being common choices. While much of the current research has focused on optimizing network structures to achieve high classification accuracy, which requires substantial training resources, we aim to extract more information from the SAR data for classification. Therefore we propose a multi-featured SAR sea ice classification method that combines polarization features calculated by polarization decomposition and spectrogram features calculated by joint time-frequency analysis (JTFA). We built a convolutional neural network (CNN) structure for learning the multi-features of sea ice, which combines spatial features and physical properties, including polarization and spectrogram features of sea ice. In this paper, we utilized ALOS PALSAR SLC data with HH, HV, VH, and VV, four types of polarization for the multi-featured sea ice classification method. We divided the sea ice into new ice (NI), first-year ice (FI), old ice (OI), deformed ice (DI), and open water (OW). Then, the accuracy calculation by confusion matrix and comparative analysis were carried out. Our experimental results demonstrate that the multi-feature method proposed in this paper can achieve high accuracy with a smaller data volume and computational effort. In the four scenes selected for validation, the overall accuracy could reach 95%, 91%, 96%, and 95%, respectively, which represents a significant improvement compared to the single-feature sea ice classification method. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) classification is one of the hotspots in remote sensing, and many methods have been continuously proposed in recent years. However, it is still challenging to achieve high accuracy classification in applications. One of the main reasons is the lack of labeled data. Due to the limitation of spatial resolution, manual labeling of HSI data is time-consuming and costly, so it is difficult to obtain a large amount of labeled data. In such a situation, many researchers turn their attention to the study of HSI classification with small samples. Focusing on this topic, this paper provides a systematic review of the research progress in recent years. Specifically, this paper contains three aspects. First, considering that the taxonomy used in previous review articles is not well-developed and confuses the reader, we propose a novel taxonomy based on the form of data utilization. This taxonomy provides a more accurate and comprehensive framework for categorizing the various approaches. Then, using the proposed taxonomy as a guideline, we analyze and summarize the existing methods, especially the latest research results (both deep and non-deep models) that were not included in the previous reviews, so that readers can understand the latest progress more clearly. Finally, we conduct several sets of experiments and present our opinions on current problems and future directions. [ABSTRACT FROM AUTHOR]

Accurate urban land cover information is crucial for effective urban planning and management. While convolutional neural networks (CNNs) demonstrate superior feature learning and prediction capabilities using image-level annotations, the inherent mixed-category nature of input image patches leads to classification errors along object boundaries. Fully convolutional neural networks (FCNs) excel at pixel-wise fine segmentation, making them less susceptible to heterogeneous content, but they require fully annotated dense image patches, which may not be readily available in real-world scenarios. This paper proposes an object-based semi-supervised spatial attention residual UNet (OS-ARU) model. First, multiscale segmentation is performed to obtain segments from a remote sensing image, and segments containing sample points are assigned the categories of the corresponding points, which are used to train the model. Then, the trained model predicts class probabilities for all segments. Each unlabeled segment's probability distribution is compared against those of labeled segments for similarity matching under a threshold constraint. Through label propagation, pseudo-labels are assigned to unlabeled segments exhibiting high similarity to labeled ones. Finally, the model is retrained using the augmented training set incorporating the pseudo-labeled segments. Comprehensive experiments on aerial image benchmarks for Vaihingen and Potsdam demonstrate that the proposed OS-ARU achieves higher classification accuracy than state-of-the-art models, including OCNN, 2OCNN, and standard OS-U, reaching an overall accuracy (OA) of 87.83% and 86.71%, respectively. The performance improvements over the baseline methods are statistically significant according to the Wilcoxon Signed-Rank Test. Despite using significantly fewer sparse annotations, this semi-supervised approach still achieves comparable accuracy to the same model under full supervision. The proposed method thus makes a step forward in substantially alleviating the heavy sampling burden of FCNs (densely sampled deep learning models) to effectively handle the complex issue of land cover information identification and classification. [ABSTRACT FROM AUTHOR]

One of the greatest challenges of our time is monitoring the rapid environmental changes taking place worldwide at both local and global scales. This requires easy-to-use and ready-to-implement tools and services to monitor and quantify aspects of bio- and geodiversity change and the impact of land use intensification using freely available and global remotely sensed data, and to derive remotely sensed indicators. Currently, there are no services for quantifying both raster- and vector-based indicators in a "compact tool". Therefore, the main innovation of ESIS/Imalys is having a remote sensing (RS) tool that allows for RS data processing, data management, and continuous and discrete quantification and derivation of RS indicators in one tool. With the ESIS/Imalys project (Ecosystem Integrity Remote Sensing—Modelling and Service Tool), we try to present environmental indicators on a clearly defined and reproducible basis. The Imalys software library generates the RS indicators and remote sensing products defined for ESIS. This paper provides an overview of the functionality of the Imalys software library. An overview of the technical background of the implementation of the Imalys library, data formats and the user interfaces is given. Examples of RS-based indicators derived using the Imalys tool at pixel level and at zone level (vector level) are presented. Furthermore, the advantages and disadvantages of the Imalys tool are discussed in detail in order to better assess the value of Imalys for users and developers. The applicability of the indicators will be demonstrated through three ecological applications, namely: (1) monitoring landscape diversity, (2) monitoring landscape structure and landscape fragmentation, and (3) monitoring land use intensity and its impact on ecosystem functions. Despite the integration of large amounts of data, Imalys can run on any PC, as the processing and derivation of indicators has been greatly optimised. The Imalys source code is freely available and is hosted and maintained under an open source license. Complete documentation of all methods, functions and derived indicators can be found in the freely available Imalys manual. The user-friendliness of Imalys, despite the integration of a large amount of RS data, makes it another important tool for ecological research, modelling and application for the monitoring and derivation of ecosystem indicators from local to global scale. [ABSTRACT FROM AUTHOR]

This paper proposes a texture-enhanced network (TENet) for intertidal sediment and habitat classification using multiband multipolarization synthetic aperture radar (SAR) images. The architecture introduces the texture enhancement module (TEM) into the UNet framework to explicitly learn global texture information from SAR images. The study sites are chosen from the northern part of the intertidal zones in the German Wadden Sea. Results show that the presented TENet model is able to detail the intertidal surface types, including land, seagrass, bivalves, bright sands/beach, water, sediments, and thin coverage of vegetation or bivalves. To further assess its performance, we quantitatively compared our results from the TENet model with different instance segmentation models for the same areas of interest. The TENet model gives finer classification accuracies and shows great potential in providing more precise locations. [ABSTRACT FROM AUTHOR]

Several deep learning and transformer models have been recommended in previous research to deal with the classification of hyperspectral images (HSIs). Among them, one of the most innovative is the bidirectional encoder representation from transformers (BERT), which applies a distance-independent approach to capture the global dependency among all pixels in a selected region. However, this model does not consider the local spatial-spectral and spectral sequential relations. In this paper, a dual-dimensional (i.e., spatial and spectral) BERT (the so-called D2BERT) is proposed, which improves the existing BERT model by capturing more global and local dependencies between sequential spectral bands regardless of distance. In the proposed model, two BERT branches work in parallel to investigate relations among pixels and spectral bands, respectively. In addition, the layer intermediate information is used for supervision during the training phase to enhance the performance. We used two widely employed datasets for our experimental analysis. The proposed D2BERT shows superior classification accuracy and computational efficiency with respect to some state-of-the-art neural networks and the previously developed BERT model for this task. [ABSTRACT FROM AUTHOR]

Evaluating classification accuracy is a key component of the training and validation stages of thematic map production, and the choice of metric has profound implications for both the success of the training process and the reliability of the final accuracy assessment. We explore key considerations in selecting and interpreting loss and assessment metrics in the context of data imbalance, which arises when the classes have unequal proportions within the dataset or landscape being mapped. The challenges involved in calculating single, integrated measures that summarize classification success, especially for datasets with considerable data imbalance, have led to much confusion in the literature. This confusion arises from a range of issues, including a lack of clarity over the redundancy of some accuracy measures, the importance of calculating final accuracy from population-based statistics, the effects of class imbalance on accuracy statistics, and the differing roles of accuracy measures when used for training and final evaluation. In order to characterize classification success at the class level, users typically generate averages from the class-based measures. These averages are sometimes generated at the macro-level, by taking averages of the individual-class statistics, or at the micro-level, by aggregating values within a confusion matrix, and then, calculating the statistic. We show that the micro-averaged producer's accuracy (recall), user's accuracy (precision), and F1-score, as well as weighted macro-averaged statistics where the class prevalences are used as weights, are all equivalent to each other and to the overall accuracy, and thus, are redundant and should be avoided. Our experiment, using a variety of loss metrics for training, suggests that the choice of loss metric is not as complex as it might appear to be, despite the range of choices available, which include cross-entropy (CE), weighted CE, and micro- and macro-Dice. The highest, or close to highest, accuracies in our experiments were obtained by using CE loss for models trained with balanced data, and for models trained with imbalanced data, the highest accuracies were obtained by using weighted CE loss. We recommend that, since weighted CE loss used with balanced training is equivalent to CE, weighted CE loss is a good all-round choice. Although Dice loss is commonly suggested as an alternative to CE loss when classes are imbalanced, micro-averaged Dice is similar to overall accuracy, and thus, is particularly poor for training with imbalanced data. Furthermore, although macro-Dice resulted in models with high accuracy when the training used balanced data, when the training used imbalanced data, the accuracies were lower than for weighted CE. In summary, the significance of this paper lies in its provision of readers with an overview of accuracy and loss metric terminology, insight regarding the redundancy of some measures, and guidance regarding best practices. [ABSTRACT FROM AUTHOR]

The classification of optical satellite-derived remote sensing images is an important satellite remote sensing application. Due to the wide variety of artificial features and complex ground situations in urban areas, the classification of complex urban features has always been a focus of and challenge in the field of remote sensing image classification. Given the limited information that can be obtained from traditional optical satellite-derived remote sensing data of a classification area, it is difficult to classify artificial features in detail at the pixel level. With the development of technologies, such as satellite platforms and sensors, the data types acquired by remote sensing satellites have evolved from static images to dynamic videos. Compared with traditional satellite-derived images, satellite-derived videos contain increased ground object reflection information, especially information obtained from different observation angles, and can thus provide more information for classifying complex urban features and improving the corresponding classification accuracies. In this paper, first, we analyze urban-area, ground feature characteristics and satellite-derived video remote sensing data. Second, according to these characteristics, we design a pixel-level classification method based on the application of machine learning techniques to video remote sensing data that represents complex, urban-area ground features. Last, we conduct experiments on real data. The test results show that applying the method designed in this paper to classify dynamic, satellite-derived video remote sensing data can improve the classification accuracy of complex features in urban areas compared with the classification results obtained using static, satellite-derived remote sensing image data at the same resolution. [ABSTRACT FROM AUTHOR]

This paper focuses on the problem of joint detection, tracking, and classification (JDTC) for multiple extended objects (EOs) within a Poisson multi-Bernoulli (MB) mixture (PMBM) filter, where an EO is described as an ellipse, and the ellipse is modeled by a random matrix. The EOs are classified according to the size information of the ellipse. Usually, detection, tracking, and classification are processed step-by-step. However, step-by-step processing ignores the coupling relationship between detection, tracking, and classification, resulting in information loss. In fact, detection, tracking, and classification affect each other, and JDTC is expected to be beneficial for achieving better overall performance. In the multi-target tracking problem based on RFS, the overall performance of the PMBM filter satisfying the conjugate priors has been verified to be superior to other filters. Specifically, the PMBM filter propagates multiple MB simultaneously during iterative updates and model the distribution of hitherto undetected EOs. At present, the PMBM filter is only applied to multiple extended objects tracking problem. Therefore, we consider using the PMBM filter to solve the JDTC problem of multiple EOs and further improve JDTC performance. Furthermore, the closed-form implementation based on the product of a gamma Gaussian inverse Wishart (GGIW) and class probability mass function (PMF) is proposed. The details of parameters calculation in the implementation process and the derivation of class PMF are presented in this paper. Simulation experiments verify that the proposed algorithm, named the JDTC-PMBM-GGIW filter, performs well in comparison to the existing JDTC strategies for multiple extended objects. [ABSTRACT FROM AUTHOR]

Remote sensing image scene classification has become more and more popular in recent years. As we all know, it is very difficult and time-consuming to obtain a large number of manually labeled remote sensing images. Therefore, few-shot scene classification of remote sensing images has become an urgent and important research task. Fortunately, the recently proposed deep nearest neighbor neural network (DN4) has made a breakthrough in few-shot classification. However, due to the complex background in remote sensing images, DN4 is easily affected by irrelevant local features, so DN4 cannot be directly applied in remote sensing images. For this reason, a deep nearest neighbor neural network based on attention mechanism (DN4AM) is proposed to solve the few-shot scene classification task of remote sensing images in this paper. Scene class-related attention maps are used in our method to reduce interference from scene-semantic irrelevant objects to improve the classification accuracy. Three remote sensing image datasets are used to verify the performance of our method. Compared with several state-of-the-art methods, including MatchingNet, RelationNet, MAML, Meta-SGD and DN4, our method achieves promising results in the few-shot scene classification of remote sensing images. [ABSTRACT FROM AUTHOR]

The classification of point clouds is an important research topic due to the increasing speed, accuracy, and detail of their acquisition. Classification using only color is basically absent in the literature; the few available papers provide only algorithms with limited usefulness (transformation of three-dimensional color information to a one-dimensional one, such as intensity or vegetation indices). Here, we proposed two methods for classifying point clouds in RGB space (without using spatial information) and evaluated the classification success since it allows a computationally undemanding classification potentially applicable to a wide range of scenes. The first is based on Gaussian mixture modeling, modified to exploit specific properties of the RGB space (a finite number of integer combinations, with these combinations repeated in the same class) to automatically determine the number of spatial normal distributions needed to describe a class (mGMM). The other method is based on a deep neural network (DNN), for which different configurations (number of hidden layers and number of neurons in the layers) and different numbers of training subsets were tested. Real measured data from three sites with different numbers of classified classes and different "complexity" of classification in terms of color distinctiveness were used for testing. Classification success rates averaged 99.0% (accuracy) and 96.2% (balanced accuracy) for the mGMM method and averaged 97.3% and 96.7% (balanced accuracy) for the DNN method in terms of the best parameter combinations identified. [ABSTRACT FROM AUTHOR]

Chinese Materia Medica Resources (CMMRs) are crucial for developing the tradition and industry of traditional Chinese medicine. Given the increasing demand for CMMRs, an accurate and effective understanding of CMMRs is urgently needed. Chinese medicinal plants (CMPs) are the most important sources of CMMRs. Traditional methods of investigating medicinal plant resources have limitations, including severe subjectivity and poor timeliness, which make it difficult to meet the demand for real-time monitoring of large-scale medicinal plant resources. In recent years, remote sensing technology has become an important means of obtaining information on medicinal plants, and the application of this technology has made up for the shortcomings of traditional methods. This paper first discusses the development of investigation methods of CMMRs; points out the importance of remote sensing technology in the application of spatial distribution and information identification and extraction of Chinese medicinal plant resources (CMPRs); analyzes the characteristics of CMPs in different planting patterns, different habitats, and different regions from the perspective of remote sensing information extraction; and explores the selection of suitable data sources, providing a reference for medicinal plant identification and information extraction. Secondly, according to the existing classification and identification methods, previous studies are summarized from the perspectives of classification scales, classification features, and classification accuracy, and the advantages and disadvantages of the commonly used remote sensing classification methods in the investigation of CMPRs are summarized and compared. Finally, the development trend of remote sensing technology in the identification and information extraction of CMPs is examined, and the key technical problems to be solved in the identification and classification of CMPs and the extraction of area information are summarized so as to provide technical support and experience references for the application of remote sensing in the investigation of CMPRs. [ABSTRACT FROM AUTHOR]

A large portion of Canada is covered by wetlands; mapping and monitoring them is of great importance for various applications. In this regard, Remote Sensing (RS) technology has been widely employed for wetland studies in Canada over the past 45 years. This study evaluates meta-data to investigate the status and trends of wetland studies in Canada using RS technology by reviewing the scientific papers published between 1976 and the end of 2020 (300 papers in total). Initially, a meta-analysis was conducted to analyze the status of RS-based wetland studies in terms of the wetland classification systems, methods, classes, RS data usage, publication details (e.g., authors, keywords, citations, and publications time), geographic information, and level of classification accuracies. The deep systematic review of 128 peer-reviewed articles illustrated the rising trend in using multi-source RS datasets along with advanced machine learning algorithms for wetland mapping in Canada. It was also observed that most of the studies were implemented over the province of Ontario. Pixel-based supervised classifiers were the most popular wetland classification algorithms. This review summarizes different RS systems and methodologies for wetland mapping in Canada to outline how RS has been utilized for the generation of wetland inventories. The results of this review paper provide the current state-of-the-art methods and datasets for wetland studies in Canada and will provide direction for future wetland mapping research. [ABSTRACT FROM AUTHOR]

In order to categorize feature classes by capturing subtle differences, hyperspectral images (HSIs) have been extensively used due to the rich spectral-spatial information. The 3D convolution-based neural networks (3DCNNs) have been widely used in HSI classification because of their powerful feature extraction capability. However, the 3DCNN-based HSI classification approach could only extract local features, and the feature maps it produces include a lot of spatial information redundancy, which lowers the classification accuracy. To solve the above problems, we proposed a spatial attention network (SATNet) by combining 3D OctConv and ViT. Firstly, 3D OctConv divided the feature maps into high-frequency maps and low-frequency maps to reduce spatial information redundancy. Secondly, the ViT model was used to obtain global features and effectively combine local-global features for classification. To verify the effectiveness of the method in the paper, a comparison with various mainstream methods on three publicly available datasets was performed, and the results showed the superiority of the proposed method in terms of classification evaluation performance. [ABSTRACT FROM AUTHOR]

Accurate and reliable informal settlement maps are fundamental decision-making tools for planning, and for expediting informed management of cities. However, extraction of spatial information for informal settlements has remained a mammoth task due to the spatial heterogeneity of urban landscape components, requiring complex analytical processes. To date, the use of Google Earth Engine platform (GEE), with cloud computing prowess, provides unique opportunities to map informal settlements with precision and enhanced accuracy. This paper leverages cloud-based computing techniques within GEE to integrate spectral and textural features for accurate extraction of the location and spatial extent of informal settlements in Durban, South Africa. The paper aims to investigate the potential and advantages of GEE's innovative image processing techniques to precisely depict morphologically varied informal settlements. Seven data input models derived from Sentinel 2A bands, band-derived texture metrics, and spectral indices were investigated through a random forest supervised protocol. The main objective was to explore the value of different data input combinations in accurately mapping informal settlements. The results revealed that the classification based on spectral bands + textural information yielded the highest informal settlement identification accuracy (94% F-score). The addition of spectral indices decreased mapping accuracy. Our results confirm that the highest spatial accuracy is achieved with the 'textural features' model, which yielded the lowest root-mean-square log error (0.51) and mean absolute percent error (0.36). Our approach highlights the capability of GEE's complex integrative data processing capabilities in extracting morphological variations of informal settlements in rugged and heterogeneous urban landscapes, with reliable accuracy. [ABSTRACT FROM AUTHOR]

For the multi-label classification task of remote sensing images (RSIs), it is difficult to accurately extract feature information from complex land covers, and it is easy to generate redundant features by ordinary convolution extraction features. This paper proposes a multi-label classification model for multi-source RSIs that combines dense convolution and an attention mechanism. This method adds fusion channel attention and a spatial attention mechanism to each dense block module of the DenseNet, and the sigmoid activation function replaces the softmax activation function in multi-label classification. The improved model retains the main features of RSIs to the greatest extent and enhances the feature extraction of the images. The model can integrate local features, capture global dependencies, and aggregate contextual information to improve the multi-label land cover classification accuracy of RSIs. We conducted comparative experiments on the SEN12-MS and UC-Merced land cover dataset and analyzed the evaluation indicators. The experimental results show that this method effectively improves the multi-label classification accuracy of RSIs. [ABSTRACT FROM AUTHOR]

Deep learning (DL) algorithms have demonstrated important breakthroughs for hyperspectral image (HSI) classification. Despite the remarkable success of DL, the burden of a manually designed DL structure with increased depth and size aroused the difficulty for the application in the mobile and embedded devices in a real application. To tackle this issue, in this paper, we proposed an efficient lightweight attention network architecture search algorithm (EL-NAS) for realizing an efficient automatic design of a lightweight DL structure as well as improving the classification performance of HSI. First, aimed at realizing an efficient search procedure, we construct EL-NAS based on a differentiable network architecture search (NAS), which can greatly accelerate the convergence of the over-parameter supernet in a gradient descent manner. Second, in order to realize lightweight search results with high accuracy, a lightweight attention module search space is designed for EL-NAS. Finally, further for alleviating the problem of higher validation accuracy and worse classification performance, the edge decision strategy is exploited to perform edge decisions through the entropy of distribution estimated over non-skip operations to avoid further performance collapse caused by numerous skip operations. To verify the effectiveness of EL-NAS, we conducted experiments on several real-world hyperspectral images. The results demonstrate that the proposed EL-NAS indicates a more efficient search procedure with smaller parameter sizes and high accuracy performance for HSI classification, even under data-independent and sensor-independent scenarios. [ABSTRACT FROM AUTHOR]

Over an extended period, considerable research has focused on elaborated mapping in navigation systems. Multispectral point clouds containing both spatial and spectral information play a crucial role in remote sensing by enabling more accurate land cover classification and the creation of more accurate maps. However, existing graph-based methods often overlook the individual characteristics and information patterns in these graphs, leading to a convoluted pattern of information aggregation and a failure to fully exploit the spatial–spectral information to classify multispectral point clouds. To address these limitations, this paper proposes a deep spatial graph convolution network with adaptive spectral aggregated residuals (DSGCN-ASR). Specifically, the proposed DSGCN-ASR employs spatial graphs for deep convolution, using spectral graph aggregated information as residuals. This method effectively overcomes the limitations of shallow networks in capturing the nonlinear characteristics of multispectral point clouds. Furthermore, the incorporation of adaptive residual weights enhances the use of spatial–spectral information, resulting in improved overall model performance. Experimental validation was conducted on two datasets containing real scenes, comparing the proposed DSGCN-ASR with several state-of-the-art graph-based methods. The results demonstrate that DSGCN-ASR better uses the spatial–spectral information and produces superior classification results. This study provides new insights and ideas for the joint use of spatial and spectral information in the context of multispectral point clouds. [ABSTRACT FROM AUTHOR]

The technology of remote sensing-assisted tree species classification is increasingly developing, but the rapid refinement of tree species classification on a large scale is still challenging. As one of the treasures of ecological resources in China, Arxan has 80% forest cover, and tree species classification surveys guarantee ecological environment management and sustainable development. In this study, we identified tree species in three samples within the Arxan Duraer Forestry Zone based on the spectral, textural, and topographic features of unmanned aerial vehicle (UAV) multispectral remote sensing imagery and light detection and ranging (LiDAR) point cloud data as classification variables to distinguish among birch, larch, and nonforest areas. The best extracted classification variables were combined to compare the accuracy of the random forest (RF), support vector machine (SVM), and classification and regression tree (CART) methodologies for classifying species into three sample strips in the Arxan Duraer Forestry Zone. Furthermore, the effect on the overall classification results of adding a canopy height model (CHM) was investigated based on spectral and texture feature classification combined with field measurement data to improve the accuracy. The results showed that the overall accuracy of the RF was 79%, and the kappa coefficient was 0.63. After adding the CHM extracted from the point cloud data, the overall accuracy was improved by 7%, and the kappa coefficient increased to 0.75. The overall accuracy of the CART model was 78%, and the kappa coefficient was 0.63; the overall accuracy of the SVM was 81%, and the kappa coefficient was 0.67; and the overall accuracy of the RF was 86%, and the kappa coefficient was 0.75. To verify whether the above results can be applied to a large area, Google Earth Engine was used to write code to extract the features required for classification from Sentinel-2 multispectral and radar topographic data (create equivalent conditions), and six tree species and one nonforest in the study area were classified using RF, with an overall accuracy of 0.98, and a kappa coefficient of 0.97. In this paper, we mainly integrate active and passive remote sensing data for forest surveying and add vertical data to a two-dimensional image to form a three-dimensional scene. The main goal of the research is not only to find schemes to improve the accuracy of tree species classification, but also to apply the results to large-scale areas. This is necessary to improve the time-consuming and labor-intensive traditional forest survey methods and to ensure the accuracy and reliability of survey data. [ABSTRACT FROM AUTHOR]

Deep learning-based label noise learning methods provide promising solutions for hyperspectral image (HSI) classification with noisy labels. Currently, label noise learning methods based on deep learning improve their performance by modifying one aspect, such as designing a robust loss function, revamping the network structure, or adding a noise adaptation layer. However, these methods face difficulties in coping with relatively high noise situations. To address this issue, this paper proposes a unified label noise learning framework with a dual-network structure. The goal is to enhance the model's robustness to label noise by utilizing two networks to guide each other. Specifically, to avoid the degeneration of the dual-network training into self-training, the "disagreement" strategy is incorporated with co-learning. Then, the "agreement" strategy is introduced into the model to ensure that the model iterates in the right direction under high noise conditions. To this end, an agreement and disagreement-based co-learning (ADCL) framework is proposed for HSI classification with noisy labels. In addition, a joint loss function consisting of a supervision loss of two networks and a relative loss between two networks is designed for the dual-network structure. Extensive experiments are conducted on three public HSI datasets to demonstrate the robustness of the proposed method to label noise. Specifically, our method obtains the highest overall accuracy of 98.62%, 90.89%, and 99.02% on the three datasets, respectively, which represents an improvement of 2.58%, 2.27%, and 0.86% compared to the second-best method. In future research, the authors suggest using more networks as backbones to implement the ADCL framework. [ABSTRACT FROM AUTHOR]

Efficient models capable of handling large numbers of data points in point cloud research are in high demand in computer vision. Despite recent advancements in 3D classification and segmentation tasks in point cloud processing, the deep learning PointNeXt and PointMLP models are plagued with heavy computation requirements with limited efficiencies. In this paper, a novel GhostMLP model for point clouds is thus introduced. It takes the advantages of the GhostNet design modules and uses them to replace the MLP layers in the existing PointMLP model. The resulting GhostMLP architecture achieves superior classification performance with lower computation requirements. Compared to the PointMLP, GhostMLP maintains sustainable performance with fewer parameters and lower FLOPs computations. Indeed, it outperforms PointMLP on the ScanObjectNN dataset, achieving 88.7% overall accuracy and 87.6% mean accuracy with only 6 million parameters and 7.2 GFLOPs—about half the resources required by PointMLP. At the same time, GhostMLP-S is introduced as a lightweight version which also outperforms PointMLP in performance. GhostMLP completes faster training and inference with GPU and is the best-performing method that does not require any extra training data in the ScanObjectNN benchmark. Efficient point cloud analysis is essential in computer vision, and we believe that GhostMLP has the potential to become a powerful tool for large-scale point cloud analysis. [ABSTRACT FROM AUTHOR]

Crop-type mapping is the foundation of grain security and digital agricultural management. Accuracy, efficiency and large-scale scene consistency are required to perform crop classification from remote sensing images. Many current remote-sensing crop extraction methods based on deep learning cannot account for adaptation effects in large-scale, complex scenes. Therefore, this study proposes a novel adaptive feature-fusion network for crop classification using single-temporal Sentinel-2 images. The selective patch module implemented in the network can adaptively integrate the features of different patch sizes to assess complex scenes better. TabNet was used simultaneously to extract spectral information from the center pixels of the patches. Multitask learning was used to supervise the extraction process to improve the weight of the spectral characteristics while mitigating the negative impact of a small sample size. In the network, superpixel optimization was applied to post-process the classification results to improve the crop edges. By conducting the crop classification of peanut, rice, and corn based on Sentinel-2 images in 2022 in Henan Province, China, the novel method proposed in this paper was more accurate, indicated by an F1 score of 96.53%, than other mainstream methods. This indicates our model's potential for application in crop classification in large scenes. [ABSTRACT FROM AUTHOR]

The reconstruction of 3D geometries starting from reality-based data is challenging and time-consuming due to the difficulties involved in modeling existing structures and the complex nature of built heritage. This paper presents a methodological approach for the automated segmentation and classification of surveying outputs to improve the interpretation and building information modeling from laser scanning and photogrammetric data. The research focused on the surveying of reticular, space grid structures of the late 19th–20th–21st centuries, as part of our architectural heritage, which might require monitoring maintenance activities, and relied on artificial intelligence (machine learning and deep learning) for: (i) the classification of 3D architectural components at multiple levels of detail and (ii) automated masking in standard photogrammetric processing. Focusing on the case study of the grid structure in steel named La Vela in Bologna, the work raises many critical issues in space grid structures in terms of data accuracy, geometric and spatial complexity, semantic classification, and component recognition. [ABSTRACT FROM AUTHOR]

Due to their ability to offer more comprehensive information than data from a single view, multi-view (e.g., multi-source, multi-modal, multi-perspective) data are being used more frequently in remote sensing tasks. However, as the number of views grows, the issue of data quality is becoming more apparent, limiting the potential benefits of multi-view data. Although recent deep neural network (DNN)-based models can learn the weight of data adaptively, a lack of research on explicitly quantifying the data quality of each view when fusing them renders these models inexplicable, performing unsatisfactorily and inflexibly in downstream remote sensing tasks. To fill this gap, in this paper, evidential deep learning is introduced to the task of aerial-ground dual-view remote sensing scene classification to model the credibility of each view. Specifically, the theory of evidence is used to calculate an uncertainty value which describes the decision-making risk of each view. Based on this uncertainty, a novel decision-level fusion strategy is proposed to ensure that the view with lower risk obtains more weight, making the classification more credible. On two well-known, publicly available datasets of aerial-ground dual-view remote sensing images, the proposed approach achieves state-of-the-art results, demonstrating its effectiveness. [ABSTRACT FROM AUTHOR]

In this paper we propose a novel rotation normalization technique for point cloud processing using an oriented bounding box. We use this method to create a point cloud annotation tool for part segmentation on real camera data. Custom data sets are used to train our network for classification and part segmentation tasks. Successful deployment is completed on an embedded device with limited processing power. A comparison is made with other rotation-invariant features in noisy synthetic datasets. Our method offers more auxiliary information related to the dimension, position, and orientation of the object than previous methods while performing at a similar level. [ABSTRACT FROM AUTHOR]

The realization of efficient classification with limited labeled samples is a critical task in hyperspectral image classification (HSIC). Convolutional neural networks (CNNs) have achieved remarkable advances while considering spectral–spatial features simultaneously, while conventional patch-wise-based CNNs usually lead to redundant computations. Therefore, in this paper, we established a novel active inference transfer convolutional fusion network (AI-TFNet) for HSI classification. First, in order to reveal and merge the local low-level and global high-level spectral–spatial contextual features at different stages of extraction, an end-to-end fully hybrid multi-stage transfer fusion network (TFNet) was designed to improve classification performance and efficiency. Meanwhile, an active inference (AI) pseudo-label propagation algorithm for spatially homogeneous samples was constructed using the homogeneous pre-segmentation of the proposed TFNet. In addition, a confidence-augmented pseudo-label loss (CapLoss) was proposed in order to define the confidence of a pseudo-label with an adaptive threshold in homogeneous regions for acquiring pseudo-label samples; this can adaptively infer a pseudo-label by actively augmenting the homogeneous training samples based on their spatial homogeneity and spectral continuity. Experiments on three real HSI datasets proved that the proposed method had competitive performance and efficiency compared to several related state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Cross-domain classification with small samples is a more challenging and realistic experimental setup. Until now, few studies have focused on the problem of small-sample cross-domain classification between completely different hyperspectral images (HSIs) since they possess different land cover types and statistical characteristics. To this end, this paper proposes a general-purpose representation learning method for cross-domain HSI classification, aiming to enable the model to learn more general-purpose deep representations that can quickly adapt to different target domains with small samples. The core of this method is to propose a novel three-level distillation strategy to transfer knowledge from multiple models well-trained on source HSIs into a single distilled model at the channel-, feature- and logit-level simultaneously. The learned representations can be further fine-tuned with small samples and quickly adapt to new target HSIs and previously unseen classes. Specifically, to transfer and fuse knowledge from multiple-source domains into a single model simultaneously and solve the inconsistency of the number of bands in different HSIs, an extensible multi-task model, including the channel transformation module, the feature extraction module and the linear classification module, is designed. Only the feature extraction module is shared across different HSIs, while the other two modules are domain-specific. Furthermore, the typical episode-based learning strategy of the metric-based meta-learning is adopted in the whole learning process to further improve the generalization ability and data efficiency. Extensive experiments are conducted on six source HSIs and four target HSIs, and the results demonstrate that the proposed method outperforms the existing advanced methods in cross-domain HSI classification with small samples. [ABSTRACT FROM AUTHOR]

With deep learning-based methods growing (even with scarce data in some fields), few-shot remote sensing scene classification (FSRSSC) has received a lot of attention. One mainstream approach uses base data to train a feature extractor (FE) in the pre-training phase and employs novel data to design the classifier and complete the classification task in the meta-test phase. Due to the scarcity of remote sensing data, obtaining a suitable feature extractor for remote sensing data and designing a robust classifier have become two major challenges. In this paper, we propose a novel dictionary learning (DL) algorithm for few-shot remote sensing scene classification to address these two difficulties. First, we use natural image datasets with sufficient data to obtain a pre-trained feature extractor. We fine-tune the parameters with the remote sensing dataset to make the feature extractor suitable for remote sensing data. Second, we design the kernel space classifier to map the features to a high-dimensional space and embed the label information into the dictionary learning to improve the discrimination of features for classification. Extensive experiments on four popular remote sensing scene classification datasets demonstrate the effectiveness of our proposed dictionary learning method. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) classification has recently been successfully explored by using deep learning (DL) methods. However, DL models rely heavily on a large number of labeled samples, which are laborious to obtain. Therefore, finding a way to efficiently embed DL models in limited labeled samples is a hot topic in the field of HSI classification. In this paper, an active learning-based siamese network (ALSN) is proposed to solve the limited labeled samples problem in HSI classification. First, we designed a dual learning-based siamese network (DLSN), which consists of a contrastive learning module and a classification module. Secondly, in view of the problem that active learning is difficult to effectively sample under the extremely limited labeling cost, we proposed an adversarial uncertainty-based active learning (AUAL) method to query valuable samples, and to promote DLSN to learn a more complete feature distribution by fine-tuning. Finally, an active learning architecture, based on inter-class uncertainty (ICUAL), is proposed to construct a lightweight sample pair training set, fully extracting the inter-class information of sample pairs and improving classification accuracy. Experiments on three generic HSI datasets strongly demonstrated the effectiveness of ALSN for HSI classification, with performance improvements over other related DL methods. [ABSTRACT FROM AUTHOR]

Satellite image time series (SITS) classification is a challenging application concurrently driven by long-term, large-scale, and high spatial-resolution observations acquired by remote sensing satellites. The focus of current SITS classification research is to exploit the richness of temporal information in SITS data. In the literature, self-attention mechanism-based networks, which are capable of capturing global temporal attention, have achieved state-of-the-art results in SITS classification. However, these methods lack attention to local temporal information, which is also significant for SITS classification tasks. To explore the potential of different scales of temporal information in SITS data, a global–local temporal attention encoder (GL-TAE) is proposed in this paper. GL-TAE has two submodules set up in parallel, one of which is a lightweight temporal attention encoder (LTAE) for extracting global temporal attention and the other is lightweight convolution (LConv) for extracting local temporal attention. Compared with methods exploring global-only or local-only temporal features, the proposed GL-TAE can achieve better performance on two public SITS datasets, which proves the effectiveness of hybrid global–local temporal attention features. The experiments also demonstrate that GL-TAE is a lightweight model, which achieves the same performance as other models but with fewer parameters. [ABSTRACT FROM AUTHOR]