Search

Image segmentation is a well-known image processing task that consists of partitioning an image into homogeneous areas. It is applied to remotely sensed imagery for many problems such as land use classification and landscape changes. Recently, several hybrid remote sensing image segmentation techniques have been proposed that include metaheuristic approaches in order to increase the segmentation accuracy; however, the critical point of these approaches is the high computational complexity, which affects time and memory consumption. In order to overcome this criticality, we propose a fuzzy-based image segmentation framework implemented in a GIS-based platform for remotely sensed images; furthermore, the proposed model allows us to evaluate the reliability of the segmentation. The Fast Generalized Fuzzy c-means algorithm is implemented to segment images in order to detect local spatial relations between pixels and the Triple Center Relation validity index is used to find the optimal number of clusters. The framework elaborates the composite index to be analyzed starting by multiband remotely sensed images. For each cluster, a segmented image is obtained in which the pixel value represents, transformed into gray levels, the graph belonging to the cluster. A final thematic map is built in which the pixels are classified based on the assignment to the cluster to which they belong with the highest membership degree. In addition, the reliability of the classification is estimated by associating each class with the average of the membership degrees of the pixels assigned to it. The method was tested in the study area consisting of the south-western districts of the city of Naples (Italy) for the segmentation of composite indices maps determined by multiband remote sensing images. The segmentation results are consistent with the segmentations of the study area by morphological and urban characteristics, carried out by domain experts. The high computational speed of the proposed image segmentation method allows it to be applied to massive high-resolution remote sensing images. [ABSTRACT FROM AUTHOR]

Floe size distribution (FSD) has become a parameter of great interest in observations of sea ice because of its importance in affecting climate change, marine ecosystems, and human activities in the polar ocean. A most effective way to monitor FSD in the ice-covered regions is to apply image processing techniques to airborne and satellite remote sensing data, where the segmentation of individual ice floes is a challenge in obtaining FSD from remotely sensed images. In this study, we adopt a deep learning (DL) semantic segmentation network to fast and adaptive implement the task of ice floe instance segmentation. In order to alleviate the costly and time-consuming data annotation problem of model training, classical image processing technique is applied to automatically label ice floes in local-scale marginal ice zone (MIZ). Several state-of-the-art (SoA) semantic segmentation models are then trained on the labelled MIZ dataset and further applied to additional large-scale optical Sentinel-2 images to evaluate their performance in floe instance segmentation and to determine the best model. A post-processing algorithm is also proposed in our work to refine the segmentation. Our approach has been applied to both airborne and high-resolution optical (HRO) satellite images to derive acceptable FSDs at local and global scales. [ABSTRACT FROM AUTHOR]

Cloud detection is critical in remote sensing image processing, and convolutional neural networks (CNNs) have significantly advanced this field. However, traditional CNNs primarily focus on extracting local features, which can be challenging for cloud detection due to the variability in the size, shape, and boundaries of clouds. To address this limitation, we propose a hybrid Swin transformer–CNN cloud detection (STCCD) network that combines the strengths of both architectures. The STCCD network employs a novel dual-stream encoder that integrates Swin transformer and CNN blocks. Swin transformers can capture global context features more effectively than traditional CNNs, while CNNs excel at extracting local features. The two streams are fused via a fusion coupling module (FCM) to produce a richer representation of the input image. To further enhance the network's ability in extracting cloud features, we incorporate a feature fusion module based on the attention mechanism (FFMAM) and an aggregation multiscale feature module (AMSFM). The FFMAM selectively merges global and local features based on their importance, while the AMSFM aggregates feature maps from different spatial scales to obtain a more comprehensive representation of the cloud mask. We evaluated the STCCD network on three challenging cloud detection datasets (GF1-WHU, SPARCS, and AIR-CD), as well as the L8-Biome dataset to assess its generalization capability. The results show that the STCCD network outperformed other state-of-the-art methods on all datasets. Notably, the STCCD model, trained on only four bands (visible and near-infrared) of the GF1-WHU dataset, outperformed the official Landsat-8 Fmask algorithm in the L8-Biome dataset, which uses additional bands (shortwave infrared, cirrus, and thermal). [ABSTRACT FROM AUTHOR]

Cloud and cloud shadow segmentation is one of the most critical challenges in remote sensing image processing. Because of susceptibility to factors such as disturbance from terrain features and noise, as well as a poor capacity to generalize, conventional deep learning networks, when directly used to cloud and cloud shade detection and division, have a tendency to lose fine features and spatial data, leading to coarse segmentation of cloud and cloud shadow borders, false detections, and omissions of targets. To address the aforementioned issues, a multi-scale strip feature attention network (MSFANet) is proposed. This approach uses Resnet18 as the backbone for obtaining semantic data at multiple levels. It incorporates a particular attention module that we name the deep-layer multi-scale pooling attention module (DMPA), aimed at extracting multi-scale contextual semantic data, deep channel feature information, and deep spatial feature information. Furthermore, a skip connection module named the boundary detail feature perception module (BDFP) is introduced to promote information interaction and fusion between adjacent layers of the backbone network. This module performs feature exploration on both the height and width dimensions of the characteristic pattern to enhance the recovery of boundary detail intelligence of the detection targets. Finally, during the decoding phase, a self-attention module named the cross-layer self-attention feature fusion module (CSFF) is employed to direct the aggregation of deeplayer semantic feature and shallow detail feature. This approach facilitates the extraction of feature information to the maximum extent while conducting image restoration. The experimental outcomes unequivocally prove the efficacy of our network in effectively addressing complex cloud-covered scenes, showcasing good performance across the cloud and cloud shadow datasets, the HRC_WHU dataset, and the SPARCS dataset. Our model outperforms existing methods in terms of segmentation accuracy, underscoring its paramount importance in the field of cloud recognition research. [ABSTRACT FROM AUTHOR]

In remote-sensing image processing tasks, images with higher resolution always result in better performance on downstream tasks, such as scene classification and object segmentation. However, objects in remote-sensing images often have low resolution and complex textures due to the imaging environment. Therefore, effectively reconstructing high-resolution remote-sensing images remains challenging. To address this concern, we investigate embedding context information and object priors from remote-sensing images into current deep learning super-resolution models. Hence, this paper proposes a novel remote-sensing image super-resolution method called Context-Guided Constrained Network (CGC-Net). In CGC-Net, we first design a simple but effective method to generate inverse distance maps from the remote-sensing image segmentation maps as prior information. Combined with prior information, we propose a Global Context-Constrained Layer (GCCL) to extract high-quality features with global context constraints. Furthermore, we introduce a Guided Local Feature Enhancement Block (GLFE) to enhance the local texture context via a learnable guided filter. Additionally, we design a High-Frequency Consistency Loss (HFC Loss) to ensure gradient consistency between the reconstructed image (HR) and the original high-quality image (HQ). Unlike existing remote-sensing image super-resolution methods, the proposed CGC-Net achieves superior visual results and reports new state-of-the-art (SOTA) performance on three popular remote-sensing image datasets, demonstrating its effectiveness in remote-sensing image super-resolution (RSI-SR) tasks. [ABSTRACT FROM AUTHOR]

Semantic segmentation is a growing topic in high-resolution remote sensing image processing. The information in remote sensing images is complex, and the effectiveness of most remote sensing image semantic segmentation methods depends on the number of labels; however, labeling images requires significant time and labor costs. To solve these problems, we propose a semi-supervised semantic segmentation method based on dual cross-entropy consistency and a teacher–student structure. First, we add a channel attention mechanism to the encoding network of the teacher model to reduce the predictive entropy of the pseudo label. Secondly, the two student networks share a common coding network to ensure consistent input information entropy, and a sharpening function is used to reduce the information entropy of unsupervised predictions for both student networks. Finally, we complete the alternate training of the models via two entropy-consistent tasks: (1) semi-supervising student prediction results via pseudo-labels generated from the teacher model, (2) cross-supervision between student models. Experimental results on publicly available datasets indicate that the suggested model can fully understand the hidden information in unlabeled images and reduce the information entropy in prediction, as well as reduce the number of required labeled images with guaranteed accuracy. This allows the new method to outperform the related semi-supervised semantic segmentation algorithm at half the proportion of labeled images. [ABSTRACT FROM AUTHOR]

Generation of random fields (GRF) for image segmentation represents partitioning an image into different regions that are homogeneous or have similar facets of the image. It is one of the most challenging tasks in image processing and a very important pre-processing step in the fields of computer vision, image analysis, medical image processing, pattern recognition, remote sensing, and geographical information system. Many researchers have presented numerous image segmentation approaches, but still, there are challenges like segmentation of low contrast images, removal of shadow in the images, reduction of high dimensional images, and computational complexity of segmentation techniques. In this review paper, the authors address these issues. The experiments are conducted and tested on the Berkely dataset (BSD500), Semantic dataset, and our own dataset, and the results are shown in the form of tables and graphs. [ABSTRACT FROM AUTHOR]

Image segmentation is an important task in image processing and analysis but due to the same ground object having different spectra and different ground objects having similar spectra, segmentation, particularly on high-resolution remote sensing images, can be significantly challenging. Since the spectral distribution of high-resolution remote sensing images can have complex characteristics (e.g., asymmetric or heavy-tailed), an innovative image segmentation algorithm is proposed based on the hierarchical Student's-t mixture model (HSMM) and spatial constraints with adaptive smoothing. Considering the complex distribution of spectral intensities, the proposed algorithm constructs the HSMM to accurately build the statistical model of the image, making more reasonable use of the spectral information and improving segmentation accuracy. The component weight is defined by the attribute probability of neighborhood pixels to overcome the influence of image noise and make a simple and easy-to-implement structure. To avoid the effects of artificially setting the smoothing coefficient, the gradient optimization method is used to solve the model parameters, and the smoothing coefficient is optimized through iterations. The experimental results suggest that the proposed HSMM can accurately model asymmetric, heavy-tailed, and bimodal distributions. Compared with traditional segmentation algorithms, the proposed algorithm can effectively overcome noise and generate more accurate segmentation results for high-resolution remote sensing images. [ABSTRACT FROM AUTHOR]

The detection and counting of lunar impact craters are crucial for the selection of detector landing sites and the estimation of the age of the Moon. However, traditional crater detection methods are based on machine learning and image processing technologies. These are inefficient for situations with different distributions, overlaps, and crater sizes, and most of them mainly focus on the accuracy of detection and ignore the efficiency. In this paper, we propose an efficient lunar crater detection (ELCD) algorithm based on a novel crater edge segmentation network (AFNet) to detect lunar craters from digital elevation model (DEM) data. First, in AFNet, a lightweight attention mechanism module is introduced to enhance the feature extract capabilities of networks, and a new multiscale feature fusion module is designed by fusing different multi-level feature maps to reduce the information loss of the output map. Then, considering the imbalance in the classification and the distributions of the crater data, an efficient crater edge segmentation loss function (CESL) is designed to improve the network optimization performance. Lastly, the crater positions are obtained from the network output map by the crater edge extraction (CEA) algorithm. The experiment was conducted on the PyTorch platform using two lunar crater catalogs to evaluate the ELCD. The experimental results show that ELCD has a superior detection accuracy and inference speed compared with other state-of-the-art crater detection algorithms. As with most crater detection models that use DEM data, some small craters may be considered to be noise that cannot be detected. The proposed algorithm can be used to improve the accuracy and speed of deep space probes in detecting candidate landing sites, and the discovery of new craters can increase the size of the original data set. [ABSTRACT FROM AUTHOR]

Data stream partitioning is a fundamental and important mechanism for distributed systems. However, use of an inappropriate partition scheme may generate a data skew problem, which can influence the execution efficiency of many application tasks. Processing of skewed partitions usually takes a longer time, need more computational resources to complete the task and can even become a performance bottleneck. To solve such data skew issues, this paper proposes a novel partition method to divide on demand the image tiles uniformly into partitions. The partitioning problem is then transformed into a uniform and compact clustering problem whereby the image tiles are regarded as image pixels without spectrum and texture information. First, the equal area conversion principle was used to select the seed points of the partitions and then the image tiles were aggregated in an image layout, thus achieving an initial partition scheme. Second, the image tiles of the initial partition were finely adjusted in the vertical and horizontal directions in separate steps to achieve a uniform distribution among the partitions. Two traditional partition methods were adopted to evaluate the efficiency of the proposed method in terms of the image segmentation testing, data shuffle testing, and image clipping testing. The results demonstrated that the proposed partition method solved the data skew problem observed in the hash partition method. In addition, this method is designed specifically for processing of image tiles and makes the related processing operations for large-scale images faster and more efficient. [ABSTRACT FROM AUTHOR]

The semantic segmentation of high-resolution remote sensing images (HRRSIs) is a basic task for remote sensing image processing and has a wide range of applications. However, the abundant texture information and wide imaging range of HRRSIs lead to the complex distribution of ground objects and unclear boundaries, which bring huge challenges to the segmentation of HRRSIs. To solve this problem, in this paper we propose an improved squeeze and excitation residual network (SERNet), which integrates several squeeze and excitation residual modules (SERMs) and a refine attention module (RAM). The SERM can recalibrate feature responses adaptively by modeling the long-range dependencies in the channel and spatial dimensions, which enables effective information to be transmitted between the shallow and deep layers. The RAM pays attention to global features that are beneficial to segmentation results. Furthermore, the ISPRS datasets were processed to focus on the segmentation of vegetation categories and introduce Digital Surface Model (DSM) images to learn and integrate features to improve the segmentation accuracy of surface vegetation, which has certain prospects in the field of forestry applications. We conduct a set of comparative experiments on ISPRS Vaihingen and Potsdam datasets. The results verify the superior performance of the proposed SERNet. [ABSTRACT FROM AUTHOR]

The automatic extraction of lake water is one of the research hotspots in the field of remote sensing image processing. Due to the small interclass variance between lakes and other ground objects, and the complex texture characteristics of lake boundaries, existing methods often have problems such as over-segmentation and inaccurate boundary segmentation when segmenting lake water bodies. To alleviate these problems, this article designs an end-to-end semantic segmentation network [noise-canceling transformer network (NT-Net)] for the automatic extraction of lake water bodies from remote sensing images. Aiming at the problem of over-segmentation caused by nonlake objects, an interference attenuation module is designed in the network. This module can model the key features that are distinguishable and suitable for segmenting lake water by analyzing the difference in feature representation between lakes and other ground objects, thus suppressing the feature representation of nonlake objects. To more accurately segment the lake boundary, a multilevel transformer module is designed. This module can capture the context association of boundary information and enhance the feature representation of boundary information by using the self-attention mechanism. The comparative experimental results show that, compared with the current mainstream semantic segmentation networks, the method in this article has advantages in extracting lake water bodies comprehensively and coherently. [ABSTRACT FROM AUTHOR]

Arial images are very high resolution. The automation for map generation and semantic segmentation of aerial images are challenging problems in semantic segmentation. The semantic segmentation process does not give us precise details of the remote sensing images due to the low resolution of the aerial images. Hence, we propose an algorithm U-Net Architecture to solve this problem. It is classified into two paths. The compression path (also called: the encoder) is the first path and is used to capture the image's context. The encoder is just a convolutional and maximal pooling layer stack. The symmetric expanding path (also called: the decoder) is the second path, which is used to enable exact localization by transposed convolutions. This task is commonly referred to as dense prediction, which is completely connected to each other and also with the former neurons which gives rise to dense layers. Thus it is an end-to-end fully convolutional network (FCN), i.e. it only contains convolutional layers and does not contain any dense layer because of which it can accept images of any size. The performance of the model will be evaluated by improving the image using the proposed method U-NET and obtaining an improved image by measuring the accuracy compared with the value of accuracy with previous methods. [ABSTRACT FROM AUTHOR]

Cloud and cloud shadow segmentation is one of the most important issues in remote sensing image processing. Most of the remote sensing images are very complicated. In this work, a dual-branch model composed of transformer and convolution network is proposed to extract semantic and spatial detail information of the image, respectively, to solve the problems of false detection and missed detection. To improve the model’s feature extraction, a mutual guidance module (MGM) is introduced, so that the transformer branch and the convolution branch can guide each other for feature mining. Finally, in view of the problem of rough segmentation boundary, this work uses different features extracted by the transformer branch and the convolution branch for decoding and repairs the rough segmentation boundary in the decoding part to make the segmentation boundary clearer. Experimental results on the Landsat-8, Sentinel-2 data, the public dataset high-resolution cloud cover validation dataset created by researchers at Wuhan University (HRC_WHU), and the public dataset Spatial Procedures for Automated Removal of Cloud and Shadow (SPARCS) demonstrate the effectiveness of our method and its superiority to the existing state-of-the-art cloud and cloud shadow segmentation approaches. [ABSTRACT FROM AUTHOR]

Urban scene image segmentation is an important research area in high-resolution remote sensing image processing. However, due to its complex three-dimensional structure, interference factors such as occlusion, shadow, intra-class inconsistency, and inter-class indistinction affect segmentation performance. Many methods have combined local and global information using CNNs and Transformers to achieve high performance in remote sensing image segmentation tasks. However, these methods are not stable when dealing with these interference factors. Recent studies have found that semantic segmentation is highly sensitive to frequency information, so we introduced frequency information to make the model learn more comprehensively about different categories of targets from multiple dimensions. By modeling the target with local features, global information, and frequency information, the target features can be learned in multiple dimensions to reduce the impact of interference factors on the model and improve its robustness. In this paper, we consider frequency information in addition to combining CNNs and Transformers for modeling and propose a Multidimensional Information Fusion Network (MIFNet) for high-resolution remote sensing image segmentation of urban scenes. Specifically, we design an information fusion Transformer module that can adaptively associate local features, global semantic information, and frequency information and a relevant semantic aggregation module for aggregating features at different scales to construct the decoder. By aggregating image features at different depths, the specific representation of the target and the correlation between targets can be modeled in multiple dimensions, allowing the network to better recognize and understand the features of each class of targets to resist various interference factors that affect segmentation performance. We conducted extensive ablation experiments and comparative experiments on the ISPRS Vaihingen and ISPRS Potsdam benchmarks to verify our proposed method. In a large number of experiments, our method achieved the best results, with 84.53% and 87.3% mIoU scores on the Vaihingen and Potsdam datasets, respectively, proving the superiority of our method. The source code will be available at https://github.com/JunyuFan/MIFNet. [ABSTRACT FROM AUTHOR]

Scene classification for remote sensing is a popular topic, and many recent convolutional neural networks (CNNs)‐based methods have shown the great model capacity and learning ability of highly discriminative features. Given a large number of training data, CNN can extract extensive features and learn to predict a remote sensing image. However, for supervised learning tasks, deep models often rely on a large number of labelled remote sensing images, which are difficult to pre‐process. Thus, training a lightweight deep learning model is essential. Easy‐classified and hard samples may also cause an imbalance of training set and lead the model to overwhelm the loss function. Accordingly, a novel Efficient Recurrent Attention Network (ERANet) for remote sensing scene classification is proposed. Different from traditional deep learning methods, Efficientnet‐B0 is introduced as a lightweight backbone for the ARCNet framework, replacing the original one. By applying the modified efficient backbone, the low Floating Point Operations (FLOPs) and parameter numbers of the proposed ERANet are maintained. The significance of focal loss is determined and applied to address the sample imbalance problem and yield a desirable performance. Extensive experiments on several challenging remote sensing scene classification data sets prove the efficiency of the proposed ERANet. [ABSTRACT FROM AUTHOR]

A dynamic monitoring algorithm of natural resources in scenic spots based on MODIS remote sensing technology is proposed to improve natural resources monitoring accuracy in scenic spots. The remote sensing images of scenic spots obtained by MODIS were preprocessed by TM image processing, atmospheric correction, and other technologies to get high-precision remote sensing images. The remote sensing images of scenic spots were segmented by the multiscale segmentation method, and then the hierarchical supervision classification method was used. The change points of natural resources were extracted. The resource changes and independent variables of scenic spots were analyzed based on the least square method to realize the dynamic monitoring of natural resources in scenic locations. The experimental results show that the technique can accurately monitor the dynamic changes of forest resources and water resources in scenic spots, and the monitoring results have high accuracy. [ABSTRACT FROM AUTHOR]

High/very-high-resolution (HR/VHR) multitemporal images are important in remote sensing to monitor the dynamics of the Earth’s surface. Unsupervised object-based image analysis provides an effective solution to analyze such images. Image semantic segmentation assigns pixel labels from meaningful object groups and has been extensively studied in the context of single-image analysis, however not explored for multitemporal one. In this article, we propose to extend supervised semantic segmentation to the unsupervised joint semantic segmentation of multitemporal images. We propose a novel method that processes multitemporal images by separately feeding to a deep network comprising of trainable convolutional layers. The training process does not involve any external label, and segmentation labels are obtained from the argmax classification of the final layer. A novel loss function is used to detect object segments from individual images as well as establish a correspondence between distinct multitemporal segments. Multitemporal semantic labels and weights of the trainable layers are jointly optimized in iterations. We tested the method on three different HR/VHR data sets from Munich, Paris, and Trento, which shows the method to be effective. We further extended the proposed joint segmentation method for change detection (CD) and tested on a VHR multisensor data set from Trento. [ABSTRACT FROM AUTHOR]

With an increasing number of remote sensing images (RSIs), the automatic region of interest (ROI) extraction based on convolutional neural networks (CNNs) has attracted much interest in recent years. Although fully supervised CNN-based methods have shown superiority in the field of object extraction, pixelwise annotations are expensive and time-consuming. Moreover, due to the unstable distribution of ROIs in complex landscapes, the ratios of foreground and background areas are quite different in RSIs. Training CNNs with such unbalanced data sets lead to over-fitting and low accuracy. In this article, we propose a framework that combines multiview learning and attention mechanism (MLAM) to solve the above mentioned problems. First, we develop a CNN-based weakly supervised method with a weight-balanced loss function to solve the problems caused by an unbalanced data set. It also helps to generate imagewise saliency maps by computing the gradient maps with respect to the input images. Then, we design a multiview strategy to dramatically reduce the missing inspection. Finally, we design a feedback attention mechanism based on the stage neighbor binary pattern to further modify the extraction result. In summary, the proposed framework achieves pixelwise ROI extraction under imagewise annotations through data-driven ML and a knowledge-driven visual attention mechanism. We evaluate the performance of the MLAM framework on two challenging data sets with complex backgrounds. The experimental results indicate that the proposed framework can achieve better performance than other eight ROI extraction models for unbalanced remote sensing data sets. [ABSTRACT FROM AUTHOR]

Polarimetric synthetic aperture radar (PolSAR) image segmentation is currently of great importance in image processing for remote sensing applications. However, it is a challenging task due to two main reasons. Firstly, the label information is difficult to acquire due to high annotation costs. Secondly, the speckle effect embedded in the PolSAR imaging process remarkably degrades the segmentation performance. To address these two issues, we present a contextual PolSAR image semantic segmentation method in this paper. With a newly defined channel-wise consistent feature set as input, the three-dimensional discrete wavelet transform (3D-DWT) technique is employed to extract discriminative multi-scale features that are robust to speckle noise. Then Markov random field (MRF) is further applied to enforce label smoothness spatially during segmentation. By simultaneously utilizing 3D-DWT features and MRF priors for the first time, contextual information is fully integrated during the segmentation to ensure accurate and smooth segmentation. To demonstrate the effectiveness of the proposed method, we conduct extensive experiments on three real benchmark PolSAR image data sets. Experimental results indicate that the proposed method achieves promising segmentation accuracy and preferable spatial consistency using a minimal number of labeled pixels. [ABSTRACT FROM AUTHOR]

• Effective strategies for noisy image segmentation using adaptive wavelet shrinkage. • Edge enhancement in wavelet domain improve the results. • Significantly better performance than other methods on severely noisy images. • No parameter-tuning required for different noise levels and types • Very consistent results even when the noise level has a large variation. Noisy image segmentation is a hot topic in natural, medical, and remote sensing image processing. It is among the non-trivial problems of computer vision having to address denoising and segmentation at the same time. Fuzzy C-means (FCM) is a clustering algorithm that has been shown to be effective at dealing with both segmentation-oriented denoising and segmentation at the same time. Moreover, with a high level of noise and other imaging artifacts, FCM loses its ability to perform image segmentation effectively. This paper introduces a Particle Swarm Optimization (PSO)-based feature enhancement approach in the wavelet domain for noisy image segmentation. This approach applies adaptive wavelet shrinkage using FCM clustering performance as an evaluation mechanism and also as the segmentation algorithm. The PSO-based process helps to enhance intensity features for clustering-based denoising, and also provides adaptivity for the system that performs well on a range of real, synthetic, and simulated noisy images with different noise levels and range/spatial properties. Furthermore, the algorithm applies edge enhancement based on Canny edge detector in order to further improve accuracy. Experiments are presented using three different datasets each degraded with different types of common noise. The presented algorithms show effective and consistent performance over a range of severe noise levels without the need for any parameter tuning. [ABSTRACT FROM AUTHOR]

Semantic segmentation requires methods capable of learning high-level features while dealing with large volume of data. Toward such goal, convolutional networks can learn specific and adaptable features based on the data. However, these networks are not capable of processing a whole remote sensing image, given its huge size. To overcome such limitation, the image is processed using fixed size patches. The definition of the input patch size is usually performed empirically (evaluating several sizes) or imposed (by network constraint). Both strategies suffer from drawbacks and could not lead to the best patch size. To alleviate this problem, several works exploited multicontext information by combining networks or layers. This process increases the number of parameters, resulting in a more difficult model to train. In this paper, we propose a novel technique to perform semantic segmentation of remote sensing images that exploits a multicontext paradigm without increasing the number of parameters while defining, in training time, the best patch size. The main idea is to train a dilated network with distinct patch sizes, allowing it to capture multicontext characteristics from heterogeneous contexts. While processing these varying patches, the network provides a score for each patch size, helping in the definition of the best size for the current scenario. A systematic evaluation of the proposed algorithm is conducted using four high-resolution remote sensing data sets with very distinct properties. Our results show that the proposed algorithm provides improvements in pixelwise classification accuracy when compared to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Image segmentation techniques are challenging to apply to large-size remote sensing imagery. Indeed, if the data to be processed are larger than the computer’s available memory, it must be split into smaller pieces. Without precaution, segmentation errors appear along the edges of these pieces. The goal of this paper is to present a tilewise processing method to overcome this issue for superpixel segmentation, applied in particular to the simple linear iterative clustering algorithm. Incidentally, tilewise methods allow for several pieces of the image to be processed simultaneously, which enables the deployment of these methods in a parallel processing environment. Estimations of the speed-up when using multiple processors are provided. Then, it is demonstrated that the result of the tilewise segmentation is equivalent to the segmentation of the complete image, with respect to a number of global unsupervised segmentation criteria. Finally, experimental results on a large-size Sentinel-2 time series validate the method’s feasibility. [ABSTRACT FROM AUTHOR]

Semantic segmentation of remote sensing ship targets is one of the most challenging works in image processing, especially for small and multi‐scale ship target detection. To solve these problems, an efficient method based on convolutional neural networks (CNN) to detect ship targets is proposed. This method introduces the attention model to the network to enhance the characteristics of small targets and combines atrous convolution with traditional CNN to increase the receptive field. To preserve the information lost by pooling, the proposed method uses the passthrough layer method to retain more features and concatenate the high‐ and low‐resolution features. To verify the effectiveness of the method proposed in this study, the performance was evaluated by using precision, recall, F1‐Score, mean intersection‐over‐union (IoU), and pixel accuracy measurements. These performances are all higher than the traditional semantic segmentation network SegNet. Mean IoU increases to 0.783 and pixel accuracy increases to 0.935. This method can conclusively identify ship targets in remote sensing images and has a certain reference value for remote sensing target detection. [ABSTRACT FROM AUTHOR]

The effective identification of clouds and monitoring of their evolution are important toward more accurate quantitative precipitation estimation and forecast. In this study, a new gradient-based cloud-image segmentation algorithm is developed using image processing techniques. This method integrates morphological image gradient magnitudes to separate cloud systems and patches boundaries. A varying scale kernel is implemented to reduce the sensitivity of image segmentation to noise and to capture objects with various finenesses of the edges in remote sensing images. The proposed method is flexible and extendable from single to multispectral imagery. Case studies were carried out to validate the algorithm by applying the proposed segmentation algorithm to synthetic radiances for channels of the Geostationary Operational Environmental Satellite (GOES-16) simulated by a high-resolution weather prediction model. The proposed method compares favorably with the existing cloud-patch-based segmentation technique implemented in the Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks–Cloud Classification System (PERSIANN-CCS) rainfall retrieval algorithm. Evaluation of event-based images indicates that the proposed algorithm has potentials comparing to the conventional segmentation technique used in PERSIANN-CCS to improve rain detection and estimation skills with an accuracy rate of up to 98% in identifying cloud regions. [ABSTRACT FROM AUTHOR]

It is a classical task to automatically extract road networks from very high-resolution (VHR) images in remote sensing. This paper presents a novel method for extracting road networks from VHR remotely sensed images in complex urban scenes. Inspired by image segmentation, edge detection, and object skeleton extraction, we develop a multitask convolutional neural network (CNN), called RoadNet, to simultaneously predict road surfaces, edges, and centerlines, which is the first work in such field. The RoadNet solves seven important issues in this vision problem: 1) automatically learning multiscale and multilevel features [gained by the deeply supervised nets (DSN) providing integrated direct supervision] to cope with the roads in various scenes and scales; 2) holistically training the mentioned tasks in a cascaded end-to-end CNN model; 3) correlating the predictions of road surfaces, edges, and centerlines in a network model to improve the multitask prediction; 4) designing elaborate architecture and loss function, by which the well-trained model produces approximately single-pixel width road edges/centerlines without nonmaximum suppression postprocessing; 5) cropping and bilinear blending to deal with the large VHR images with finite-computing resources; 6) introducing rough and simple user interaction to obtain desired predictions in the challenging regions; and 7) establishing a benchmark data set which consists of a series of VHR remote sensing images with pixelwise annotation. Different from the previous works, we pay more attention to the challenging situations, in which there are lots of shadows and occlusions along the road regions. Experimental results on two benchmark data sets show the superiority of our proposed approaches. [ABSTRACT FROM AUTHOR]

Floods are natural disasters which cause the most economic damage at the global level. Therefore, flood monitoring and damage estimation are very important for the population, authorities and insurance companies. The paper proposes an original solution, based on a hybrid network and complex image processing, to this problem. As first novelty, a multilevel system, with two components, terrestrial and aerial, was proposed and designed by the authors as support for image acquisition from a delimited region. The terrestrial component contains a Ground Control Station, as a coordinator at distance, which communicates via the internet with more Ground Data Terminals, as a fixed nodes network for data acquisition and communication. The aerial component contains mobile nodes—fixed wing type UAVs. In order to evaluate flood damage, two tasks must be accomplished by the network: area coverage and image processing. The second novelty of the paper consists of texture analysis in a deep neural network, taking into account new criteria for feature selection and patch classification. Color and spatial information extracted from chromatic co-occurrence matrix and mass fractal dimension were used as well. Finally, the experimental results in a real mission demonstrate the validity of the proposed methodologies and the performances of the algorithms. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new unsupervised change detection method designed to analyze multispectral remotely sensed image pairs. It is formulated as a segmentation problem to discriminate the changed class from the unchanged class in the difference images. The proposed method is in the category of the committee machine learning model that utilizes an ensemble of classifiers (i.e., the set of segmentation results obtained by several thresholding methods) with a dynamic structure type. More specifically, in order to obtain the final “change/no-change” output, the responses of several classifiers are combined by means of a mechanism that involves the input data (the difference image) under an iterative Bayesian–Markovian framework. The proposed method is evaluated and compared to previously published results using satellite imagery. [ABSTRACT FROM PUBLISHER]

Multi-scale image segmentation and the selection of optimal segmentation parameters are the key processes in the object-oriented information extraction of high-resolution remote sensing images. The accuracy of remote sensing special subject information depends on this extraction. On the basis of WorldView-2 high-resolution data, the optimal segmentation parameters methodof object-oriented image segmentation and high-resolution image information extraction, the following processes were conducted in this study. Firstly, the best combination of the bands and weights was determined for the information extraction of high-resolution remote sensing image. An improved weighted mean-variance method was proposed andused to calculatethe optimal segmentation scale. Thereafter, the best shape factor parameter and compact factor parameters were computed with the use of the control variables and the combination of the heterogeneity and homogeneity indexes. Different types of image segmentation parameters were obtained according to the surface features. The high-resolution remote sensing images were multi-scale segmented with the optimal segmentation parameters. Ahierarchical network structure was established by setting the information extraction rules to achieve object-oriented information extraction. This study presents an effective and practical method that can explain expert input judgment by reproducible quantitative measurements. Furthermore the results of this procedure may be incorporated into a classification scheme. [ABSTRACT FROM AUTHOR]

The need for timely, accurate, and interoperable geospatial information is steadily increasing. In this context, process-based image processing systems will be the initial segment for future’s automatic systems. A process-based system is believed to be a good approach for agricultural purpose because agricultural activities are carried out according to a periodic (annual) cycle. Therefore, a process-based image analysis procedure was designed for routine crop classification for an agricultural region in Kırklareli, Turkey. The process tree developed uses a multi-temporal image data set as an input and gives the final crop classification as an output by using an incremental rule set. The test data set was composed of five images of Satellite Pour l’Observation de la Terre 4 (SPOT 4) data acquired in 2007. Basically, image objects were first extracted and then classified. A rule set was structured depending on class definitions. A decision-based process was executed and formed a multilevel image classification system. The final classification was obtained by merging classes from the appropriate levels where they were extracted. To evaluate the success of the application the accuracy of the classification was assessed. The overall accuracy and kappa index of agreement was found to be 80% and 0.78, respectively. At the end of the study, problems of segmentation and classification operations were discussed and solution approaches were outlined. To assess the process in terms of its scope for automation, the efficiency and success of the rule set were also discussed. [ABSTRACT FROM AUTHOR]

Processing large very high-resolution remote sensing images on resource-constrained devices is a challenging task because of the large size of these data sets. For applications such as environmental monitoring or natural resources management, complex algorithms have to be used to extract information from the images. The memory required to store the images and the data structures of such algorithms may be very high (hundreds of gigabytes) and therefore leads to unfeasibility on commonly available computers. Segmentation algorithms constitute an essential step for the extraction of objects of interest in a scene and will be the topic of the investigation in this paper. The objective of the present work is to adapt image segmentation algorithms for large amounts of data. To overcome the memory issue, large images are usually divided into smaller image tiles, which are processed independently. Region-merging algorithms do not cope well with image tiling since artifacts are present on the tile edges in the final result due to the incoherencies of the regions across the tiles. In this paper, we propose a scalable tile-based framework for region-merging algorithms to segment large images, while ensuring identical results, with respect to processing the whole image at once. We introduce the original concept of the stability margin for a tile. It allows ensuring identical results to those obtained if the whole image had been segmented without tiling. Finally, we discuss the benefits of this framework and demonstrate the scalability of this approach by applying it to real large images. [ABSTRACT FROM PUBLISHER]

Just over a decade has passed since the concept of morphological profile was defined for the analysis of remote sensing images. Since then, the morphological profile has largely proved to be a powerful tool able to model spatial information (e.g., contextual relations) of the image. However, due to the shortcomings of using the morphological profiles, many variants, extensions, and refinements of its definition have appeared stating that the morphological profile is still under continuous development. In this case, recently introduced theoretically sound attribute profiles (APs) can be considered as a generalization of the morphological profile, which is a powerful tool to model spatial information existing in the scene. Although the concept of the AP has been introduced in remote sensing only recently, an extensive literature on its use in different applications and on different types of data has appeared. To that end, the great amount of contributions in the literature that address the application of the AP to many tasks (e.g., classification, object detection, segmentation, change detection, etc.) and to different types of images (e.g., panchromatic, multispectral, and hyperspectral) proves how the AP is an effective and modern tool. The main objective of this survey paper is to recall the concept of the APs along with all its modifications and generalizations with special emphasis on remote sensing image classification and summarize the important aspects of its efficient utilization while also listing potential future works. [ABSTRACT FROM AUTHOR]

Segmentation of real-world remote sensing images is challenging because of the large size of those data, particularly for very high resolution imagery. However, a lot of high-level remote sensing methods rely on segmentation at some point and are therefore difficult to assess at full image scale, for real remote sensing applications. In this paper, we define a new property called stability of segmentation algorithms and demonstrate that piece- or tile-wise computation of a stable segmentation algorithm can be achieved with identical results with respect to processing the whole image at once. We also derive a technique to empirically estimate the stability of a given segmentation algorithm and apply it to four different algorithms. Among those algorithms, the mean-shift algorithm is found to be quite unstable. We propose a modified version of this algorithm enforcing its stability and thus allowing for tile-wise computation with identical results. Finally, we present results of this method and discuss the various trends and applications. [ABSTRACT FROM PUBLISHER]

Segmentation is a widely used operation in very high resolution remote sensing processing such as object based image analysis. Since the available memory resource might be limited, it is often impossible to process a whole satellite image without using piece-wise processing, which in the case of segmentation introduces a huge amount of artifacts. The work presented in this paper introduce a solution to this problem in the case of the Mean-Shift algorithm, which guarantees that piece-wise segmentation results matches exactly those of full image processing at once. First, we define a new property of segmentation algorithms called stability. After proposing a methodology to measure the stability of segmentation algorithms, we demonstrate that among the Mean-Shift, watershed and connected components algorithms, only the latter is stable. Then, we propose a stabilized version of the Mean-Shift algorithm and use it to build a rigorous and exact solution for piece-wise processing of this algorithm. Last, we present some examples demonstrating the usefulness of the proposed method. This method is available in the Orfeo ToolBox free software, and documented in the software guide. [ABSTRACT FROM AUTHOR]

Object detection is an important task in very high-resolution remote sensing image analysis. Traditional detection approaches are often not sufficiently robust in dealing with the variations of targets and sometimes suffer from limited training samples. In this paper, we tackle these two problems by proposing a novel method for object detection based on structural feature description and query expansion. The feature description combines both local and global information of objects. After initial feature extraction from a query image and representative samples, these descriptors are updated through an augmentation process to better describe the object of interest. The object detection step is implemented using a ranking support vector machine (SVM), which converts the detection task to a ranking query task. The ranking SVM is first trained on a small subset of training data with samples automatically ranked based on similarities to the query image. Then, a novel query expansion method is introduced to update the initial object model by active learning with human inputs on ranking of image pairs. Once the query expansion process is completed, which is determined by measuring entropy changes, the model is then applied to the whole target data set in which objects in different classes shall be detected. We evaluate the proposed method on high-resolution satellite images and demonstrate its clear advantages over several other object detection methods. [ABSTRACT FROM PUBLISHER]

Visual navigation is an essential part of planetary rover autonomy. Rock segmentation emerged as an important interdisciplinary topic among image processing, robotics, and mathematical modeling. Rock segmentation is a challenging topic for rover autonomy because of the high computational consumption, real-time requirement, and annotation difficulty. This research proposes a rock segmentation framework and a rock segmentation network (NI-U-Net++) to aid with the visual navigation of rovers. The framework consists of two stages: the pre-training process and the transfer-training process. The pre-training process applies the synthetic algorithm to generate the synthetic images; then, it uses the generated images to pre-train NI-U-Net++. The synthetic algorithm increases the size of the image dataset and provides pixel-level masks—both of which are challenges with machine learning tasks. The pre-training process accomplishes the state-of-the-art compared with the related studies, which achieved an accuracy, intersection over union (IoU), Dice score, and root mean squared error (RMSE) of 99.41%, 0.8991, 0.9459, and 0.0775, respectively. The transfer-training process fine-tunes the pre-trained NI-U-Net++ using the real-life images, which achieved an accuracy, IoU, Dice score, and RMSE of 99.58%, 0.7476, 0.8556, and 0.0557, respectively. Finally, the transfer-trained NI-U-Net++ is integrated into a planetary rover navigation vision and achieves a real-time performance of 32.57 frames per second (or the inference time is 0.0307 s per frame). The framework only manually annotates about 8% (183 images) of the 2250 images in the navigation vision, which is a labor-saving solution for rock segmentation tasks. The proposed rock segmentation framework and NI-U-Net++ improve the performance of the state-of-the-art models. The synthetic algorithm improves the process of creating valid data for the challenge of rock segmentation. All source codes, datasets, and trained models of this research are openly available in Cranfield Online Research Data (CORD). [ABSTRACT FROM AUTHOR]

Machine learning, particularly deep learning (DL), has become a central and state-of-the-art method for several computer vision applications and remote sensing (RS) image processing. Researchers are continually trying to improve the performance of the DL methods by developing new architectural designs of the networks and/or developing new techniques, such as attention mechanisms. Since the attention mechanism has been proposed, regardless of its type, it has been increasingly used for diverse RS applications to improve the performances of the existing DL methods. However, these methods are scattered over different studies impeding the selection and application of the feasible approaches. This study provides an overview of the developed attention mechanisms and how to integrate them with different deep learning neural network architectures. In addition, it aims to investigate the effect of the attention mechanism on deep learning-based RS image processing. We identified and analyzed the advances in the corresponding attention mechanism-based deep learning (At-DL) methods. A systematic literature review was performed to identify the trends in publications, publishers, improved DL methods, data types used, attention types used, overall accuracies achieved using At-DL methods, and extracted the current research directions, weaknesses, and open problems to provide insights and recommendations for future studies. For this, five main research questions were formulated to extract the required data and information from the literature. Furthermore, we categorized the papers regarding the addressed RS image processing tasks (e.g., image classification, object detection, and change detection) and discussed the results within each group. In total, 270 papers were retrieved, of which 176 papers were selected according to the defined exclusion criteria for further analysis and detailed review. The results reveal that most of the papers reported an increase in overall accuracy when using the attention mechanism within the DL methods for image classification, image segmentation, change detection, and object detection using remote sensing images. [ABSTRACT FROM AUTHOR]

Image segmentation plays a significant role in remote sensing image processing. Among numerous segmentation algorithms, the region-merging segmentation algorithm is widely used due to its well-organized structure and outstanding results. Many merging criteria (MC) were designed to improve the accuracy of region-merging segmentation, but each MC has its own shortcomings, which can cause segmentation errors. Segmentation accuracy can be improved by referring to the segmentation results. To achieve this, an approach for detecting and correcting region-merging image segmentation errors is proposed, and then an iterative optimization model is established. The main contributions of this paper are as follows: (1) The conflict types of matching segment pairs are divided into scale-expression conflict (SEC) and region-ownership conflict (ROC), and ROC is more suitable for optimization. (2) An equal-scale local evaluation method was designed to quantify the optimization potential of ROC. (3) A regional anchoring strategy is proposed to preserve the results of the previous iteration optimization. Three QuickBird satellite images of different land-cover types were used for validating the proposed approach. Both unsupervised and supervised evaluation results prove that the proposed approach can effectively improve segmentation accuracy. All explicit and implicit optimization modes are concluded, which further illustrate the stability of the proposed approach. [ABSTRACT FROM AUTHOR]

The volume of remote sensing images continues to grow as image sources become more diversified and with increasing spatial and spectral resolution. The handling of such large-volume datasets, which exceed available CPU memory, in a timely and efficient manner is becoming a challenge for single machines. The distributed cluster provides an effective solution with strong calculation power. There has been an increasing number of big data technologies that have been adopted to deal with large images using mature parallel technology. However, since most commercial big data platforms are not specifically developed for the remote sensing field, two main issues exist in processing large images with big data platforms using a distributed cluster. On the one hand, the quantities and categories of official algorithms used to process remote sensing images in big data platforms are limited compared to large amounts of sequential algorithms. On the other hand, the sequential algorithms employed directly to process large images in parallel over a distributed cluster may lead to incomplete objects in the tile edges and the generation of large communication volumes at the shuffle stage. It is, therefore, necessary to explore the distributed strategy and adapt the sequential algorithms over the distributed cluster. In this research, we employed two seed-based image segmentation algorithms to construct a distributed strategy based on the Spark platform. The proposed strategy focuses on modifying the incomplete objects by processing border areas and reducing the communication volume to a reasonable size by limiting the auxiliary bands and the buffer size to a small range during the shuffle stage. We calculated the F-measure and execution time to evaluate the accuracy and execution efficiency. The statistical data reveal that both segmentation algorithms maintained high accuracy, as achieved in the reference image segmented in the sequential way. Moreover, generally the strategy took less execution time compared to significantly larger auxiliary bands and buffer sizes. The proposed strategy can modify incomplete objects, with execution time being twice as fast as the strategies that do not employ communication volume reduction in the distributed cluster. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicles (UAV) have had significant progress in the last decade, which is applied to many relevant fields because of the progress of aerial image processing and the convenience to explore areas that men cannot reach. Still, as the basis of further applications such as object tracking and terrain classification, semantic image segmentation is one of the most difficult challenges in the field of computer vision. In this paper, we propose a method for urban UAV images semantic segmentation, which utilizes the geographical information of the region of interest in the form of a digital surface model (DSM). We introduce an Affiliated Fusion Conditional Random Field (AF-CRF), which combines the information of visual pictures and DSM, and a multi-scale strategy with attention to improve the segmenting results. The experiments show that the proposed structure performs better than state-of-the-art networks in multiple metrics. [ABSTRACT FROM AUTHOR]

The use of medium resolution, open access, and freely distributed satellite images, such as those of Landsat, is still understudied in the domain of archaeological research, mainly due to restrictions of spatial resolution. This investigation aims to showcase how the synergistic use of Landsat and Sentinel optical sensors can efficiently support archaeological research through object-based image analysis (OBIA), a relatively new scientific trend, as highlighted in the relevant literature, in the domain of remote sensing archaeology. Initially, the fusion of a 30 m spatial resolution Landsat 8 OLI/TIRS Level-2 and a 10 m spatial resolution Sentinel 2 Level-1C optical images, over the archaeological site of "Nea Paphos" in Cyprus, are evaluated in order to improve the spatial resolution of the Landsat image. At this step, various known fusion models are implemented and evaluated, namely Gram–Schmidt, Brovey, principal component analysis (PCA), and hue-saturation-value (HSV) algorithms. In addition, all four 10 m available spectral bands of the Sentinel 2 sensor, namely the blue, green, red, and near-infrared bands (Bands 2 to 4 and Band 8, respectively) were assessed for each of the different fusion models. On the basis of these findings, the next step of the study, focused on the image segmentation process, through the evaluation of different scale factors. The segmentation process is an important step moving from pixel-based to object-based image analysis. The overall results show that the Gram–Schmidt fusion method based on the near-infrared band of the Sentinel 2 (Band 8) at a range of scale factor segmentation to 70 are the optimum parameters for the detection of standing visible monuments, monitoring excavated areas, and detecting buried archaeological remains, without any significant spectral distortion of the original Landsat image. The new 10 m fused Landsat 8 image provides further spatial details of the archaeological site and depicts, through the segmentation process, important details within the landscape under examination. [ABSTRACT FROM AUTHOR]

The extraction of information about individual trees is essential to supporting the growing of fruit in orchard management. Data acquired from spectral sensors mounted on unmanned aerial vehicles (UAVs) have very high spatial and temporal resolution. However, an efficient and reliable method for extracting information about individual trees with irregular tree-crown shapes and a complicated background is lacking. In this study, we developed and tested the performance of an approach, based on UAV imagery, to extracting information about individual trees in an orchard with a complicated background that includes apple trees (Plot 1) and pear trees (Plot 2). The workflow involves the construction of a digital orthophoto map (DOM), digital surface models (DSMs), and digital terrain models (DTMs) using the Structure from Motion (SfM) and Multi-View Stereo (MVS) approaches, as well as the calculation of the Excess Green minus Excess Red Index (ExGR) and the selection of various thresholds. Furthermore, a local-maxima filter method and marker-controlled watershed segmentation were used for the detection and delineation, respectively, of individual trees. The accuracy of the proposed method was evaluated by comparing its results with manual estimates of the numbers of trees and the areas and diameters of tree-crowns, all three of which parameters were obtained from the DOM. The results of the proposed method are in good agreement with these manual estimates: The F-scores for the estimated numbers of individual trees were 99.0% and 99.3% in Plot 1 and Plot 2, respectively, while the Producer's Accuracy (PA) and User's Accuracy (UA) for the delineation of individual tree-crowns were above 95% for both of the plots. For the area of individual tree-crowns, root-mean-square error (RMSE) values of 0.72 m2 and 0.48 m2 were obtained for Plot 1 and Plot 2, respectively, while for the diameter of individual tree-crowns, RMSE values of 0.39 m and 0.26 m were obtained for Plot 1 (339 trees correctly identified) and Plot 2 (203 trees correctly identified), respectively. Both the areas and diameters of individual tree-crowns were overestimated to varying degrees. [ABSTRACT FROM AUTHOR]

Image segmentation is extensively used in remote sensing spectral image processing. Most of the existing region merging methods assess the heterogeneity or homogeneity using global or pre-defined parameters, which lack the flexibility to further improve the goodness-of-fit. Recently, the local spectral angle (SA) threshold was used to produce promising segmentation results. However, this method falls short of considering the inherent relationship between adjacent segments. In order to overcome this limitation, an adaptive SA thresholds methods, which combines the inter-segment and boundary homogeneities of adjacent segment pairs by their respective weights to refine predetermined SA threshold, is employed in a hybrid segmentation framework to enhance the image segmentation accuracy. The proposed method can effectively improve the segmentation accuracy with different kinds of reference objects compared to the conventional segmentation approaches based on the global SA and local SA thresholds. The results of the visual comparison also reveal that our method can match more accurately with reference polygons of varied sizes and types. [ABSTRACT FROM AUTHOR]

Extracting farmland from high spatial resolution remote sensing images is a basic task for agricultural information management. According to Tobler's first law of geography, closer objects have a stronger relation. Meanwhile, due to the scale effect, there are differences on both spatial and attribute scales among different kinds of objects. Thus, it is not appropriate to segment images with unique or fixed parameters for different kinds of objects. In view of this, this paper presents a stratified object-based farmland extraction method, which includes two key processes: one is image region division on a rough scale and the other is scale parameter pre-estimation within local regions. Firstly, the image in RGB color space is converted into HSV color space, and then the texture features of the hue layer are calculated using the grey level co-occurrence matrix method. Thus, the whole image can be divided into different regions based on the texture features, such as the mean and homogeneity. Secondly, within local regions, the optimal spatial scale segmentation parameter was pre-estimated by average local variance and its first-order and second-order rate of change. The optimal attribute scale segmentation parameter can be estimated based on the histogram of local variance. Through stratified regionalization and local segmentation parameters estimation, fine farmland segmentation can be achieved. GF-2 and Quickbird images were used in this paper, and mean-shift and multi-resolution segmentation algorithms were applied as examples to verify the validity of the proposed method. The experimental results have shown that the stratified processing method can release under-segmentation and over-segmentation phenomena to a certain extent, which ultimately benefits the accurate farmland information extraction. [ABSTRACT FROM AUTHOR]

Binary segmentation in remote sensing aims to obtain binary prediction mask classifying each pixel in the given image. Deep learning methods have shown outstanding performance in this task. These existing methods in fully supervised manner need massive high-quality datasets with manual pixel-level annotations. However, the annotations are generally expensive and sometimes unreliable. Recently, using only image-level annotations, weakly supervised methods have proven to be effective in natural imagery, which significantly reduce the dependence on manual fine labeling. In this paper, we review existing methods and propose a novel weakly supervised binary segmentation framework, which is capable of addressing the issue of class imbalance via a balanced binary training strategy. Besides, a weakly supervised feature-fusion network (WSF-Net) is introduced to adapt to the unique characteristics of objects in remote sensing image. The experiments were implemented on two challenging remote sensing datasets: Water dataset and Cloud dataset. Water dataset is acquired by Google Earth with a resolution of 0.5 m, and Cloud dataset is acquired by Gaofen-1 satellite with a resolution of 16 m. The results demonstrate that using only image-level annotations, our method can achieve comparable results to fully supervised methods. [ABSTRACT FROM AUTHOR]