Search

Water mapping for satellite imagery has been an active research field for many applications, in particular natural disasters such as floods. Synthetic Aperture Radar (SAR) provides high-resolution imagery without constraints on weather conditions. The single-date SAR approach is less accurate than the multi-temporal approach but can produce results more promptly. This paper proposes novel segmentation schemes that are designed to process both a target superpixel and its surrounding ones for the input for machine learning. Mixture-based Superpixel-Shallow Deit-Ti/XGBoost (MISP-SDT/XGB) schemes are devised to generate, annotate, and classify superpixels, and perform the land/water segmentation of SAR imagery. These schemes are applied to Sentinel-1 SAR data to examine segmentation performances. Single/mask/neighborhood models and single/neighborhood models are introduced in the MISP-SDT scheme and the MISP-XGB scheme, respectively. The effects of the contextual information about the target and its neighbor superpixels are assessed on its segmentation performances. Regarding polarization, it is shown that the VH mode produces more encouraging results than the VV, which is consistent with previous studies. Also, under our MISP-SDT/XGP schemes, the neighborhood models show better performances than FCNN models. Overall, the neighborhood model gives better performances than the single model. Results from attention maps and feature importance scores show that neighbor regions are looked at or used by the algorithms in the neighborhood models. Our findings suggest that under our schemes, the contextual information has positive effects on land/water segmentation.

Supervised polarimetric synthetic aperture radar (PolSAR) image classification demands a large amount of precisely labeled data. However, such data are difficult to obtain. Therefore, many unsupervised methods have been proposed for unsupervised PolSAR image classification. The classification maps of unsupervised methods contain many high-confidence samples. These samples, which are often ignored, can be used as supervisory information to improve classification performance on PolSAR images. This study proposes a new unsupervised PolSAR image classification framework. The framework combines high-confidence superpixel pseudo-labeled samples and semi-supervised classification methods. The experiments indicated that this framework could achieve higher-level effectiveness in unsupervised PolSAR image classification. First, superpixel segmentation was performed on PolSAR images, and the geometric centers of the superpixels were generated. Second, the classification maps of rotation-domain deep mutual information (RDDMI), an unsupervised PolSAR image classification method, were used as the pseudo-labels of the central points of the superpixels. Finally, the unlabeled samples and the high-confidence pseudo-labeled samples were used to train an excellent semi-supervised method, similarity matching (SimMatch). Experiments on three real PolSAR datasets illustrated that, compared with the excellent RDDMI, the accuracy of the proposed method was increased by 1.70%, 0.99%, and 0.8%. The proposed framework provides significant performance improvements and is an efficient method for improving unsupervised PolSAR image classification.

The multi-scale representation of remote sensing images is crucial for information extraction, data analysis, and image processing. However, traditional methods such as image pyramid and image filtering often result in the loss of image details, particularly edge information, during the simplification and merging processes at different scales and resolutions. Furthermore, when applied to coastal landforms with rich texture features, such as biologically diverse areas covered with vegetation, these methods struggle to preserve the original texture characteristics. In this study, we propose a new method, multi-scale expression of coastal landforms considering texture features (METF-C), based on computer vision techniques. This method combines superpixel segmentation and texture transfer technology to improve the multi-scale representation of coastal landforms in remote sensing images. First, coastal landform elements are segmented using superpixel technology. Then, global merging is performed by selecting different classes of superpixels, with boundaries smoothed using median filtering and morphological operators. Finally, texture transfer is applied to create a fusion image that maintains both scale and level consistency. Experimental results demonstrate that METF-C outperforms traditional methods by effectively simplifying images while preserving important geomorphic features and maintaining global texture information across multiple scales. This approach offers significant improvements in edge preservation and texture retention, making it a valuable tool for analyzing coastal landforms in remote sensing imagery.

Extracting water bodies from synthetic aperture radar (SAR) images plays a crucial role in the management of water resources, flood monitoring, and other applications. Recently, transformer-based models have been extensively utilized in the remote sensing domain. However, due to regular patch-partition and weak inductive bias, transformer-based models face challenges such as edge serration and high data dependency when used for water body extraction from SAR images. To address these challenges, we introduce a new model, the Superpixel-based Transformer (SPT), based on the adaptive characteristic of superpixels and knowledge constraints of the adjacency matrix. (1) To mitigate edge serration, the SPT replaces regular patch partition with superpixel segmentation to fully utilize the internal homogeneity of superpixels. (2) To reduce data dependency, the SPT incorporates a normalized adjacency matrix between superpixels into the Multi-Layer Perceptron (MLP) to impose knowledge constraints. (3) Additionally, to integrate superpixel-level learning from the SPT with pixel-level learning from the CNN, we combine these two deep networks to form SPT-UNet for water body extraction. The results show that our SPT-UNet is competitive compared with other state-of-the-art extraction models, both in terms of quantitative metrics and visual effects.

The most critical aspect of panorama generation is maintaining local semantic consistency. Objects may be projected from different depths in the captured image. When warping the image to a unified canvas, pixels at the semantic boundaries of the different views are significantly misaligned. We propose two lightweight strategies to address this challenge efficiently. First, the original image is segmented as superpixels rather than regular grids to preserve the structure of each cell. We propose effective cost functions to generate the warp matrix for each superpixel. The warp matrix varies progressively for smooth projection, which contributes to a more faithful reconstruction of object structures. Second, to deal with artifacts introduced by stitching, we use a seam line method tailored to superpixels. The algorithm takes into account the feature similarity of neighborhood superpixels, including color difference, structure and entropy. We also consider the semantic information to avoid semantic misalignment. The optimal solution constrained by the cost functions is obtained under a graph model. The resulting stitched images exhibit improved naturalness. Extensive testing on common panorama stitching datasets is performed on the algorithm. Experimental results show that the proposed algorithm effectively mitigates artifacts, preserves the completeness of semantics and produces panoramic images with a subjective quality that is superior to that of alternative methods.

Given the escalating frequency and severity of global forest fires, it is imperative to develop advanced detection and segmentation technologies to mitigate their impact. To address the challenges of these technologies, the development of deep learning-based forest fire surveillance has significantly accelerated. Nevertheless, the integration of graph convolutional networks (GCNs) in forest fire detection remains relatively underexplored. In this context, we introduce a novel superpixel-based graph convolutional network (SCGCN) for forest fire image segmentation. Our proposed method utilizes superpixels to transform images into a graph structure, thereby reinterpreting the image segmentation challenge as a node classification task. Additionally, we transition the spatial graph convolution operation to a GraphSAGE graph convolution mechanism, mitigating the class imbalance issue and enhancing the network’s versatility. We incorporate an innovative loss function to contend with the inconsistencies in pixel dimensions within superpixel clusters. The efficacy of our technique is validated on two different forest fire datasets, demonstrating superior performance compared to four alternative segmentation methodologies.

Nearshore ship detection has significant applications in both the military and civilian domains. Compared to synthetic aperture radar (SAR), polarimetric synthetic aperture radar (PolSAR) provides richer information for analyzing the scattering mechanisms of ships and enables better detection of ship targets. However, ships in nearshore areas tend to be highly concentrated, and ship detection is often affected by adjacent strong scattering, resulting in false alarms or missed detections. While the GP-PNF detector performs well in PolSAR ship detection, it cannot obtain satisfactory results in these scenarios, and it also struggles in the presence of azimuthal ambiguity or strong clutter interference. To address these challenges, we propose a nearshore ship detection method named ECD-PNF by integrating superpixel-level GP-PNF and refined polarimetric decomposition. Firstly, polarimetric superpixel segmentation and sea–land segmentation are performed to reduce the influence of land on ship detection. To estimate the sea clutter more accurately, an automatic censoring (AC) mechanism combined with superpixels is used to select the sea clutter superpixels. By utilizing refined eight-component polarimetric decomposition to improve the scattering vector, the physical interpretability of the detector is enhanced. Additionally, the expression of polarimetric coherence is improved to enhance the target clutter ratio (TCR). Finally, this paper combines the third eigenvalue of eigenvalue–eigenvector decomposition to reduce the impact of azimuthal ambiguity. Three spaceborne PolSAR datasets from Radarsat-2 and GF-3 are adopted in the experiments for comparison. The proposed ECD-PNF method achieves the highest figure of merit (FoM) value of 0.980, 1.000, and 1.000 for three datasets, validating the effectiveness of the proposed method.

Despite the societal burden of chronic wounds and despite advances in image processing, automated image-based prediction of wound prognosis is not yet in routine clinical practice. While specific tissue types are known to be positive or negative prognostic indicators, image-based wound healing prediction systems that have been demonstrated to date do not (1) use information about the proportions of tissue types within the wound and (2) predict time-to-healing (most predict categorical clinical labels). In this work, we analyzed a unique dataset of time-series images of healing wounds from a controlled study in dogs, as well as human wound images that are annotated for the tissue type composition. In the context of a hybrid-learning approach (neural network segmentation and decision tree regression) for the image-based prediction of time-to-healing, we tested whether explicitly incorporating tissue type-derived features into the model would improve the accuracy for time-to-healing prediction versus not including such features. We tested four deep convolutional encoder–decoder neural network models for wound image segmentation and identified, in the context of both original wound images and an augmented wound image-set, that a SegNet-type network trained on an augmented image set has best segmentation performance. Furthermore, using three different regression algorithms, we evaluated models for predicting wound time-to-healing using features extracted from the four best-performing segmentation models. We found that XGBoost regression using features that are (i) extracted from a SegNet-type network and (ii) reduced using principal components analysis performed the best for time-to-healing prediction. We demonstrated that a neural network model can classify the regions of a wound image as one of four tissue types, and demonstrated that adding features derived from the superpixel classifier improves the performance for healing-time prediction.

Recently, deep learning methods have been widely studied in the field of polarimetric synthetic aperture radar (PolSAR) ship detection. However, extracting polarimetric and spatial features on the whole PolSAR image will result in high computational complexity. In addition, in the massive data ship detection task, the image to be detected contains a large number of invalid areas, such as land and seawater without ships. Therefore, using ship coarse detection methods to quickly locate the potential areas of ships, that is, ship potential area extraction, is an important prerequisite for PolSAR ship detection. Since existing unsupervised PolSAR ship detection methods based on pixel-level features often rely on fine sea–land segmentation pre-processing and have poor applicability to images with complex backgrounds, in order to solve the abovementioned issue, this paper proposes a PolSAR ship potential area extraction method based on the neighborhood semantic differences of an LDA bag-of-words topic model. Specifically, a polarimetric feature suitable for the scattering diversity condition is selected, and a polarimetric feature map is constructed; the superpixel segmentation method is used to generate the bag of words on the feature map, and latent high-level semantic features are extracted and classified with the improved LDA bag-of-words topic model method to obtain the PolSAR ship potential area extraction result, i.e., the PolSAR ship coarse detection result. The experimental results on the self-established PolSAR dataset validate the effectiveness and demonstrate the superiority of our method.

Automatic image segmentation plays an important role in the fields of medical image processing so that these fields constantly put forward higher requirements for the accuracy and speed of segmentation. In order to improve the speed and performance of the segmentation algorithm of medical images, we propose a medical image segmentation algorithm based on simple non-iterative clustering (SNIC). Firstly, obtain the feature map of the image by extracting the texture information of it with feature extraction algorithm; Secondly, reduce the image to a quarter of the original image size by downscaling; Then, the SNIC super-pixel algorithm with texture information and adaptive parameters which used to segment the downscaling image to obtain the superpixel mark map; Finally, restore the superpixel labeled image to the original size through the idea of the nearest neighbor algorithm. Experimental results show that the algorithm uses an improved superpixel segmentation method on downscaling images, which can increase the segmentation speed when segmenting medical images, while ensuring excellent segmentation accuracy.

Evaluating and tracking the size of a wound is a crucial step in wound assessment. The measurement of various indicators on wounds over time plays a vital role in treating and managing crucial wounds. This article introduces the concept of utilizing mobile device-captured photographs to address this challenge. The research explores the application of digital technologies in the treatment of chronic wounds, offering tools to assist healthcare professionals in enhancing patient care and decision-making. Additionally, it investigates the use of deep learning (DL) algorithms along with the use of computer vision techniques to enhance the validation results of wounds. The proposed method involves tissue classification as well as visual recognition system. The wound’s region of interest (RoI) is determined using superpixel techniques, enabling the calculation of its wounded zone. A classification model based on the Region Anchored CNN framework is employed to detect and differentiate wounds and classify their tissues. The outcome demonstrates that the suggested method of DL, with visual methodologies to detect the shape of a wound and measure its size, achieves exceptional results. By utilizing Resnet50, an accuracy of 0.85 percent is obtained, while the Tissue Classification CNN exhibits a Median Deviation Error of 2.91 and a precision range of 0.96%. These outcomes highlight the effectiveness of the methodology in real-world scenarios and its potential to enhance therapeutic treatments for patients with chronic wounds.

The presence of haze significantly degrades the quality of remote sensing images, resulting in issues such as color distortion, reduced contrast, loss of texture, and blurred image edges, which can ultimately lead to the failure of remote sensing application systems. In this paper, we propose a superpixel-based visible remote sensing image dehazing algorithm, namely SRD. To begin, the remote sensing haze images are divided into content-aware patches using superpixels, which cluster adjacent pixels considering their similarities in color and brightness. We assume that each superpixel region shares the same atmospheric light and transmission properties. Subsequently, methods to estimate local atmospheric light and transmission within each superpixel are proposed. Unlike existing dehazing algorithms that assume a globally constant atmospheric light, our approach considers the global heterogeneous distribution of the atmospheric ambient light, which allows us to model it as a global non-uniform variable. Furthermore, we introduce an effective atmospheric light estimation method inspired by the maximum reflectance prior. Moreover, recognizing the wavelength-dependent nature of light transmission, we independently estimate the transmittance for each RGB channel of the input image. The quantitative and qualitative evaluation results of comprehensive experiments on synthetic datasets and real-world samples demonstrate the superior performance of the proposed algorithm compared to state-of-the-art methods for remote sensing image dehazing.

Forests are the most important carbon reservoirs on land, and forest carbon sinks can effectively reduce atmospheric CO2 concentrations and mitigate climate change. In recent years, various satellites have been launched that provide opportunities for identifying forest types with low cost and high time efficiency. Using multi-temporal remote sensing images and combining them with vegetation indices takes into account the vegetation growth pattern and substantially improves the identification accuracy, but it has high requirements for imaging, such as registration, multiple times, etc. Sometimes, it is difficult to satisfy, the plateau area is severely limited by the influence of clouds and rain, and Gaofen (GF) data require more control points for orthophoto correction. The study area was chosen to be Huize County, situated in Qujing City of Yunnan Province, China. The analysis was using the GF and Landsat images. According to deep learning and remote sensing image feature extraction methods, the semantic segmentation method of F-Pix2Pix was proposed, and the domain adaptation method according to transfer learning effectively solved the class imbalance in needleleaf/broadleaf forest identification. The results showed that (1) this method had the best performance and a higher accuracy than the existing products, 21.48% in non-forest/forest and 29.44% in needleleaf/broadleaf forest for MIoU improvement. (2) Applying transfer learning domain adaptation to semantic segmentation showed significant benefits, and this approach utilized satellite images of different resolutions to solve the class imbalance problem. (3) It can be used for long-term monitoring of multiple images and has strong generalization. The identification of needleleaf and broadleaf forests combined with the actual geographical characteristics of the forest provides a foundation for the accurate estimation of regional carbon sources/sinks.

The dimension reduction (DR) technique plays an important role in hyperspectral image (HSI) processing. Among various DR methods, superpixel-based approaches offer flexibility in capturing spectral–spatial information and have shown great potential in HSI tasks. The superpixel-based methods divide the samples into groups and apply the DR technique to the small groups. Nevertheless, we find these methods would increase the intra-class disparity by neglecting the fact the samples from the same class may reside on different superpixels, resulting in performance decay. To address this problem, a novel unsupervised DR named the Collaborative superpixelwise Auto-Encoder (ColAE) is proposed in this paper. The ColAE begins by segmenting the HSI into different homogeneous regions using a superpixel-based method. Then, a set of Auto-Encoders (AEs) is applied to the samples within each superpixel. To reduce the intra-class disparity, a manifold loss is introduced to restrict the samples from the same class, even if located in different superpixels, to have similar representations in the code space. In this way, the compact and discriminative spectral–spatial feature is obtained. Experimental results on three HSI data sets demonstrate the promising performance of ColAE compared to existing state-of-the-art methods.

Multispectral satellite imagery offers a new perspective for spatial modelling, change detection and land cover classification. The increased demand for accurate classification of geographically diverse regions led to advances in object-based methods. A novel spatiotemporal method is presented for object-based land cover classification of satellite imagery using a Graph Neural Network. This paper introduces innovative representation of sequential satellite images as a directed graph by connecting segmented land region through time. The method’s novel modular node classification pipeline utilises the Convolutional Neural Network as a multispectral image feature extraction network, and the Graph Neural Network as a node classification model. To evaluate the performance of the proposed method, we utilised EfficientNetV2-S for feature extraction and the GraphSAGE algorithm with Long Short-Term Memory aggregation for node classification. This innovative application on Sentinel-2 L2A imagery produced complete 4-year intermonthly land cover classification maps for two regions: Graz in Austria, and the region of Portorož, Izola and Koper in Slovenia. The regions were classified with Corine Land Cover classes. In the level 2 classification of the Graz region, the method outperformed the state-of-the-art UNet model, achieving an average F1-score of 0.841 and an accuracy of 0.831, as opposed to UNet’s 0.824 and 0.818, respectively. Similarly, the method demonstrated superior performance over UNet in both regions under the level 1 classification, which contains fewer classes. Individual classes have been classified with accuracies up to 99.17%.

In the field of geoinformation science, multiview, image-based 3D city modeling has developed rapidly, and image depth estimation is an important step in it. To address the problems of the poor adaptability of training models of existing neural network methods and the long reconstruction time of traditional geometric methods, we propose a general depth estimation method for fast 3D city modeling that combines prior knowledge and information propagation. First, the original image is downsampled and input into the neural network to predict the initial depth value. Then, depth plane fitting and joint optimization are combined with the superpixel information and the superpixel optimized depth value is upsampled to the original resolution. Finally, the depth information propagation is checked pixel-by-pixel to obtain the final depth estimate. Experiments were conducted using multiple image datasets taken from actual indoor and outdoor scenes. Our method was compared and analyzed with a variety of existing widely used methods. The experimental results show that our method maintains high reconstruction accuracy and a fast reconstruction speed, and it achieves better performance. This paper offers a framework to integrate neural networks and traditional geometric methods, which provide a new approach for obtaining geographic information and fast 3D city modeling.

Polarimetric synthetic aperture radar (PolSAR) has unique advantages in building extraction due to its sensitivity to building structures and all-time/all-weather imaging capabilities. However, the structure of buildings is complex, and buildings are easily confused with other objects in polarimetric SAR images. The speckle noise of SAR images will affect the accuracy of building extraction. This paper proposes a novel building extraction approach from PolSAR images with statistical texture and polarization features by using a convolutional neural network and superpixel. A feature space that is sensitive to building, including G0 statistical texture and PualiRGB features, is constructed and used as CNN input. Considering that the building boundary of the CNN classification result is inaccurate due to speckle noise, the simple linear iterative cluster (SLIC) superpixel is utilized to constrain the building extraction result. Finally, the effectiveness of the proposed method has been verified by experimenting with PolSAR images from three different sensors, including ESAR, GF-3, and RADARSAT-2. Experiment results show that compared with the other five PolSAR building extraction methods including threshold, SVM, RVCNN, and PFDCNN, our method without superpixel constraint, the F1-score of this method is the highest, reaching 84.22%, 91.24%, and 87.49%, respectively. The false alarm rate of this method is at least 10% lower and the F1 index is at least 6% higher when the building extraction accuracy is comparable. Further, the discussion and method parameter analysis results show that increasing the use of G0 statistical texture parameters can improve building extraction accuracy and reduce false alarms, and the introduction of superpixel constraints can further reduce false alarms.

The timely detection and mapping of surface water bodies from Polarimetric Synthetic Aperture Radar (PolSAR) images are of great significance for emergency management and post-disaster restoration tasks. Though various methods have been proposed in previous years, there are still some inherent flaws. Thus, this paper proposes a new surface water extraction method based on superpixels and Graph Convolutional Networks (GCN). First, the PolSAR images are segmented to generate superpixels as the basic unit of classification, and the graph structure data are established according to their connection to superpixels. Then, the features of each superpixel are extracted. Finally, a GCN is used to classify each superpixel unit using node features and their relationships. This study conducted experiments on a sudden flooding event due to heavy rain and a lake in the city. Detailed verification was carried out. Compared to traditional methods, the recall was improved by 3% while maintaining almost 100% accuracy in complex flood areas. The results show that the proposed method of surface water extraction from PolSAR images has great advantages, acquiring higher accuracy and better boundary adherence in cases of fewer samples. This paper also illustrates the advantage of using GCN to mine the contextual information of classification objects.

Obstacle detection is the primary task of the Advanced Driving Assistance System (ADAS). However, it is very difficult to achieve accurate obstacle detection in complex traffic scenes. To this end, this paper proposes an obstacle detection method based on the local spatial features of point clouds. Firstly, the local spatial point cloud of a superpixel is obtained through stereo matching and the SLIC image segmentation algorithm. Then, the probability of the obstacle in the corresponding area is estimated from the spatial feature information of the local plane normal vector and the superpixel point-cloud height, respectively. Finally, the detection results of the two methods are input into the Bayesian framework in the form of probabilities for the final decision. In order to describe the traffic scene efficiently and accurately, the detection results are further transformed into a multi-layer stixel representation. We carried out experiments on the KITTI dataset and compared several obstacle detection methods. The experimental results indicate that the proposed method has advantages in terms of its Pixel-wise True Positive Rate (PTPR) and Pixel-wise False Positive Rate (PFPR), particularly in complex traffic scenes, such as uneven roads.

Superpixel generation of polarimetric synthetic aperture radar (PolSAR) images is widely used for intelligent interpretation due to its feasibility and efficiency. However, the initial superpixel size setting is commonly neglected, and empirical values are utilized. When prior information is missing, a smaller value will increase the computational burden, while a higher value may result in inferior boundary adherence. Additionally, existing similarity metrics are time-consuming and cannot achieve better segmentation results. To address these issues, a novel strategy is proposed in this article for the first time to construct the function relationship between the initial superpixel size (number of pixels contained in the initial superpixel) and the structural complexity of PolSAR images; additionally, the determinant ratio test (DRT) distance, which is exactly a second form of Wilks’ lambda distribution, is adopted for local clustering to achieve a lower computational burden and competitive accuracy for superpixel generation. Moreover, a hexagonal distribution is exploited to initialize the PolSAR image based on the estimated initial superpixel size, which can further reduce the complexity of locating pixels for relabeling. Extensive experiments conducted on five real-world data sets demonstrate the reliability and generalization of adaptive size estimation, and the proposed superpixel generation method exhibits higher computational efficiency and better-preserved details in heterogeneous regions compared to six other state-of-the-art approaches.

Classification algorithms integrated with convolutional neural networks (CNN) display high accuracies in synthetic aperture radar (SAR) image classification. However, their consideration of spatial information is not comprehensive and effective, which causes poor performance in edges and complex regions. This paper proposes a Markov random field (MRF)-based algorithm for SAR image classification which fully considers the spatial constraints between superpixel regions. Firstly, the initialization of region labels is obtained by the CNN. Secondly, a probability field is constructed to improve the distribution of spatial relationships between adjacent superpixels. Thirdly, a novel region-level MRF is employed to classify the superpixels, which combines the intensity field and probability field in one framework. In our algorithm, the generation of superpixels reduces the misclassification at the pixel level, and region-level misclassification is rectified by the improvement of spatial description. Experimental results on simulated and real SAR images confirm the efficacy of the proposed algorithm for classification.

Nature-inspired artificial intelligence algorithms have been applied to color image quantization (CIQ) for some time. Among these algorithms, the particle swarm optimization algorithm (PSO-CIQ) and its numerous modifications are important in CIQ. In this article, the usefulness of such a modification, labeled IDE-PSO-CIQ and additionally using the idea of individual difference evolution based on the emotional states of particles, is tested. The superiority of this algorithm over the PSO-CIQ algorithm was demonstrated using a set of quality indices based on pixels, patches, and superpixels. Furthermore, both algorithms studied were applied to superpixel versions of quantized images, creating color palettes in much less time. A heuristic method was proposed to select the number of superpixels, depending on the size of the palette. The effectiveness of the proposed algorithms was experimentally verified on a set of benchmark color images. The results obtained from the computational experiments indicate a multiple reduction in computation time for the superpixel methods while maintaining the high quality of the output quantized images, slightly inferior to that obtained with the pixel methods.

Digital/true orthoimage maps (D/TOMs) are one of the most important forms of national spatial data infrastructure (NSDI). The traditional generation of D/TOM is to orthorectify an aerial image into its upright and correct position by deleting displacements on and distortions of imagery. This results in the generated D/TOM having no building façade texture when the D/TOM superimposes on the digital building model (DBM). This phenomenon is no longer tolerated for certain applications, such as micro-climate investigation. For this reason, this paper presents the generation of a true2 orthoimage map (T2OM), which is radically different from the traditional D/TOM. The basic idea for the T2OM generation of a single building is to orthorectify the DBM-based building roof from up to down, the building façade from front to back, from back to front, from left side to right side, and from right side to left side, as well as complete a digital terrain model (DTM)-based T2OM, of which a superpixel is proposed to store building ID, texture ID, the elevation of each pixel, and gray information. Two study areas are applied to verify the methods. The experimental results demonstrate that the T2OM not only maintains the traditional characteristics of D/TOM, but also displays building façade texture and three-dimensional (3D) coordinates (XYZ) measurable at any point, and the accuracy of 3D measurement on a T2OM can achieve 0.025 m (0.3 pixel).

Superpixels could aggregate pixels with similar properties, thus reducing the number of image primitives for subsequent advanced computer vision tasks. Nevertheless, existing algorithms are not effective enough to tackle computing redundancy and inaccurate segmentation. To this end, an optimized superpixel generation framework termed Boundary Awareness and Content Adaptation (BACA) is presented. Firstly, an adaptive seed sampling method based on content complexity is proposed in the initialization stage. Different from the conventional uniform mesh initialization, it takes content differentiation into consideration to incipiently eliminate the redundancy of seed distribution. In addition to the efficient initialization strategy, this work also leverages contour prior information to strengthen the boundary adherence from whole to part. During the similarity calculation of inspecting the unlabeled pixels in the non-iterative clustering framework, a multi-feature associated measurement is put forward to ameliorate the misclassification of boundary pixels. Experimental results indicate that the two optimizations could generate a synergistic effect. The integrated BACA achieves an outstanding under-segmentation error (3.34%) on the BSD dataset over the state-of-the-art performances with a minimum number of superpixels (345). Furthermore, it is not limited to image segmentation and can be facilitated by remote sensing imaging analysis.

Superpixel segmentation for polarimetric synthetic aperture radar (PolSAR) images plays a key role in remote-sensing tasks, such as ship detection and land-cover classification. However, the existing methods cannot directly generate multi-scale superpixels in a hierarchical style and they will take a long time when multi-scale segmentation is executed separately. In this article, we propose an effective and accurate hierarchical superpixel segmentation method, by introducing a minimum spanning tree (MST) algorithm called the Boruvka algorithm. To accurately measure the difference between neighboring pixels, we obtain the scattering mechanism information derived from the model-based refined 5-component decomposition (RFCD) and construct a comprehensive dissimilarity measure. In addition, the edge strength map and homogeneity measurement are considered to make use of the structural and spatial distribution information in the PolSAR image. On this basis, we can generate superpixels using the distance metric along with the MST framework. The proposed method can maintain good segmentation accuracy at multiple scales, and it generates superpixels in real time. According to the experimental results on the ESAR and AIRSAR datasets, our method is faster than the current state-of-the-art algorithms and preserves somewhat more image details in different segmentation scales.

We propose three methods for the color quantization of superpixel images. Prior to the application of each method, the target image is first segmented into a finite number of superpixels by grouping the pixels that are similar in color. The color of a superpixel is given by the arithmetic mean of the colors of all constituent pixels. Following this, the superpixels are quantized using common splitting or clustering methods, such as median cut, k-means, and fuzzy c-means. In this manner, a color palette is generated while the original pixel image undergoes color mapping. The effectiveness of each proposed superpixel method is validated via experimentation using different color images. We compare the proposed methods with state-of-the-art color quantization methods. The results show significantly decreased computation time along with high quality of the quantized images. However, a multi-index evaluation process shows that the image quality is slightly worse than that obtained via pixel methods.

This paper proposes a superpixel spatial intuitionistic fuzzy C-means (SSIFCM) clustering algorithm to address the problems of misclassification, salt and pepper noise, and classification uncertainty arising in the pixel-level unsupervised classification of high spatial resolution remote sensing (HSRRS) images. To reduce information redundancy and ensure noise immunity and image detail preservation, we first use a superpixel segmentation to obtain the local spatial information of the HSRRS image. Secondly, based on the bias-corrected fuzzy C-means (BCFCM) clustering algorithm, the superpixel spatial intuitionistic fuzzy membership matrix is constructed by counting an intuitionistic fuzzy set and spatial function. Finally, to minimize the classification uncertainty, the local relation between adjacent superpixels is used to obtain the classification results according to the spectral features of superpixels. Four HSRRS images of different scenes in the aerial image dataset (AID) are selected to analyze the classification performance, and fifteen main existing unsupervised classification algorithms are used to make inter-comparisons with the proposed SSIFCM algorithm. The results show that the overall accuracy and Kappa coefficients obtained by the proposed SSIFCM algorithm are the best within the inter-comparison of fifteen algorithms, which indicates that the SSIFCM algorithm can effectively improve the classification accuracy of HSRRS image.

Clustering-based methods of polarimetric synthetic aperture radar (PolSAR) image superpixel generation are popular due to their feasibility and parameter controllability. However, these methods pay more attention to improving boundary adherence and are usually time-consuming to generate satisfactory superpixels. To address this issue, a novel cross-iteration strategy is proposed to integrate various advantages of different distances with higher computational efficiency for the first time. Therefore, the revised Wishart distance (RWD), which has better boundary adherence but is time-consuming, is first integrated with the geodesic distance (GD), which has higher efficiency and more regular shape, to form a comprehensive similarity measure via the cross-iteration strategy. This similarity measure is then utilized alternately in the local clustering process according to the difference between two consecutive ratios of the current number of unstable pixels to the total number of unstable pixels, to achieve a lower computational burden and competitive accuracy for superpixel generation. Furthermore, hexagonal initialization is adopted to further reduce the complexity of searching pixels for relabelling in the local regions. Extensive experiments conducted on the AIRSAR, RADARSAT-2 and simulated data sets demonstrate that the proposed method exhibits higher computational efficiency and a more regular shape, resulting in a smooth representation of land cover in homogeneous regions and better-preserved details in heterogeneous regions.

To facilitate measuring crystal sizes during batch crystallization at high-solid concentrations by using an invasive imaging system, an in situ imaging measurement strategy based on edge detection and superpixel is proposed for the ambiguous boundary problem of large amounts of crystals. Firstly, an image filtering is employed to cope with image degradation caused by noise disturbance and suspension turbulence in the crystallizer. Subsequently, an image segmentation method is developed by utilizing improved edge detection and superpixel, which can be easily performed for crystal extraction. Accordingly, crystal size measurement can be developed for evaluation of the crystal size distribution. The experiment results on α-form L-glutamic acid present the effectiveness of the proposed method.

Ship detection in high-resolution synthetic aperture radar (SAR) images has attracted great attention. As a popular method, a constant false alarm rate (CFAR) detection algorithm is widely used. However, the detection performance of CFAR is easily affected by speckle noise. Moreover, the sliding window technique cannot effectively differentiate between clutter and target pixels and easily leads to a high computation load. In this paper, we propose a new superpixel-based non-window CFAR ship detection method for SAR images, which introduces superpixels to CFAR detection to resolve the aforementioned drawbacks. Firstly, our previously proposed fast density-based spatial clustering of applications with noise (DBSCAN) superpixel generation method is utilized to produce the superpixels for SAR images. With the assumption that SAR data obeys gamma distribution, the superpixel dissimilarity is defined. Then, superpixels can be accurately used to estimate the clutter parameters for the tested pixel, even in the multi-target situations, avoiding the drawbacks of the sliding window in the traditional CFAR. Moreover, a local superpixel contrast is proposed to optimize CFAR detection, which can eliminate numerous clutter false alarms, such as man-made urban areas and low bushes. Experimental results with real SAR images indicate that the proposed method can achieve ship detection with a higher speed and accuracy in comparison with other state-of-the-art methods.

Joint sparse representation classification (JSRC) is a representative spectral–spatial classifier for hyperspectral images (HSIs). However, the JSRC is inappropriate for highly heterogeneous areas due to the spatial information being extracted from a fixed-sized neighborhood block, which is often unable to conform to the naturally irregular structure of land cover. To address this problem, a superpixel-based JSRC with nonlocal weighting, i.e., superpixel-based nonlocal weighted JSRC (SNLW-JSRC), is proposed in this paper. In SNLW-JSRC, the superpixel representation of an HSI is first constructed based on an entropy rate segmentation method. This strategy forms homogeneous neighborhoods with naturally irregular structures and alleviates the inclusion of pixels from different classes in the process of spatial information extraction. Afterwards, the superpixel-based nonlocal weighting (SNLW) scheme is built to weigh the superpixel based on its structural and spectral information. In this way, the weight of one specific neighboring pixel is determined by the local structural similarity between the neighboring pixel and the central test pixel. Then, the obtained local weights are used to generate the weighted mean data for each superpixel. Finally, JSRC is used to produce the superpixel-level classification. This speeds up the sparse representation and makes the spatial content more centralized and compact. To verify the proposed SNLW-JSRC method, we conducted experiments on four benchmark hyperspectral datasets, namely Indian Pines, Pavia University, Salinas, and DFC2013. The experimental results suggest that the SNLW-JSRC can achieve better classification results than the other four SRC-based algorithms and the classical support vector machine algorithm. Moreover, the SNLW-JSRC can also outperform the other SRC-based algorithms, even with a small number of training samples.

Lesion segmentation is a critical task in skin cancer analysis and detection. When developing deep learning-based segmentation methods, we need a large number of human-annotated labels to serve as ground truth for model-supervised learning. Due to the complexity of dermatological images and the subjective differences of different dermatologists in decision-making, the labels in the segmentation target boundary region are prone to produce uncertain labels or error labels. These labels may lead to unsatisfactory performance of dermoscopy segmentation. In addition, the model trained by the errored one-hot label may be overconfident, which can lead to arbitrary prediction and model overfitting. In this paper, a superpixel-oriented label distribution learning method is proposed. The superpixels formed by the simple linear iterative cluster (SLIC) algorithm combine one-hot labels constraint and define a distance function to convert it into a soft probability distribution. Referring to the model structure of knowledge distillation, after Superpixel-oriented label distribution learning, we get soft labels with structural prior information. Then the soft labels are transferred as new knowledge to the lesion segmentation network for training. Ours method on ISIC 2018 datasets achieves an Dice coefficient reaching 84%, sensitivity 79.6%, precision 80.4%, improved by 19.3%, 8.6% and 2.5% respectively in comparison with the results of U-Net. We also evaluate our method on the tasks of skin lesion segmentation via several general neural network architectures. The experiments show that ours method improves the performance of network image segmentation and can be easily integrated into most existing deep learning architectures.

The classification accuracy of ground objects is improved due to the combined use of the same scene data collected by different sensors. We propose to fuse the spatial planar distribution and spectral information of the hyperspectral images (HSIs) with the spatial 3D information of the objects captured by light detection and ranging (LiDAR). In this paper, we use the optimized spatial gradient transfer method for data fusion, which can effectively solve the strong heterogeneity of heterogeneous data fusion. The entropy rate superpixel segmentation algorithm over-segments HSI and LiDAR to extract local spatial and elevation information, and a Gaussian density-based regularization strategy normalizes the local spatial and elevation information. Then, the spatial gradient transfer model and l1-total variation minimization are introduced to realize the fusion of local multi-attribute features of different sources, and fully exploit the complementary information of different features for the description of ground objects. Finally, the fused local spatial features are reconstructed into a guided image, and the guided filtering acts on each dimension of the original HSI, so that the output maintains the complete spectral information and detailed changes of the spatial fusion features. It is worth mentioning that we have carried out two versions of expansion on the basis of the proposed method to improve the joint utilization of multi-source data. Experimental results on two real datasets indicated that the fused features of the proposed method have a better effect on ground object classification than the mainstream stacking or cascade fusion methods.

In recent years, with the development of deep learning in remotely sensed big data, semantic segmentation has been widely used in large-scale landcover classification. Landsat imagery has the advantages of wide coverage, easy acquisition, and good quality. However, there are two significant challenges for the semantic segmentation of mid-resolution remote sensing images: the insufficient feature extraction capability of deep convolutional neural network (DCNN); low edge contour accuracy. In this paper, we propose a block shuffle module to enhance the feature extraction capability of DCNN, a differentiable superpixel branch to optimize the feature of small objects and the accuracy of edge contours, and a self-boosting method to fuse semantic information and edge contour information to further optimize the fine-grained edge contour. We label three sets of Landsat landcover classification datasets, and achieved an overall accuracy of 86.3%, 83.2%, and 73.4% on the three datasets, respectively. Compared with other mainstream semantic segmentation networks, our proposed block shuffle network achieves state-of-the-art performance, and has good generalization ability.

Superpixel segmentation has become a crucial pre-processing tool to reduce computation in many computer vision applications. In this paper, a superpixel extraction algorithm based on a seed strategy of contour encoding (SSCE) for infrared images is presented, which can generate superpixels with high boundary adherence and compactness. Specifically, SSCE can solve the problem of superpixels being unable to self-adapt to the image content. First, a contour encoding map is obtained by ray scanning the binary edge map, which ensures that each connected domain belongs to the same homogeneous region. Second, according to the seed sampling strategy, each seed point can be extracted from the contour encoding map. The initial seed set, which is adaptively scattered based on the local structure, is capable of improving the capability of boundary adherence, especially for small regions. Finally, the initial superpixels limited by the image contour are generated by clustering and refined by merging similar adjacent superpixels in the region adjacency graph (RAG) to reduce redundant superpixels. Experimental results on a self-built infrared dataset and the public datasets BSD500 and 3Dircadb demonstrate the generalization ability in grayscale and medical images, and the superiority of the proposed method over several state-of-the-art methods in terms of accuracy and compactness.

Semantic segmentation is one of the significant tasks in understanding aerial images with high spatial resolution. Recently, Graph Neural Network (GNN) and attention mechanism have achieved excellent performance in semantic segmentation tasks in general images and been applied to aerial images. In this paper, we propose a novel Superpixel-based Attention Graph Neural Network (SAGNN) for semantic segmentation of high spatial resolution aerial images. A K-Nearest Neighbor (KNN) graph is constructed from our network for each image, where each node corresponds to a superpixel in the image and is associated with a hidden representation vector. On this basis, the initialization of the hidden representation vector is the appearance feature extracted by a unary Convolutional Neural Network (CNN) from the image. Moreover, relying on the attention mechanism and recursive functions, each node can update its hidden representation according to the current state and the incoming information from its neighbors. The final representation of each node is used to predict the semantic class of each superpixel. The attention mechanism enables graph nodes to differentially aggregate neighbor information, which can extract higher-quality features. Furthermore, the superpixels not only save computational resources, but also maintain object boundary to achieve more accurate predictions. The accuracy of our model on the Potsdam and Vaihingen public datasets exceeds all benchmark approaches, reaching 90.23% and 89.32%, respectively.

Ischemic stroke is one of the leading causes of death among the aged population in the world. Experimental stroke models with rodents play a fundamental role in the investigation of the mechanism and impairment of cerebral ischemia. For its celerity and veracity, the 2,3,5-triphenyltetrazolium chloride (TTC) staining of rat brains has been extensively adopted to visualize the infarction, which is subsequently photographed for further processing. Two important tasks are to segment the brain regions and to compute the midline that separates the brain. This paper investigates automatic brain extraction and hemisphere segmentation algorithms in camera-based TTC-stained rat images. For rat brain extraction, a saliency region detection scheme on a superpixel image is exploited to extract the brain regions from the raw complicated image. Subsequently, the initial brain slices are refined using a parametric deformable model associated with color image transformation. For rat hemisphere segmentation, open curve evolution guided by the gradient vector flow in a medial subimage is developed to compute the midline. A wide variety of TTC-stained rat brain images captured by a smartphone were produced and utilized to evaluate the proposed segmentation frameworks. Experimental results on the segmentation of rat brains and cerebral hemispheres indicated that the developed schemes achieved high accuracy with average Dice scores of 92.33% and 97.15%, respectively. The established segmentation algorithms are believed to be potential and beneficial to facilitate experimental stroke study with TTC-stained rat brain images.

Superixel is one of the most efficient of the image segmentation approaches that are widely used for different applications. In this paper, we developed an image segmentation based on superpixel and an automatic clustering using q-Generalized Pareto distribution under linear normalization (q-GPDL), called ASCQPHGS. The proposed method uses the superpixel algorithm to segment the given image, then the Density Peaks clustering (DPC) is employed to the results obtained from the superpixel algorithm to produce a decision graph. The Hunger games search (HGS) algorithm is employed as a clustering method to segment the image. The proposed method is evaluated using two different datasets, collected form Berkeley segmentation dataset and benchmark (BSDS500) and standford background dataset (SBD). More so, the proposed method is compared to several methods to verify its performance and efficiency. Overall, the proposed method showed significant performance and it outperformed all compared methods using well-known performance metrics.

Obtaining accurate global motion is a crucial step for video stabilization. This paper proposes a robust and simple method to implement global motion estimation. We don’t extend the framework of 2D video stabilization but add a “plug and play” module to motion estimation based on feature points. Firstly, simple linear iterative clustering (SLIC) pre-segmentation is used to obtain superpixels of the video frame, clustering is performed according to the superpixel centroid motion vector and cluster center with large value is eliminated. Secondly, in order to obtain accurate global motion estimation, an improved K-means clustering is proposed. We match the feature points of the remaining superpixels between two adjacent frames, establish a feature points’ motion vector space, and use improved K-means clustering for clustering. Finally, the richest cluster is being retained, and the global motion is obtained by homography transformation. Our proposed method has been verified on different types of videos and has efficient performance than traditional approaches. The stabilization video has an average improvement of 0.24 in the structural similarity index than the original video and 0.1 higher than the traditional method.

As a popular research direction in the field of intelligent transportation, road detection has been extensively concerned by many researchers. However, there are still some key issues in specific applications that need to be further improved, such as the feature processing of road images, the optimal choice of information extraction and detection methods, and the inevitable limitations of detection schemes. In the existing research work, most of the image segmentation algorithms applied to road detection are sensitive to noise data and are prone to generate redundant information or over-segmentation, which makes the computation of segmentation process more complicated. In addition, the algorithm needs to overcome objective factors such as different road conditions and natural environments to ensure certain execution efficiency and segmentation accuracy. In order to improve these issues, we integrate the idea of shallow machine-learning model that clusters first and then classifies in this paper, and a hierarchical multifeature road image segmentation integration framework is proposed. The proposed model has been tested and evaluated on two sets of road datasets based on real scenes and compared with common detection methods, and its effectiveness and accuracy have been verified. Moreover, it demonstrates that the method opens up a new way to enhance the learning and detection capabilities of the model. Most importantly, it has certain potential for application in various practical fields such as intelligent transportation or assisted driving.

Deep learning-based hyperspectral image (HSI) classification has attracted more and more attention because of its excellent classification ability. Generally, the outstanding performance of these methods mainly depends on a large number of labeled samples. Therefore, it still remains an ongoing challenge how to integrate spatial structure information into these frameworks to classify the HSI with limited training samples. In this study, an effective spectral-spatial HSI classification scheme is proposed based on superpixel pooling convolutional neural network with transfer learning (SP-CNN). The suggested method includes three stages. The first part consists of convolution and pooling operation, which is a down-sampling process to extract the main spectral features of an HSI. The second part is composed of up-sampling and superpixel (homogeneous regions with adaptive shape and size) pooling to explore the spatial structure information of an HSI. Finally, the hyperspectral data with each superpixel as a basic input rather than a pixel are fed to fully connected neural network. In this method, the spectral and spatial information is effectively fused by using superpixel pooling technique. The use of popular transfer learning technology in the proposed classification framework significantly improves the training efficiency of SP-CNN. To evaluate the effectiveness of the SP-CNN, extensive experiments were conducted on three common real HSI datasets acquired from different sensors. With 30 labeled pixels per class, the overall classification accuracy provided by this method on three benchmarks all exceeded 93%, which was at least 4.55% higher than that of several state-of-the-art approaches. Experimental and comparative results prove that the proposed algorithm can effectively classify the HSI with limited training labels.

Deep learning (DL) has been shown to obtain superior results for classification tasks in the field of remote sensing hyperspectral imaging. Superpixel-based techniques can be applied to DL, significantly decreasing training and prediction times, but the results are usually far from satisfactory due to overfitting. Data augmentation techniques alleviate the problem by synthetically generating new samples from an existing dataset in order to improve the generalization capabilities of the classification model. In this paper we propose a novel data augmentation framework in the context of superpixel-based DL called dual-window superpixel (DWS). With DWS, data augmentation is performed over patches centered on the superpixels obtained by the application of simple linear iterative clustering (SLIC) superpixel segmentation. DWS is based on dividing the input patches extracted from the superpixels into two regions and independently applying transformations over them. As a result, four different data augmentation techniques are proposed that can be applied to a superpixel-based CNN classification scheme. An extensive comparison in terms of classification accuracy with other data augmentation techniques from the literature using two datasets is also shown. One of the datasets consists of small hyperspectral small scenes commonly found in the literature. The other consists of large multispectral vegetation scenes of river basins. The experimental results show that the proposed approach increases the overall classification accuracy for the selected datasets. In particular, two of the data augmentation techniques introduced, namely, dual-flip and dual-rotate, obtained the best results.

Motivated by applications in topographic map information extraction, our goal was to discover a practical method for scanned topographic map (STM) segmentation. We present an advanced guided watershed transform (AGWT) to generate superpixels on STM. AGWT utilizes the information from both linear and area elements to modify detected boundary maps and sequentially achieve superpixels based on the watershed transform. With achieving an average of 0.06 on under-segmentation error, 0.96 on boundary recall, and 0.95 on boundary precision, it has been proven to have strong ability in boundary adherence, with fewer over-segmentation issues. Based on AGWT, a benchmark for STM segmentation based on superpixels and a shallow convolutional neural network (SCNN), termed SSCNN, is proposed. There are several notable ideas behind the proposed approach. Superpixels are employed to overcome the false color and color aliasing problems that exist in STMs. The unification method of random selection facilitates sufficient training data with little manual labeling while keeping the potential color information of each geographic element. Moreover, with the small number of parameters, SCNN can accurately and efficiently classify those unified pixel sequences. The experiments show that SSCNN achieves an overall F1 score of 0.73 on our STM testing dataset. They also show the quality of the segmentation results and the short run time of this approach, which makes it applicable to full-size maps.

Texture information allows characterizing the regions of interest in a scene. It refers to the spatial organization of the fundamental microstructures in natural images. Texture extraction has been a challenging problem in the field of image processing for decades. In this paper, different techniques based on the classic Bag of Words (BoW) approach for solving the texture extraction problem in the case of hyperspectral images of the Earth surface are proposed. In all cases the texture extraction is performed inside regions of the scene called superpixels and the algorithms profit from the information available in all the bands of the image. The main contribution is the use of superpixel segmentation to obtain irregular patches from the images prior to texture extraction. Texture descriptors are extracted from each superpixel. Three schemes for texture extraction are proposed: codebook-based, descriptor-based, and spectral-enhanced descriptor-based. The first one is based on a codebook generator algorithm, while the other two include additional stages of keypoint detection and description. The evaluation is performed by analyzing the results of a supervised classification using Support Vector Machines (SVM), Random Forest (RF), and Extreme Learning Machines (ELM) after the texture extraction. The results show that the extraction of textures inside superpixels increases the accuracy of the obtained classification map. The proposed techniques are analyzed over different multi and hyperspectral datasets focusing on vegetation species identification. The best classification results for each image in terms of Overall Accuracy (OA) range from 81.07% to 93.77% for images taken at a river area in Galicia (Spain), and from 79.63% to 95.79% for a vast rural region in China with reasonable computation times.

The combination of hyperspectral imaging (HSI) and digital pathology may yield more accurate diagnosis. In this work, we propose the use of superpixels in HS images for combining regions of pixels that can be classified according to their spectral information to classify glioblastoma (GB) brain tumors in histologic slides. The superpixels are generated by a modified simple linear iterative clustering (SLIC) method to accommodate HS images. This work employs a dataset of H&E (Hematoxylin and Eosin) stained histology slides from 13 patients with GB and over 426,000 superpixels. A linear support vector machine (SVM) classifier was performed on independent training, validation, and testing datasets. The results of this investigation show that the proposed method can detect GB brain tumors from non-tumor samples with average sensitivity and specificity of 87% and 81%, respectively. The overall accuracy of this method is 83%. The study demonstrates that hyperspectral digital pathology can be useful for detecting GB brain tumors by exploiting spectral information alone on a superpixel level.

Hyperspectral image (HSI) classification plays an important role in the automatic interpretation of the remotely sensed data. However, it is a non-trivial task to classify HSI accurately and rapidly due to its characteristics of having a large amount of data and massive noise points. To address this problem, in this work, a novel, semi-supervised, superpixel-level classification method for an HSI was proposed based on a graph and discrete potential (SSC-GDP). The key idea of the proposed scheme is the construction of the weighted connectivity graph and the division of the weighted graph. Based on the superpixel segmentation, a weighted connectivity graph is constructed usingthe weighted connection between a superpixel and its spatial neighbors. The generated graph is then divided into different communities/sub-graphs by using a discrete potential and the improved semi-supervised Wu–Huberman (ISWH) algorithm. Each community in the weighted connectivity graph represents a class in the HSI. The local connection strategy, together with the linear complexity of the ISWH algorithm, ensures the fast implementation of the suggested SSC-GDP method. To prove the effectiveness of the proposed spectral–spatial method, two public benchmarks, Indian Pines and Salinas, were utilized to test the performance of our proposal. The comparative test results confirmed that the proposed method was superior to several other state-of-the-art methods.

Deep learning methods have been successfully applied for multispectral and hyperspectral images classification due to their ability to extract hierarchical abstract features. However, the performance of these methods relies heavily on large-scale training samples. In this paper, we propose a three-dimensional spatial-adaptive Siamese residual network (3D-SaSiResNet) that requires fewer samples and still enhances the performance. The proposed method consists of two main steps: construction of 3D spatial-adaptive patches and Siamese residual network for multiband images classification. In the first step, the spectral dimension of the original multiband images is reduced by a stacked autoencoder and superpixels of each band are obtained by the simple linear iterative clustering (SLIC) method. Superpixels of the original multiband image can be finally generated by majority voting. Subsequently, the 3D spatial-adaptive patch of each pixel is extracted from the original multiband image by reference to the previously generated superpixels. In the second step, a Siamese network composed of two 3D residual networks is designed to extract discriminative features for classification and we train the 3D-SaSiResNet by pairwise inputting the training samples into the networks. The testing samples are then fed into the trained 3D-SaSiResNet and the learned features of the testing samples are classified by the nearest neighbor classifier. Experimental results on three multiband image datasets show the feasibility of the proposed method in enhancing classification performance even with limited training samples.

Superpixel segmentation has become a crucial tool in many image processing and computer vision applications. In this paper, a novel content-sensitive superpixel generation algorithm with boundary adjustment is proposed. First, the image local entropy was used to measure the amount of information in the image, and the amount of information was evenly distributed to each seed. It placed more seeds to achieve the lower under-segmentation in content-dense regions, and placed the fewer seeds to increase computational efficiency in content-sparse regions. Second, the Prim algorithm was adopted to generate uniform superpixels efficiently. Third, a boundary adjustment strategy with the adaptive distance further optimized the superpixels to improve the performance of the superpixel. Experimental results on the Berkeley Segmentation Database show that our method outperforms competing methods under evaluation metrics.

The lack of pixel-level labeling limits the practicality of deep learning-based building semantic segmentation. Weakly supervised semantic segmentation based on image-level labeling results in incomplete object regions and missing boundary information. This paper proposes a weakly supervised semantic segmentation method for building detection. The proposed method takes the image-level label as supervision information in a classification network that combines superpixel pooling and multi-scale feature fusion structures. The main advantage of the proposed strategy is its ability to improve the intactness and boundary accuracy of a detected building. Our method achieves impressive results on two 2D semantic labeling datasets, which outperform some competing weakly supervised methods and are close to the result of the fully supervised method.

Oil spill detection plays an important role in marine environment protection. Quad-polarimetric Synthetic Aperture Radar (SAR) has been proved to have great potential for this task, and different SAR polarimetric features have the advantages to recognize oil spill areas from other look-alikes. In this paper we proposed an oil spill detection method based on convolutional neural network (CNN) and Simple Linear Iterative Clustering (SLIC) superpixel. Experiments were conducted on three Single Look Complex (SLC) quad-polarimetric SAR images obtained by Radarsat-2 and Spaceborne Imaging Radar-C/X-Band Synthetic Aperture Radar (SIR-C/X-SAR). Several groups of polarized parameters, including H/A/Alpha decomposition, Single-Bounce Eigenvalue Relative Difference (SERD), correlation coefficients, conformity coefficients, Freeman 3-component decomposition, Yamaguchi 4-component decomposition were extracted as feature sets. Among all considered polarimetric features, Yamaguchi parameters achieved the highest performance with total Mean Intersection over Union (MIoU) of 90.5%. It is proved that the SLIC superpixel method significantly improved the oil spill classification accuracy on all the polarimetric feature sets. The classification accuracy of all kinds of targets types were improved, and the largest increase on mean MIoU of all features sets was on emulsions by 21.9%.