Supervised remote sensing image segmentation using boosted convolutional neural networks

Class-aware feature attention-based semantic segmentation on hyperspectral images

This research explores an innovative approach to segment hyperspectral images. Aclass-aware feature-based attention approach is combined with an enhanced attention-based network, FAttNet is proposed to segment the hyperspectral images semantically. It is introduced to address challenges associated with inaccurate edge segmentation, diverse forms of target inconsistency, and suboptimal predictive efficacy encountered in traditional segmentation networks when applied to semantic segmentation tasks in hyperspectral images. First, the class-aware feature attention procedure is used to improve the extraction and processing of distinct types of semantic information. Subsequently, the spatial attention pyramid is employed in a parallel fashion to improve the correlation between spaces and extract context information from images at different scales. Finally, the segmentation results are refined using the encoder-decoder structure. It enhances precision in delineating distinct land cover patterns. The findings from the experiments demonstrate that FAttNet exhibits superior performance compared to established semantic segmentation networks commonly used. Specifically, on the GaoFen image dataset, FAttNet achieves a higher mean intersection over union (MIoU) of 77.03% and a segmentation accuracy of 87.26% surpassing the performance of the existing network.

A Novel Fuzzy-Based Remote Sensing Image Segmentation Method

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.

The Object Segmentation from the Microstructure of a FSW Dissimilar Weld

Friction stir welding (FSW) is an environmentally friendly, solid-state welding technique. In this research work, we analyze the microstructure of a new type of FSW weld applying a two- stage framework based on image processing algorithms containing a segmentation step and microstructure analysis of objects occurring in different layers. A dual-speed tool as used to prepare the tested weld. In this paper, we present the segmentation method for recognizing areas containing particles forming bands in the microstructure of a dissimilar weld of aluminum alloys made by FSW technology. A digital analysis was performed on the images obtained using an Olympus GX51 light microscope. The image analysis process consisted of basic segmentation methods in conjunction with domain knowledge and object detection located in different layers of a weld using morphological operations and point transformations. These methods proved to be effective in the analysis of the microstructure images corrupted by noise. The segmentation parts as well as single objects were separated enough to analyze the distribution on different layers of the specimen and the variability of shape and size of the underlying microstructures, which was not possible without computer vision support.

A Novel Multi-Scale Attention PFE-UNet for Forest Image Segmentation

The precise segmentation of forest areas is essential for monitoring tasks related to forest exploration, extraction, and statistics. However, the effective and accurate segmentation of forest images will be affected by factors such as blurring and discontinuity of forest boundaries. Therefore, a Pyramid Feature Extraction-UNet network (PFE-UNet) based on traditional UNet is proposed to be applied to end-to-end forest image segmentation. Among them, the Pyramid Feature Extraction module (PFE) is introduced in the network transition layer, which obtains multi-scale forest image information through different receptive fields. The spatial attention module (SA) and the channel-wise attention module (CA) are applied to low-level feature maps and PFE feature maps, respectively, to highlight specific segmentation task features while fusing context information and suppressing irrelevant regions. The standard convolution block is replaced by a novel depthwise separable convolutional unit (DSC Unit), which not only reduces the computational cost but also prevents overfitting. This paper presents an extensive evaluation with the DeepGlobe dataset and a comparative analysis with several state-of-the-art networks. The experimental results show that the PFE-UNet network obtains an accuracy of 94.23% in handling the real-time forest image segmentation, which is significantly higher than other advanced networks. This means that the proposed PFE-UNet also provides a valuable reference for the precise segmentation of forest images.

Combining Deep Semantic Segmentation Network and Graph Convolutional Neural Network for Semantic Segmentation of Remote Sensing Imagery

Although the deep semantic segmentation network (DSSN) has been widely used in remote sensing (RS) image semantic segmentation, it still does not fully mind the spatial relationship cues between objects when extracting deep visual features through convolutional filters and pooling layers. In fact, the spatial distribution between objects from different classes has a strong correlation characteristic. For example, buildings tend to be close to roads. In view of the strong appearance extraction ability of DSSN and the powerful topological relationship modeling capability of the graph convolutional neural network (GCN), a DSSN-GCN framework, which combines the advantages of DSSN and GCN, is proposed in this paper for RS image semantic segmentation. To lift the appearance extraction ability, this paper proposes a new DSSN called the attention residual U-shaped network (AttResUNet), which leverages residual blocks to encode feature maps and the attention module to refine the features. As far as GCN, the graph is built, where graph nodes are denoted by the superpixels and the graph weight is calculated by considering the spectral information and spatial information of the nodes. The AttResUNet is trained to extract the high-level features to initialize the graph nodes. Then the GCN combines features and spatial relationships between nodes to conduct classification. It is worth noting that the usage of spatial relationship knowledge boosts the performance and robustness of the classification module. In addition, benefiting from modeling GCN on the superpixel level, the boundaries of objects are restored to a certain extent and there are less pixel-level noises in the final classification result. Extensive experiments on two publicly open datasets show that DSSN-GCN model outperforms the competitive baseline (i.e., the DSSN model) and the DSSN-GCN when adopting AttResUNet achieves the best performance, which demonstrates the advance of our method.

Image classification based on the linear unmixing and GEOBIA

Geographic Object-Based Image Analysis and linear unmixing are common methods in image classification. The purpose of this study is to analyze the classification efficiency by integrating these two methods in the mountain area. This research selected Jiangle County, Fujian, as a study area. Two Landsat8 OLI images, which covered the county, were used. Linear spectral mixture model, multi-scale segmentation, and decision tree were applied in the classification. After image preprocessing, linear spectral mixture model was used to unmix the image into three fraction images-vegetation, shade, and soil. The principal component analysis and tasseled cap transformation were used to derived three principal components and the brightness, wetness, and greenness. Multi-scale segmentation is applied by eCognition. Under scale 40, the image was divided into vegetation and non-vegetation area, then under scale 20, the vegetation area was divided into different types by integrating the fraction with different methods. The accuracy assessment of the classification map was done using the forestry resource survey and the high-resolution image of Google Earth. This study indicated that the unmixed bands could improve the classification accuracy. The overall classification accuracy was 92.40% with a Kappa coefficient of 0.9032. Therefore, there is a conclusion that this approach is an efficient way to classify different plantation.

Convolutional Neural Network-Based Remote Sensing Images Segmentation Method for Extracting Winter Wheat Spatial Distribution

When extracting winter wheat spatial distribution by using convolutional neural network (CNN) from Gaofen-2 (GF-2) remote sensing images, accurate identification of edge pixel is the key to improving the result accuracy. In this paper, an approach for extracting accurate winter wheat spatial distribution based on CNN is proposed. A hybrid structure convolutional neural network (HSCNN) was first constructed, which consists of two independent sub-networks of different depths. The deeper sub-network was used to extract the pixels present in the interior of the winter wheat field, whereas the shallower sub-network extracts the pixels at the edge of the field. The model was trained by classification-based learning and used in image segmentation for obtaining the distribution of winter wheat. Experiments were performed on 39 GF-2 images of Shandong province captured during 2017–2018, with SegNet and DeepLab as comparison models. As shown by the results, the average accuracy of SegNet, DeepLab, and HSCNN was 0.765, 0.853, and 0.912, respectively. HSCNN was equally as accurate as DeepLab and superior to SegNet for identifying interior pixels, and its identification of the edge pixels was significantly better than the two comparison models, which showed the superiority of HSCNN in the identification of winter wheat spatial distribution.