Change detection is a technique that can observe changes in the surface of the earth dynamically. It is one of the most significant tasks in remote sensing image processing. In the past few years, with the ability of extracting rich deep image features, the deep learning techniques have gained popularity in the field of change detection. In order to obtain obvious image change information, the attention mechanism is added in the decoder and output stage in many deep learning-based methods. Many of these approaches neglect to upgrade the ability of the encoders and the feature extractors to extract the representational features. To resolve this problem, this study proposes a deep multi-scale multi-attention siamese transformer network. A special contextual attention module combining a convolution and self-attention module is introduced into the siamese feature extractor to enhance the global representation ability. A lightly efficient channel attention block is added in the siamese feature extractor to obtain the information interaction among different channels. Furthermore, a multi-scale feature fusion module is proposed to fuse the features from different stages of the siamese feature extractor, and it can detect objects of different sizes and irregularities. To increase the accuracy of the proposed approach, the transformer module is utilized to model the long-range context in two-phase images. The experimental results on the LEVIR-CD and the CCD datasets show the effectiveness of the proposed network.

Deep learning-based approaches play important roles and achieve impressive performances in remote sensing image change detection. Most of the networks are designed by the researchers with rich experiences. It is difficult to design the fixed networks with universal and good performance on various datasets. Regarding this issue, this study presents a transformer architecture search for remote sensing image change detection. The transformer architectures can be designed automatically by a two-stage transformer architecture search. The first stage can search for the effective combinations of attention mechanisms, while the second stage can identify the suitable combinations of multi-scale modules. A gradient-based optimization method is employed for enabling the stable and efficient transformer architecture search. The experiments on various change detection datasets can verify the effectiveness of this work.

This paper presents an unsupervised fuzzy clustering based on evolutionary algorithm for image segmentation. It needs no prior information about exact numbers of segments. Local and nonlocal spatial information derived from observed images are incorporated into fuzzy clustering process. It consists of three major procedures. First, a multi-objective evolutionary sampling is proposed to locate image pixels with a variety of image information. Secondly, optimizing fuzzy compactness and fuzzy separation, a multi-objective evolutionary fuzzy clustering with spatial information is performed on sampling pixels. The particular numbers of segments and balances of spatial information can be obtained. Then fuzzy clustering segmentation on whole image is carried out by two fuzzy clustering approaches, which are depended on fuzzy c-means and evolutionary algorithm respectively. To enhance qualities of final segmentation results, a label correction based on entropy and local spatial information is introduced. Experiments on different types of images demonstrate the effectiveness of our approach for image segmentation.

Superpixel segmentation has been widely used in the field of computer vision. The generations of PolSAR superpixels have also been widely studied for their feasibility and high efficiency. The initial numbers of PolSAR superpixels are usually designed manually by experience, which has a significant impact on the final performance of superpixel segmentation and the subsequent interpretation tasks. Additionally, the effective information of PolSAR superpixels is not fully analyzed and utilized in the generation process. Regarding these issues, a multiobjective evolutionary superpixel segmentation for PolSAR image classification is proposed in this study. It contains two layers, an automatic optimization layer and a fine segmentation layer. Fully considering the similarity information within the superpixels and the difference information among the superpixels simultaneously, the automatic optimization layer can determine the suitable number of superpixels automatically by the multiobjective optimization for PolSAR superpixel segmentation. Considering the difficulty of the search for accurate boundaries of complex ground objects in PolSAR images, the fine segmentation layer can further improve the qualities of superpixels by fully using the boundary information of good-quality superpixels in the evolution process for generating PolSAR superpixels. The experiments on different PolSAR image datasets validate that the proposed approach can automatically generate high-quality superpixels without any prior information.