The coastal zone represents a unique interface between land and sea, and addressing the ecological crisis it faces is of global significance. One of the most fundamental and effective measures is to extract the coastline’s location on a large scale, dynamically, and accurately. Remote sensing technology has been widely employed in coastline extraction due to its temporal, spatial, and sensor diversity advantages. Substantial progress has been made in coastline extraction with diversifying data types and information extraction methods. This paper focuses on discussing the research progress related to data sources and extraction methods for remote sensing-based coastline extraction. We summarize the suitability of data and some extraction algorithms for several specific coastline types, including rocky coastlines, sandy coastlines, muddy coastlines, biological coastlines, and artificial coastlines. We also discuss the significant challenges and prospects of coastline dataset construction, remotely sensed data selection, and the applicability of the extraction method. In particular, we propose the idea of extracting coastlines based on the coastline scene knowledge map (CSKG) semantic segmentation method. This review serves as a comprehensive reference for future development and research pertaining to coastal exploitation and management.

Aiming at the characteristics of remote sensing images such as a complex background, a large number of small targets, and various target scales, this paper presents a remote sensing image target detection algorithm based on improved YOLOv8. First, in order to extract more information about small targets in images, we add an extra detection layer for small targets in the backbone network; second, we propose a C2f-E structure based on the Efficient Multi-Scale Attention Module (EMA) to enhance the network’s ability to detect targets of different sizes; and lastly, Wise-IoU is used to replace the CIoU loss function in the original algorithm to improve the robustness of the model. Using our improved algorithm for the detection of multiple target categories in the DOTAv1.0 dataset, the mAP@0.5 value is 82.7%, which is 1.3% higher than that of the original YOLOv8 algorithm. It is proven that the algorithm proposed in this paper can effectively improve target detection accuracy in remote sensing images.

Infrared images are susceptible to interference from a variety of factors during acquisition and transmission, resulting in the inclusion of mixed noise, which seriously affects the accuracy of subsequent vision tasks. To solve this problem, we designed a mixed noise removal algorithm for infrared images based on improved CycleGAN. First, we proposed a ResNet-E Block that incorporates the EMA (Efficient Multi-Scale Attention Module) and build a generator based on it using the skip-connection structure to improve the network’s ability to remove mixed noise of different strengths. Second, we added the PSNR (Peak Signal-to-Noise Ratio) as an extra calculation item of cycle consistency loss, so that the network can effectively retain the detailed information of infrared images while denoising. Finally, we conducted experimental validation on both synthetic noisy images and real noisy images, which proved that our algorithm can effectively remove the mixed noise in infrared images and the denoising effect is better than other similar methods.

With the progress of remote sensing sensors, the quality of optical remote sensing image is significantly improved, and target detection on it can extract rich feature information. However, due to the characteristics of remote sensing image with various target sizes and a large proportion of the number of small targets, increasing the difficulty in target detection for it. In response to this challenge, this paper proposes an improved YOLOv8 algorithm for multi-scale target detection of optical remote sensing images. First, we propose a PSPPF module, which improves the model's ability to adapt to different data distributions; Second, DSConv is introduced into the Backbone structure of YOLOv8 to reduce the complexity of the network while maintaining the performance of model detection; Finally, we replace the original loss function CIoU with MPDIoU to improve the localization accuracy of the prediction box. Applying the improved algorithm to the public dataset NWPU VHR-10, the mAP value of the our algorithm is 95.1%, which is 3.0% higher than that of the original YOLOv8, indicating that the proposed algorithm is able to effectively detect multi-scale targets in optical remote sensing images.