Saliency Guided DNL-Yolo for Optical Remote Sensing Images for Off-Shore Ship Detection

Abstract

The complexity of changeable marine backgrounds makes ship detection from satellite remote sensing images a challenging task. The ubiquitous interference of cloud and fog led to missed detection and false-alarms when using imagery-based optical satellite remote sensing. An off-shore ship detection method with scene classification and a saliency-tuned YOLONet is proposed to solve this problem. First, the image blocks are classified into four categories by a density peak clustering algorithm (DPC) according to their grayscale histograms, i.e., cloudless areas, thin cloud areas, scattered clouds areas, and thick cloud areas. Secondly, since the ships can be regarded as salient objects in a marine background, the spectral residue saliency detection method is used to extract prominent targets from different image blocks. Finally, the saliency tuned YOLOv4 network is designed to quickly and accurately detect ships from different marine backgrounds. We validated the proposed method using more than 2000 optical remote sensing images from the GF-1 satellite. The experimental results demonstrated that the proposed method obtained a better detection performance than other state-of-the-art methods.

YOLOv7-Based Anomaly Detection Using Intensity and NG Types in Labeling in Cosmetic Manufacturing Processes

“…Quantum leaps in performance have been realized in the last decade [30]. Different image preprocessing methods are required to perform different tasks such as image sharpening, contrast enhancement, and cloud removal [31]. Data preprocessing is an important part of a deep learning project and is a large part of the overall analytics pipeline [32].…”

Rockburst intensity prediction in underground buildings based on improved spectral clustering algorithm

“…As an important branch of clustering algorithms in unsupervised learning, spectral clustering algorithms have a low sensitivity to sample shapes, which tend to converge to the global optimal and support high-dimensional data (Bai et al, 2021). Therefore, it has been applied to various aspects, including pattern recognition during or before image processing (Shen et al, 2021;Guo et al, 2022), classification and prediction of big data samples (Pellicer-Valero et al, 2020;Wang and Shi, 2021), and segmentation of remote sensing images (Li et al, 2018). The application of spectral clustering has expanded in recent decades, which means that algorithms need to be tailored and improved in time to maintain usability and robustness in specific scenarios.…”