文献类型：期刊文献

英文题名：Multi-Scale Ship Detection Algorithm Based on YOLOv7 for Complex Scene SAR Images

作者：Chen, Zhuo[1];Liu, Chang[1,2];Filaretov, V. F.[2];Yukhimets, D. A.[2]

机构：[1]Guangdong Ocean Univ, Coll Elect & Informat Engn, Zhanjiang 524088, Peoples R China;[2]Russian Acad Sci, Inst Automat & Control Proc, Robot Lab, 5 Radio St, Vladivostok 690041, Russia

年份：2023

卷号：15

期号：8

外文期刊名：REMOTE SENSING

收录：SCI-EXPANDED(收录号：WOS:000978667200001)、、EI(收录号：20231914056217)、Scopus(收录号：2-s2.0-85156101097)、WOS

基金：This article is supported by the 2021 project of Guangdong Province Science and Technology Special Funds ("College Special Project + Task List") Competitive Distribution (2021A05237), by the project of Enhancing School with Innovation of Guangdong Ocean University (230420023 and 080507112201), and by the program for scientific research start-up funds of Guangdong Ocean University (R20065).

语种：英文

外文关键词：complex scenes; synthetic aperture radar (SAR); deep learning; multi-scale ship detection; YOLOv7

外文摘要：Recently, deep learning techniques have been extensively used to detect ships in synthetic aperture radar (SAR) images. The majority of modern algorithms can achieve successful ship detection outcomes when working with multiple-scale ships on a large sea surface. However, there are still issues, such as missed detection and incorrect identification when performing multi-scale ship object detection operations in SAR images of complex scenes. To solve these problems, this paper proposes a complex scenes multi-scale ship detection model, according to YOLOv7, called CSD-YOLO. First, this paper suggests an SAS-FPN module that combines atrous spatial pyramid pooling and shuffle attention, allowing the model to focus on important information and ignore irrelevant information, reduce the feature loss of small ships, and simultaneously fuse the feature maps of ship targets on various SAR image scales, thereby improving detection accuracy and the model's capacity to detect objects at several scales. The model's optimization is then improved with the aid of the SIoU loss function. Finally, thorough tests on the HRSID and SSDD datasets are presented to support our methodology. CSD-YOLO achieves better detection performance than the baseline YOLOv7, with a 98.01% detection accuracy, a 96.18% recall, and a mean average precision (mAP) of 98.60% on SSDD. In addition, in comparative experiments with other deep learning-based methods, in terms of overall performance, CSD-YOLO still performs better.