文献类型：期刊文献

英文题名：UM-YOLOv10: Underwater Object Detection Algorithm for Marine Environment Based on YOLOv10 Model

作者：Mai, Rengui[1];Wang, Ji[2]

机构：[1]Guangdong Ocean Univ, Coll Math & Comp Sci, Zhanjiang 524091, Peoples R China;[2]Guangdong Ocean Univ, Coll Elect & Informat Engn, Zhanjiang 524091, Peoples R China

年份：2025

卷号：10

期号：4

外文期刊名：FISHES

收录：SCI-EXPANDED(收录号：WOS:001474981200001)、、Scopus(收录号：2-s2.0-105003488965)、WOS

基金：This research was funded by the New Generation Information Technology Special Project in Key Fields of Ordinary Universities in Guangdong Province, grant number 2020ZDZX3008.

语种：英文

外文关键词：biological target detection; complex marine environments; R-AM; improved YOLOv10

外文摘要：In order to address the challenges of a low detection accuracy, missed detections, and false detections in marine precious biological target detection within complex marine environments, this paper presents a novel residual attention module called R-AM. This module is integrated into the backbone network of the YOLOv10 model to improve the model's focus on the detailed features of biological targets during feature extraction. Additionally, the introduction of a bidirectional feature pyramid with adaptive feature fusion in the neck network enhances the integration of semantic information from deep layers, and localization cues from shallow layers improve the model's ability to distinguish targets from their environments. The experimental data showed that the improved YOLOv10 model achieved 92.89% at mAP@0.5, increasing by 1.31% compared to the original YOLOv10 model. Additionally, the mAP@0.5:0.95 was 77.13%, indicating a 3.71% improvement over the original YOLOv10 model. When compared to the Faster R-CNN, SSD, RetinaNet, YOLOv6, and YOLOv7 models, the enhanced model exhibited increases of 1.5%, 1.7%, 4.06%, 4.7%, and 1.42% in mAP@0.5, respectively. This demonstrates a high detection accuracy and robust stability in complex seabed environments, providing valuable technical support for the scientific management of marine resources in underwater ranches.