文献类型：期刊文献

英文题名：U-YOLOv7: A network for underwater organism detection

作者：Yu, Guoyan[1,3];Cai, Ruilin[1,2];Su, Jinping[1,2];Hou, Mingxin[1,3];Deng, Ruoling[1,3]

机构：[1]Guangdong Ocean Univ, Sch Mech Engn, Zhanjiang 524088, Guangdong, Peoples R China;[2]Guangdong Ocean Univ, Guangdong Marine Equipment & Mfg Engn Technol Res, Zhanjiang 524088, Guangdong, Peoples R China;[3]Southern Marine Sci & Engn Guangdong Lab, Zhanjiang 524088, Guangdong, Peoples R China

年份：2023

卷号：75

外文期刊名：ECOLOGICAL INFORMATICS

收录：SCI-EXPANDED(收录号：WOS:000988704300001)、、Scopus(收录号：2-s2.0-85153298790)、WOS

基金：The authors would like to thank the reviewers and editors for their time to help improve this paper. This research was supported in part by the Joint Regional Fund Project of Guangdong Province (2019B1515120017), Guangdong Provincial Special Project for Marine Economic Development (Six Major Marine Industries) (GDNRC[2021]42), Zhanjiang Key Laboratory of Modern Marine Fishery Equipment (2021A05023), and Zhanjiang City Innovation and Entrepreneurship Team Luring and Nurturing "Pilot Program" Project (2020LHJH003).

语种：英文

外文关键词：Underwater organism detection; Deep learning; U-YOLOv7; Quantity estimation

外文摘要：Detecting and monitoring underwater organisms is very important for sea aquaculture. The human eye struggles to quickly distinguish between aquatic species due to their variety and dense dispersion. In this paper, a deep learning object detection algorithm based on YOLOv7 is used to design a new network, called Underwater-YOLOv7 (U-YOLOv7), for underwater organism detection. This model satisfies the requirements with regards to both speed and accuracy. First, a network combining CrossConv and an efficient squeeze-excitation module is created. This network increases the extraction of channel information while reducing parameters and enhancing the feature fusion of the network. Second, a lightweight Content-Aware ReAssembly of FEatures (CARAFE) operator is used to obtain more semantic information about underwater images before feature fusion. A 3D attention mechanism is incorporated to improve the anti-interference ability of the model in underwater recognition. Finally, a decoupling head using hybrid convolution is designed to accelerate convergence and improve the accuracy of underwater detection. The results show that the network proposed in this paper obtains an improvement of 3.2% in accuracy, 2.3% in recall, and 2.8% in the mean average precision value and runs at up to 179 fps, far outperforming other advanced networks. Moreover, it has a higher estimation accuracy than the YOLOv7 network.