渔业现代化2025，Vol.52Issue(6)：115-122,8.DOI:10.26958/j.cnki.1007-9580.2025.06.014
基于声呐图像与双流时空注意力的鱼类摄食行为识别
Fish feeding behavior recognition based on sonar images and dual-stream spatio-temporal attention
摘要
Abstract
Aiming at the problems of significant noise interference in sonar images and insufficient representation capability under small-sample conditions in fish feeding behavior recognition,this paper proposes a dual-stream spatio-temporal attention network that fuses domain knowledge and deep features.First,an improved wavelet filtering algorithm is proposed to effectively remove bubble noise in sonar images.Then,a dual-stream feature fusion architecture is designed,where the statistical feature stream includes 6-dimensional features such as target quantity and spacing standard deviation,and the deep feature stream extracts high-order semantic features of sonar images through the Residual Network(ResNet18).Meanwhile,a Long Short-Term Memory network(LSTM)is introduced to capture the temporal dependency of behavior sequences,and a spatio-temporal cross-attention mechanism is combined to adaptively focus on key frames and target areas.Experiments on the self-built dataset show that the classification accuracy of this network reaches 77.0%,among which wavelet denoising,dual-stream fusion,and spatio-temporal attention mechanism contribute precision improvements of 1.8%,5.9%,and 2.8%respectively,verifying the effectiveness of each component.This study provides a new method for underwater target behavior recognition.关键词
声呐图像/小波去噪/特征融合/LSTM/时空交叉注意力Key words
sonar image/wavelet denoising/feature fusion/LSTM/spatio-temporal cross-attention分类
农业科技引用本文复制引用
王志俊,赵霞..基于声呐图像与双流时空注意力的鱼类摄食行为识别[J].渔业现代化,2025,52(6):115-122,8.基金项目
国家重点研发计划(2023YFD2401304) （2023YFD2401304）
