Triple Attention Mechanism with YOLOv5s for Fish Detection
Wei Long,
Yawen Wang,
Lingxi Hu,
Jintao Zhang,
Chen Zhang,
Linhua Jiang,
Lihong Xu
Affiliations
Wei Long
Zhejiang Province Key Laboratory of Smart Management & Application of Modern Agricultural Resources, Huzhou Key Laboratory of Waters Robotics Technology, School of Information Engineering, Huzhou University, Huzhou 313000, China
Yawen Wang
Zhejiang Province Key Laboratory of Smart Management & Application of Modern Agricultural Resources, Huzhou Key Laboratory of Waters Robotics Technology, School of Information Engineering, Huzhou University, Huzhou 313000, China
Lingxi Hu
Zhejiang Province Key Laboratory of Smart Management & Application of Modern Agricultural Resources, Huzhou Key Laboratory of Waters Robotics Technology, School of Information Engineering, Huzhou University, Huzhou 313000, China
Jintao Zhang
Zhejiang Province Key Laboratory of Smart Management & Application of Modern Agricultural Resources, Huzhou Key Laboratory of Waters Robotics Technology, School of Information Engineering, Huzhou University, Huzhou 313000, China
Chen Zhang
Zhejiang Province Key Laboratory of Smart Management & Application of Modern Agricultural Resources, Huzhou Key Laboratory of Waters Robotics Technology, School of Information Engineering, Huzhou University, Huzhou 313000, China
Linhua Jiang
Zhejiang Province Key Laboratory of Smart Management & Application of Modern Agricultural Resources, Huzhou Key Laboratory of Waters Robotics Technology, School of Information Engineering, Huzhou University, Huzhou 313000, China
Lihong Xu
College of Electronics and Information Engineering, Tongji University, Shanghai 201804, China
Traditional fish farming methods suffer from backward production, low efficiency, low yield, and environmental pollution. As a result of thorough research using deep learning technology, the industrial aquaculture model has experienced gradual maturation. A variety of complex factors makes it difficult to extract effective features, which results in less-than-good model performance. This paper proposes a fish detection method that combines a triple attention mechanism with a You Only Look Once (TAM-YOLO)model. In order to enhance the speed of model training, the process of data encapsulation incorporates positive sample matching. An exponential moving average (EMA) is incorporated into the training process to make the model more robust, and coordinate attention (CA) and a convolutional block attention module are integrated into the YOLOv5s backbone to enhance the feature extraction of channels and spatial locations. The extracted feature maps are input to the PANet path aggregation network, and the underlying information is stacked with the feature maps. The method improves the detection accuracy of underwater blurred and distorted fish images. Experimental results show that the proposed TAM-YOLO model outperforms YOLOv3, YOLOv4, YOLOv5s, YOLOv5m, and SSD, with a mAP value of 95.88%, thus providing a new strategy for fish detection.
