Detection of tiger puffer using improved YOLOv5 with prior knowledge fusion  

作　　者：Haiqing Li Hong Yu Peng Zhang Haotian Gao Sixue Wei Yaoguang Wei Jingwen Xu Siqi Cheng Junfeng Wu 

机构地区：[1]College of Information Engineering,Dalian Ocean University,Dalian 116023,China [2]Key Laboratory of Facility Fisheries,Ministry of Education(Dalian Ocean University),Dalian 116023,China [3]Liaoning Provincial Key Laboratory of Marine Information Technology,Dalian 116023,China [4]National Innovation Centre for Digital Fishery,China

出　　处：《Information Processing in Agriculture》2024年第3期299-309,共11页农业信息处理(英文)

基　　金：supported by the Key Projects of Educational Department of Liaoning Province(LJKZ0729);National Natural Science Foundation of China(31972846);Liaoning Province Natural Science Foundation(2020-KF-12-09);Foundation of Educational Department of Liaoning Province(LJKZ0730).

摘　　要：Tiger puffer is a commercially important fish cultured in high-density environments,and its accurate detection is indispensable for determining growth conditions and realizing accurate feeding.However,the detection precision and recall of farmed tiger puffer are low due to target blurring and occlusion in real farming environments.The farmed tiger puffer detection model,called knowledge aggregation YOLO(KAYOLO),fuses prior knowledge with improved YOLOv5 and was proposed to solve this problem.To alleviate feature loss caused by target blurring,we drew on the human practice of using prior knowledge for reasoning when recognizing blurred targets and used prior knowledge to strengthen the tiger puffer’s features and improve detection precision.To address missed detection caused by mutual occlusion in high-density farming environments,a prediction box aggregation method,aggregating prediction boxes of the same object,was proposed to reduce the influence among different objects to improve detection recall.To validate the effectiveness of the proposed methods,ablation experiments,model performance experiments,and model robustness experiments were designed.The experimental results showed that KAYOLO’s detection precision and recall results reached 94.92% and 92.21%,respectively.The two indices were improved by 1.29% and 1.35%,respectively,compared to those of YOLOv5.Compared with the recent state-of-the-art underwater object detection models,such as SWIPENet,RoIMix,FERNet,and SK-YOLOv5,KAYOLO achieved 2.09%,1.63%,1.13% and 0.85% higher precision and 1.2%,0.18%,1.74% and 0.39% higher recall,respectively.Experiments were conducted on different datasets to verify the model’s robustness,and the precision and recall of KAYOLO were improved by approximately 1.3% compared to those of YOLOv5.The study showed that KAYOLO effectively enhanced farmed tiger puffer detection by reducing blurring and occlusion effects.Additionally,the model had a strong generalization ability on different datasets,indicating that the model can b

关 键 词：AQUACULTURE Detection of fish Object detection Deep learning Prior knowledge YOLOv5 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] Q95[自动化与计算机技术—计算机科学与技术]