基于改进YOLOv7-tiny和动态检测门的金枪鱼自动检测与计数研究

A study of automatically detecting and counting tunas based on improved YOLOv7-tiny and dynamic detection gate

远洋渔业仍面临自动化、智能化水平偏低等问题,渔获量统计仍普遍采用人工计数。为解决远洋金枪鱼渔业中人工统计渔获量费时费力的问题,本研究提出一种基于DP-YOLO(DCNv2-PConv-YOLO)模型与动态检测门算法相结合的自动计数方法。该方法选用YOLOv7-tiny作为基础模型,采用可变形卷积DCNv2获取更多形状特征,使用部分卷积PConv降低计算量,设计动态检测门算法避免重复计数,同时提出错计误差指标评估计数方法。消融试验结果显示,DP-YOLO相比YOLOv7-tiny减少了3.3%的参数,23.7%的计算量和2.1%计算时间,提高了5.3%平均精度;渔获量自动统计试验结果表明,该计数方法的识别准确率达到95.8%,计数精度达到97.9%,错计误差仅为2.1%,相比YOLOv5s+Deepsort与YOLOv7-tiny+Deepsort已有的计数算法,分别领先45.8%和25%,为远洋渔业的渔获量自动统计提供了新的思路。

Pelagic fishery is still faced with the problems of low automation and intelligence levels.As the traditional method of catch statistics is counting by people,which wastes time and energy,automatic catch statistics has become one of the hot spots in the study of pelagic fisheries.To solve this problem in the pelagic tuna fishery,this paper presents an automatic counting method based on the DP-YOLO(DCNv2-PConv-YOLO)model combined with a dynamic detection gate algorithm.Due to the lightweight nature of YOLOv7-tiny,it is treated as a baseline model.Using deformable convolution,DCNv2 can obtain more shape features.To alleviate the speed decrease caused by adopting DCNv2 and ensure that it can work on edge devices,partial convolution PConv replace replace regular convolution to improve detection speed,and reduce the hardware s model computation and performance demands.The dynamic detection gate algorithm is designed to avoid repeated counting.Meanwhile,a new miscounting error index called ECE(Error Counting Error)is proposed to evaluate the counting method.To verify the influence of the module on YOLOv7-tiny,ablation test results show that DP-YOLO not only reduces 3.3%of parameters,23.7%of calculation time and 2.1%of calculation time,but also increases the average accuracy by 5.3%.The test results of automatic catch statistics show that the identification accuracy of this method is 95.8%,the counting accuracy achieves 97.9%,and ECE is only 2.1%,which is respectively 45.8%and 25%higher than the existing counting algorithms of YOLOv5s+Deepsort and YOLOv7-tiny+Deepsort.This algorithm provides a novel method of automatic counting catch for pelagic fishery.Therefore,the study can meet the catch statistics requirements of tuna longline fishing.