基于PigsTrack跟踪器的群养生猪多目标跟踪  

Multi-target tracking of group-housed pigs based on PigsTrack tracker

作　　者：张丽雯 周昊 朱启兵[1] ZHANG Liwen;ZHOU Hao;ZHU Qibing(School of Internet of Things Engineering,Jiangnan University,Wuxi 214122,China)

机构地区：[1]江南大学物联网工程学院,无锡214122

出　　处：《农业工程学报》2023年第16期181-190,共10页Transactions of the Chinese Society of Agricultural Engineering

基　　金：江苏省重点研发-现代农业“基于物联网的智慧设施蛋鸡生产技术集成创新与示范”(BE2018334)。

摘　　要：基于视频的生猪行为跟踪和识别对于实现精细化养殖具有重要价值。为了应对群养生猪多目标跟踪任务中由猪只外观相似、遮挡交互等因素带来的挑战,研究提出了基于PigsTrack跟踪器的群养生猪多目标跟踪方法。PigsTrack跟踪器利用高性能YOLOX网络降低目标误检与漏检率,采用Transformer模型获取具有良好区分特性的目标外观特征;基于OC-SORT(observation-centric sort)的思想,通过集成特征匹配、IoU匹配和遮挡恢复匹配策略实现群养生猪的准确跟踪。基于PBVD(pigs behaviours video dataset)数据集的试验结果表明,PigsTrack跟踪器的HOTA(higher order tracking accuracy),MOTA(multiple object tracking accuracy)和IDF1得分(identification F1 score)分别为85.66%、98.59%和99.57%,相较于现有算法的最高精度,分别提高了3.71、0.03和2.05个百分点,证明了PigsTrack跟踪器在解决外观相似和遮挡交互引起的跟踪过程中身份跳变问题方面的有效性。随后,利用Slowfast网络对PigsTrack跟踪器的跟踪结果进行了典型行为统计,结果显示PigsTrack在群养生猪个体行为统计方面更准确。此外,通过在ABVD(aggressive-behavior video)数据集上的试验,PigsTrack跟踪器的HOTA、MOTA和IDF1得分分别为69.14%、94.82%和90.11%,相对于现有算法的最高精度,提高了5.33、0.57和8.60个百分点,验证了PigsTrack跟踪器在群养生猪跟踪任务中的有效性。总而言之,PigsTrack跟踪器能够有效应对外观相似和遮挡交互等挑战,实现了准确的生猪多目标跟踪,并在行为统计方面展现出更高的准确性,为生猪养殖领域的研究和实际应用提供了有价值的指导。An accurate and rapid identification of pig behavior can play a crucial role in the evaluation of health status and welfare.Individual detection and tracking of pigs can greatly enhance the recognition and statistical analysis of their behaviors in large-scale farming environments.This shift from group to precision management can enable better treatment and care,ultimately leading to the goal of welfare-friendly farming.Nevertheless,the occlusion and poses challenges often remain in the actual scenario of pig farming during object tracking,where the group-raised pigs often overlap and move irregularly with each other.Among them,the current mainstream optimization tracking algorithms(such as ByteTrack)can be used to effectively reduce the missed detection from the occlusion using low-score box matching.But it may increase the false detection.The occlusion recovery matching scheme of the OC-SORT algorithm can be used to significantly reduce the identity changes from the occlusion.However,both algorithms still lack the appearance feature matching,which can easily lead to the target loss in the low frame rate or stuttering videos.The appearance feature matching can be expected to solve occlusion and irregular motion.Unfortunately,the existing convolution-based identity recognition networks often struggle to obtain the appearance features with better discriminatory properties,due to the highly similar appearance of pigs.In this study,a PigsTrack tracker was proposed to further optimize the multi-object tracking for the group-raised pigs in actual scenarios.Firstly,the highperformance detector(YOLOX)was used in the tracker to reduce the false and missed detection rates of pigs in the occluded scenarios.Then,an identity recognition(Re-ID)network was constructed using the Transformer model to extract the appearance features with better discriminative properties.Secondly,the matching strategies of appearance feature,IoU,and occlusion recovery were integrated with the tracker for the accurate tracking of group-raised pigs

关 键 词：跟踪 检测 群养生猪 PigsTrack跟踪器 遮挡恢复匹配 生猪个体行为统计 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] S21[自动化与计算机技术—计算机科学与技术]