基于Byte的生猪多目标跟踪算法  

Multi-object tracking of pig behavior using byte algorithm

作　　者：王亚彬 徐爱俊[1] 周素茵[1] 叶俊华 WANG Yabin;XU Aijun;ZHOU Suyin;YE Junhua(School of Mathematics and Computer Science,Zhejiang A&F University,Hangzhou 311300,China;School of Environment and Resources,Zhejiang A&F University,Hangzhou 311300,China)

机构地区：[1]浙江农林大学数学与计算机科学学院,杭州311300 [2]浙江农林大学环境与资源学院,杭州311300

出　　处：《农业工程学报》2025年第7期145-155,共11页Transactions of the Chinese Society of Agricultural Engineering

基　　金：浙江省‘领雁’研发攻关计划项目(2022C02050)。

摘　　要：多目标跟踪技术对猪只精细化养殖具有重要意义。针对饲养环境差异、猪只的快速移动以及群猪之间的频繁遮挡带来的多目标跟踪挑战,该研究提出了一种基于Byte的生猪多目标跟踪算法UKFTrack。首先,构建了一个采用定向边界框(oriented bounding box,OBB)标注的多样化数据集,涵盖了猪只多种运动模式以及不同饲养场景和猪群密度;其次,引入了无迹卡尔曼滤波以更好地适配OBB标注,并对传统的状态向量进行扩展,新增了角度和角速度参数,设计了残差函数处理角度变量以避免直接相减所造成的误差。最后,提出了一种多阶段匹配策略,通过多次轨迹关联和补充匹配机制,确保在遮挡严重或剧烈运动的情况下,仍能保持对目标的持续跟踪。试验结果表明,在白天重度密集、白天极度密集、夜间重度密集和夜间极度密集4种复杂场景下,UKFTrack的高阶跟踪精度(higher order tracking accuracy,HOTA)分别为96.10%、83.10%、76.50%和84.00%,IDF1得分(identification F1 score)分别为95.70%、78.20%、70.10%和77.60%。相较于StrongSORT,UKFTrack的HOTA分别提高了1.2、13.3、5.9和6.3个百分点,IDF1分别提高了0.1、10.9、5.4和7.4个百分点。因此,该研究提出的跟踪算法能实现复杂环境下群体生猪的准确跟踪,且展现出较强的鲁棒性,能为实际应用中猪只行为与健康监测提供可靠的技术支持。Pig tracking has been one of the most important steps in precision livestock farming.Especially,some challenges are still remained on the multi-object tracking of pigs.Various factors also included the varying feeding environment,the rapid movements of pigs,and frequent occlusions among them.In this study,a UKFTrack algorithm was proposed using the Byte framework.An advanced unscented kalman filter(UKF)was also introduced to enhance the tracking accuracy and robustness.A multi-stage matching strategy was obtained in complex farming environments.A comprehensive dataset was constructed with the sufficient training data,in order to verify the effectiveness of the UKFTrack algorithm.Oriented bounding boxes(OBB)was then used to annotate the dataset.Diverse patterns of pig motion were observed in different feeding scenarios and densities.These scenarios were ranged from the rapid movements in the high-density farming to the sudden directional changes and nighttime feeding behaviors.The dataset with the considerable size also exceeded the quality,temporal length,and diversity of existing public datasets.Consequently,the robust data support was provided for the research on the multi-object tracking in complex environments of pig farming.A broad range of critical challenges was captured to test the tracking algorithms,such as the occlusions,lighting changes,and interactions between pigs.In terms of UKFTrack algorithm design,an improved version of the UKF was introduced to specifically tailor for the tracking tasks with the OBB annotations.The traditional state vector was extended into the new parameters,such as the angle and angular velocity.A residual function was designed to handle these angular variables.The relatively errors were effectively avoided to significantly improve the tracking accuracy.The errors were typically arisen from directly subtracting angles.Particularly,these errors often occurred when tracking pigs'irregular and abrupt movements in complex environments.Furthermore,the multi-stage matching strategy

关 键 词：猪 多目标跟踪 定向边界框 无迹卡尔曼滤波 UKFTrack 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] S828[自动化与计算机技术—计算机科学与技术]