基于时空流特征融合的俯视视角下奶牛跛行自动检测方法  

Automatic Detection Method of Dairy Cow Lameness from Top-view Based on the Fusion of Spatiotemporal Stream Features

作　　者：代昕 王军号 张翼 王鑫杰[1] 李晏兴 戴百生 沈维政 DAI Xin;WANG Junhao;ZHANG Yi;WANG Xinjie;LI Yanxing;DAI Baisheng;SHEN Weizheng(College of Electrical Engineering and Information,Northeast Agricultural University,Harbin 150030,China;College of Information Engineering,East University of Heilongjiang,Harbin 150086,China)

机构地区：[1]东北农业大学电气与信息学院,黑龙江哈尔滨150030 [2]黑龙江东方学院信息工程学院,黑龙江哈尔滨150086

出　　处：《智慧农业（中英文）》2024年第4期18-28,共11页Smart Agriculture

基　　金：国家自然科学基金项目(32072788);黑龙江省重点研发计划(2022ZX01A24);国家重点研发计划(2023YFD2000700);黑龙江东方学院科研平台支撑项目(PTZCXM2404)。

摘　　要：[目的/意义]奶牛跛行检测是规模化奶牛养殖过程中亟待解决的重要问题,现有方法的检测视角主要以侧视为主。然而,侧视视角存在着难以消除的遮挡问题。本研究主要解决侧视视角下存在的遮挡问题。[方法]提出一种基于时空流特征融合的俯视视角下奶牛跛行检测方法。首先,通过分析深度视频流中跛行奶牛在运动过程中的位姿变化,构建空间流特征图像序列。通过分析跛行奶牛行走时躯体前进和左右摇摆的瞬时速度,利用光流捕获奶牛运动的瞬时速度,构建时间流特征图像序列。将空间流与时间流特征图像组合构建时空流融合特征图像序列。其次,利用卷积块注意力模块(Convolutional Block Attention Module, CBAM)改进PP-TSMv2 (PaddlePaddle-Temporal Shift Module v2)视频动作分类网络,构建奶牛跛行检测模型Cow-TSM (Cow-Temporal Shift Module)。最后,分别在不同输入模态、不同注意力机制、不同视频动作分类网络和现有方法 4个方面对比,进行奶牛跛行实验,以探究所提出方法的优劣性。[结果和讨论]共采集处理了180段奶牛图像序列数据,跛行奶牛与非跛行奶牛视频段数比例为1∶1,所提出模型识别精度达到88.7%,模型大小为22 M,离线推理时间为0.046 s。与主流视频动作分类模型TSM、PP-TSM、PP-TSMv2、SlowFast和TimesFormer模型相比,综合表现最好。同时,以时空流融合特征图像作为输入时,识别精度分别比单时间模态与单空间模态分别提升12%与4.1%,证明本研究中模态融合的有效性。通过与通道注意力(Squeeze-and-Excitation, SE)、卷积核注意力(Selective Kernel, SK)、坐标注意力(Coordinate Attention, CA)与CBAM不同注意力机制进行消融实验,证明利用CBAM注意力机制构建奶牛跛行检测模型效果最佳。最后,与现有跛行检测方法进行对比,所提出的方法同时具有较好的性能和实用性。[结论]本研究能够避免侧视视角下[Objective]The detection of lameness in dairy cows is an important issue that needs to be solved urgently in the process of large-scale dairy farming.Timely detection and effective intervention can reduce the culling rate of young dairy cows,which has important practical significance for increasing the milk production of dairy cows and improving the economic benefits of pastures.Due to the low efficiency and low degree of automation of traditional manual detection and contact sensor detection,the mainstream cow lameness detection method is mainly based on computer vision.The detection perspective of existing computer vision-based cow lameness detection methods is mainly side view,but the side view perspective has limitations that are difficult to eliminate.In the actual detection process,there are problems such as cows blocking each other and difficulty in deployment.The cow lameness detection method from the top view will not be difficult to use on the farm due to occlusion problems.The aim is to solve the occlusion problem under the side view.[Methods]In order to fully explore the movement undulations of the trunk of the cow and the movement information in the time dimension during the walking process of the cow,a cow lameness detection method was proposed from a top view based on fused spatiotemporal flow features.By analyzing the height changes of the lame cow in the depth video stream during movement,a spatial stream feature image sequence was constructed.By analyzing the instantaneous speed of the lame cow's body moving forward and swaying left and right when walking,optical flow was used to capture the instantaneous speed of the cow's movement,and a time flow characteristic image sequence was constructed.The spatial flow and time flow features were combined to construct a fused spatiotemporal flow feature image sequence.Different from traditional image classification tasks,the image sequence of cows walking includes features in both time and space dimensions.There would be a certain distinction between lam

关 键 词：奶牛跛行检测 时空融合 视频动作分类 深度图像 注意力机制 TSM 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]