A computer vision-based method for spatial-temporal action recognition of tail-biting behaviour in group-housed pigs
A computer vision-based method for spatial-temporal action recognition of tail-biting behaviour in group-housed pigs
复制标题
DOI：
10.1016/j.biosystemseng.2020.04.007
复制
发表时间：
2020-07-01
影响因子：
5.1
通讯作者：
Norton, Tomas
中科院分区：
文献类型：
--
作者：
Liu, Dong;Oczak, Maciej;Norton, Tomas
作为一种典型的有害社会行为，咬尾被认为是一个福利减少的问题，对养猪生产的经济后果。在这项研究中，我们采用基于计算机视觉的方法，开发了一种新的方法来自动识别和定位群体饲养的猪咬尾相互作用。该方法采用检测跟踪算法来简化组级行为成对的相互作用。然后，卷积神经网络（CNN）和递归神经网络（RNN）相结合，提取时空特征和分类行为类别。所提出的方法的性能进行了评估，通过量化的定位精度和行为分类精度。结果表明，跟踪检测的方法是能够获得的定位精度为92.71%的咬和受害者的轨迹。CNN和RNN训练的时空特征具有鲁棒性和有效性，分类准确率为96.25%。总的来说，我们提出的方法能够识别和定位群养猪中89.23%的咬尾行为。(C)2020年IAgrE。由爱思唯尔有限公司出版。保留所有权利。
As a typical harmful social behaviour, tail biting is considered to be a welfare-reducing problem with economic consequences for pig production. Taking a computer-vision based approach, in this study, we have developed a novel method to automatically identify and locate tail-biting interactions in group-housed pigs. The method employs a tracking-by-detection algorithm to simplify the group-level behaviour to pairwise interactions. Then, a convolution neural network (CNN) and a recurrent neural network (RNN) are combined to extract the spatial-temporal features and classify behaviour categories. The performance of the proposed method was evaluated by quantifying the localisation accuracy and behaviour classification accuracy. The results demonstrate that the tracking-by-detection approach is capable of obtaining the trajectories of biters and victims with a localisation accuracy of 92.71%. The spatial-temporal features trained by CNN and RNN are robust and effective with a category accuracy of 96.25%. In total, our proposed method is capable to identify and locate 89.23% of tail-biting behaviour in group-housed pigs. (C) 2020 IAgrE. Published by Elsevier Ltd. All rights reserved.