Automated piglet tracking using a single convolutional neural network. (May 2021)

• Record Type: Journal Article
• Authors: Gan, Haiming; Ou, Mingqiang; Zhao, Fengyi; Xu, Chengguo; Li, Shimei; Chen, Changxin; Xue, Yueju
• Is Part Of: Biosystems engineering. Volume 205(2021)
• Page Start: 48
• Page End: 63
• Publication Date: 2021-05
• Subjects: Piglets -- On-line tracking -- Affinity estimation -- Convolutional neural network; Bioengineering -- Periodicals; Agricultural engineering -- Periodicals; Biological systems -- Periodicals; Génie rural -- Périodiques; Systèmes biologiques -- Périodiques; 631
• DOI: 10.1016/j.biosystemseng.2021.02.010
• Languages: English
• ISSNs: 1537-5110

Abstract

Abstract : Piglet tracking is critical to automated piglet behaviour and welfare analysis. Following the tracking-by-detection paradigm, we have developed an online piglet tracking network (OPTN) composed of a base network, a detection head and an association head. The unweaned piglets in video images were detected at the region-based detection head, and the piglet central locations were mapped onto the feature maps produced by the base network and extended network to form central feature vectors. Then the exhaustive central feature vector permutations were input to the affinity estimation network to generate an affinity matrix that accounted for the affinity between the video image pair detections. To make full use of the tracking history, we used the Hungarian algorithm to optimise affinity prediction with affinity accumulation and designed a distance-based tracking state adjustment strategy to correct false state prediction and recovered lost IDs. Our method achieved favourable tracking performance with an IDF1 score and MOTA of 96.55% and 97.04%, respectively, and an inference frame rate of 6.89 fps. Our method outperformed popular MOT methods, such as SORT, SST and CenterTrack, in short video clips and a long video episode. OPTN was robust against large illumination variations with a video rate as low as 1 fps. Our computer vision-based piglet tracking method may aid animal tracking-related behaviour analysis as well as piglet surveillance. Highlights: First use of number of housed animals to universally improve tracking performance. Developed an integrated deep learning network for on-line tracking. Full use made of learning-based features and tracking history. Achieved high tracking accuracy and robustness for low frame rate in challenging dataset.