A Long-Term Video Tracking Method for Group-Housed Pigs
by
and
Qiumei Yang
1,2,
Xiangyang Hui
1,2,
Yigui Huang
1,2,
Miaobin Chen
1,2,
Senpeng Huang
1,2 and
Deqin Xiao
1,2,* 1
College of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, China
2
Key Laboratory of Smart Agricultural Technology in Tropical South China, Ministry of Agriculture and Rural Affairs, Guangzhou 510642, China
*
Author to whom correspondence should be addressed.
Animals 2024, 14(10), 1505; https://doi.org/10.3390/ani14101505
Submission received: 17 April 2024
/
Revised: 9 May 2024
/
Accepted: 17 May 2024
/
Published: 19 May 2024
(This article belongs to the Section Pigs)
Simple Summary
Simple Summary: Pig tracking provides strong support for refined management in pig farms and can assist in realizing customized, automated, and intellectualized management. However, there are many complex factors in actual production that result in pigs not being tracked consistently over time. To address this issue, we proposed a long-term video tracking method for group-housed pigs based on improved StrongSORT. The experimental results proved that our study demonstrates high practicality, catering to the needs of practical production. It improved the efficiency of farming personnel and lays the foundation for the automated monitoring of pigs. Additionally, it is worth mentioning that we have also released a dataset specifically designed for long-term pig tracking in this paper.
Abstract
Pig tracking provides strong support for refined management in pig farms. However, long and continuous multi-pig tracking is still extremely challenging due to occlusion, distortion, and motion blurring in real farming scenarios. This study proposes a long-term video tracking method for group-housed pigs based on improved StrongSORT, which can significantly improve the performance of pig tracking in production scenarios. In addition, this research constructs a 24 h pig tracking video dataset, providing a basis for exploring the effectiveness of long-term tracking algorithms. For object detection, a lightweight pig detection network, YOLO v7-tiny_Pig, improved based on YOLO v7-tiny, is proposed to reduce model parameters and improve detection speed. To address the target association problem, the trajectory management method of StrongSORT is optimized according to the characteristics of the pig tracking task to reduce the tracking identity (ID) switching and improve the stability of the algorithm. The experimental results show that YOLO v7-tiny_Pig ensures detection applicability while reducing parameters by 36.7% compared to YOLO v7-tiny and achieving an average video detection speed of 435 frames per second. In terms of pig tracking, Higher-Order Tracking Accuracy (HOTA), Multi-Object Tracking Accuracy (MOTP), and Identification F1 (IDF1) scores reach 83.16%, 97.6%, and 91.42%, respectively. Compared with the original StrongSORT algorithm, HOTA and IDF1 are improved by 6.19% and 10.89%, respectively, and Identity Switch (IDSW) is reduced by 69%. Our algorithm can achieve the continuous tracking of pigs in real scenarios for up to 24 h. This method provides technical support for non-contact pig automatic monitoring.
Keywords:
pig; object detection; deep learning; multi-object tracking
