Enhanced camera-based individual pig detection and tracking for smart pig farms

Negative social interactions are harmful for animal health and welfare. It is increasingly important to employ a continuous and effective monitoring system for detecting and tracking individual animals in large-scale farms. Such a system can provide timely alarms for farmers to intervene when damagi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computers and electronics in agriculture 2023-08, Vol.211, p.108009, Article 108009
Hauptverfasser: Guo, Qinghua, Sun, Yue, Orsini, Clémence, Bolhuis, J. Elizabeth, de Vlieg, Jakob, Bijma, Piter, de With, Peter H.N.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Negative social interactions are harmful for animal health and welfare. It is increasingly important to employ a continuous and effective monitoring system for detecting and tracking individual animals in large-scale farms. Such a system can provide timely alarms for farmers to intervene when damaging behavior occurs. Deep learning combined with camera-based monitoring is currently arising in agriculture. In this work, deep neural networks are employed to assist individual pig detection and tracking, which enables further analyzing behavior at the individual pig level. First, three state-of-the-art deep learning-based Multi-Object Tracking (MOT) methods are investigated, namely Joint Detection and Embedding (JDE), FairMOT, and YOLOv5s with DeepSORT. All models facilitate automated and continuous individual detection and tracking. Second, weighted-association algorithms are proposed for each MOT method, in order to optimize the object re-identification (re-ID), and improve the individual animal-tracking performance, especially for reducing the number of identity switches. The proposed weighted-association methods are evaluated on a large manually annotated pig dataset, and compared with the state-of-the-art methods. FairMOT with the proposed weighted association achieves the highest IDF1, the least number of identity switches, and the fastest execution rate. YOLOv5s with DeepSORT results in the highest MOTA and MOTP tracking metrics. These methods show high accuracy and robustness for individual pig tracking, and are promising candidates for continuous multi-object tracking for real use in commercial farms. •Tracking performance in animals declines than in pedestrian.•Additional comparison adding appearance features of pigs are helpful for multi-object re-identification.•Anchor-free detection method reduces identity switches significantly during the tracking procedure.•One-stage multi-object tracking systems are faster than a two-stage multi-object tracking system.
ISSN:0168-1699
1872-7107
DOI:10.1016/j.compag.2023.108009