VTag: a semi-supervised pipeline for tracking pig activity with a single top-view camera

Abstract

Precision livestock farming has become an important research focus with the rising demand of meat production in the swine industry. Currently, the farming practice is widely conducted by the technology of computer vision (CV), which automates monitoring pig activity solely based on video recordings. Automation is fulfilled by deriving imagery features that can guide CV systems to recognize animals’ body contours, positions, and behavioral categories. Nevertheless, the performance of the CV systems is sensitive to the quality of imagery features. When the CV system is deployed in a variable environment, its performance may decrease as the features are not generalized enough under different illumination conditions. Moreover, most CV systems are established by supervised learning, in which intensive effort in labeling ground truths for the training process is required. Hence, a semi-supervised pipeline, VTag, is developed in this study. The pipeline focuses on long-term tracking of pig activity without requesting any pre-labeled video but a few human supervisions to build a CV system. The pipeline can be rapidly deployed as only one top-view RGB camera is needed for the tracking task. Additionally, the pipeline was released as a software tool with a friendly graphical interface available to general users. Among the presented datasets, the average tracking error was 17.99 centimeters. Besides, with the prediction results, the pig moving distance per unit time can be estimated for activity studies. Lastly, as the motion is monitored, a heat map showing spatial hot spots visited by the pigs can be useful guidance for farming management. The presented pipeline saves massive laborious work in preparing training dataset. The rapid deployment of the tracking system paves the way for pig behavior monitoring.

A Long-Term Video Tracking Method for Group-Housed Pigs

“…Although it has been difficult for existing research to achieve the long-term regular analysis of individual pigs [30], it is valuable for behavioral studies and is beneficial for a deeper understanding of the health status of pigs [31]. In this study, we realized the all-day tracking of pigs.…”

Pig Movement Estimation by Integrating Optical Flow with a Multi-Object Tracking Model

“…These methods primarily concentrate on static behaviors and fail to provide quantified assessments of the current and cumulative movements of individual pigs, i.e., how far each pig moves. The other method harnesses tracking algorithms within the domain of computer vision to monitor the positions of individual pigs and subsequently assess pig movement using the center point of bounding boxes [8,13,14]. As we explained before, the size of bounding boxes is easily changed during the tracking process; thus, it is not reliable to be used for estimating the actual movement of each pig.…”

“…The first approach leverages behavior recognition algorithms [9][10][11][12] to classify various pig activities, encompassing lying, walking, sitting, standing, drinking, etc. The second approach harnesses tracking algorithms [8,13,14] within the domain of computer vision to monitor the positions of individual pigs and subsequently assess pig movement using the center point of bounding boxes. Notably, two pivotal considerations underlie the process of calculating pig movement.…”

Technical note: ShinyAnimalCV: open-source cloud-based web application for object detection, segmentation, and three-dimensional visualization of animals using computer vision

“…For instance, previous studies have applied CV to monitor animal growth by predicting growth and body composition traits ( Doeschl-Wilson et al, 2004 ; Cang et al, 2019 ; Miller et al, 2019 ; Yu et al, 2021 ). Other applications of CV include animal identification ( Andrew et al, 2017 ; Parham et al, 2018 ), tracking ( Ahrendt et al, 2011 ; Chen et al, 2022 ), behavior recognition ( Nasirahmadi et al, 2017 ; Yang et al, 2018 ; Zhang et al, 2019 ; Tsai et al, 2020 ), and posture inference ( Zheng et al, 2018 ; Riekert et al, 2020 ).…”