GCNTrack: A Pig-Tracking Method Based on Skeleton Feature Similarity

Pig tracking contributes to the assessment of pig behaviour and health. However, pig tracking on real farms is very difficult. Owing to incomplete camera field of view (FOV), pigs frequently entering and exiting the camera FOV affect the tracking accuracy. To improve pig-tracking efficiency, we prop...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhaoyang Yin, Zehua Wang, Junhua Ye, Suyin Zhou, Aijun Xu
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Animals
Subjects:
Online Access:https://www.mdpi.com/2076-2615/15/7/1040
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849730948129619968
author Zhaoyang Yin
Zehua Wang
Junhua Ye
Suyin Zhou
Aijun Xu
author_facet Zhaoyang Yin
Zehua Wang
Junhua Ye
Suyin Zhou
Aijun Xu
author_sort Zhaoyang Yin
collection DOAJ
description Pig tracking contributes to the assessment of pig behaviour and health. However, pig tracking on real farms is very difficult. Owing to incomplete camera field of view (FOV), pigs frequently entering and exiting the camera FOV affect the tracking accuracy. To improve pig-tracking efficiency, we propose a pig-tracking method that is based on skeleton feature similarity, which we named GcnTrack. We used YOLOv7-Pose to extract pig skeleton key points and design a dual-tracking strategy. This strategy combines IOU matching and skeleton keypoint-based graph convolutional reidentification (Re-ID) algorithms to track pigs continuously, even when pigs return from outside the FOV. Three identical FOV sets of data that separately included long, medium, and short duration videos were used to test the model and verify its performance. The GcnTrack method achieved a Multiple Object Tracking Accuracy (MOTA) of 84.98% and an identification F1 Score (IDF1) of 82.22% for the first set of videos (short duration, 87 s to 220 s). The tracking precision was 74% for the second set of videos (medium duration, average 302 s). The pigs entered the scene 15.29 times on average, with an average of 6.28 identity switches (IDSs) per pig during the tracking experiments on the third batch set of videos (long duration, 14 min). In conclusion, our method contributes an accurate and reliable pig-tracking solution applied to scenarios with incomplete camera FOV.
format Article
id doaj-art-198600c2a1984a17bd5bed84caa1d65c
institution DOAJ
issn 2076-2615
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Animals
spelling doaj-art-198600c2a1984a17bd5bed84caa1d65c2025-08-20T03:08:43ZengMDPI AGAnimals2076-26152025-04-01157104010.3390/ani15071040GCNTrack: A Pig-Tracking Method Based on Skeleton Feature SimilarityZhaoyang Yin0Zehua Wang1Junhua Ye2Suyin Zhou3Aijun Xu4School of Mathematics and Computer Science, Zhejiang Agriculture and Forestry University, Hangzhou 311300, ChinaSchool of Mathematics and Computer Science, Zhejiang Agriculture and Forestry University, Hangzhou 311300, ChinaSchool of Environmental and Resource Science, Zhejiang Agriculture and Forestry University, Hangzhou 311300, ChinaSchool of Mathematics and Computer Science, Zhejiang Agriculture and Forestry University, Hangzhou 311300, ChinaSchool of Mathematics and Computer Science, Zhejiang Agriculture and Forestry University, Hangzhou 311300, ChinaPig tracking contributes to the assessment of pig behaviour and health. However, pig tracking on real farms is very difficult. Owing to incomplete camera field of view (FOV), pigs frequently entering and exiting the camera FOV affect the tracking accuracy. To improve pig-tracking efficiency, we propose a pig-tracking method that is based on skeleton feature similarity, which we named GcnTrack. We used YOLOv7-Pose to extract pig skeleton key points and design a dual-tracking strategy. This strategy combines IOU matching and skeleton keypoint-based graph convolutional reidentification (Re-ID) algorithms to track pigs continuously, even when pigs return from outside the FOV. Three identical FOV sets of data that separately included long, medium, and short duration videos were used to test the model and verify its performance. The GcnTrack method achieved a Multiple Object Tracking Accuracy (MOTA) of 84.98% and an identification F1 Score (IDF1) of 82.22% for the first set of videos (short duration, 87 s to 220 s). The tracking precision was 74% for the second set of videos (medium duration, average 302 s). The pigs entered the scene 15.29 times on average, with an average of 6.28 identity switches (IDSs) per pig during the tracking experiments on the third batch set of videos (long duration, 14 min). In conclusion, our method contributes an accurate and reliable pig-tracking solution applied to scenarios with incomplete camera FOV.https://www.mdpi.com/2076-2615/15/7/1040pigtrackingre-identificationgraph convolutional networkskeleton
spellingShingle Zhaoyang Yin
Zehua Wang
Junhua Ye
Suyin Zhou
Aijun Xu
GCNTrack: A Pig-Tracking Method Based on Skeleton Feature Similarity
Animals
pig
tracking
re-identification
graph convolutional network
skeleton
title GCNTrack: A Pig-Tracking Method Based on Skeleton Feature Similarity
title_full GCNTrack: A Pig-Tracking Method Based on Skeleton Feature Similarity
title_fullStr GCNTrack: A Pig-Tracking Method Based on Skeleton Feature Similarity
title_full_unstemmed GCNTrack: A Pig-Tracking Method Based on Skeleton Feature Similarity
title_short GCNTrack: A Pig-Tracking Method Based on Skeleton Feature Similarity
title_sort gcntrack a pig tracking method based on skeleton feature similarity
topic pig
tracking
re-identification
graph convolutional network
skeleton
url https://www.mdpi.com/2076-2615/15/7/1040
work_keys_str_mv AT zhaoyangyin gcntrackapigtrackingmethodbasedonskeletonfeaturesimilarity
AT zehuawang gcntrackapigtrackingmethodbasedonskeletonfeaturesimilarity
AT junhuaye gcntrackapigtrackingmethodbasedonskeletonfeaturesimilarity
AT suyinzhou gcntrackapigtrackingmethodbasedonskeletonfeaturesimilarity
AT aijunxu gcntrackapigtrackingmethodbasedonskeletonfeaturesimilarity