A pig behavior-tracking method based on a multi-channel high-efficiency attention mechanism

Summary: Given that the pig behavior reflects their health status, continuous and precise monitoring of behavior is important for effective health management and welfare protection. To mitigate potential tracking failures during analysis of video footage, we introduced a novel multi-target pig track...

Full description

Saved in:
Bibliographic Details
Main Authors: Qifeng Li, Zhenyuan Zhuo, Ronghua Gao, Rong Wang, Na Zhang, Yan Shi, Tonghui Wu, Weihong Ma
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Agriculture Communications
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2949798124000383
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849219964625485824
author Qifeng Li
Zhenyuan Zhuo
Ronghua Gao
Rong Wang
Na Zhang
Yan Shi
Tonghui Wu
Weihong Ma
author_facet Qifeng Li
Zhenyuan Zhuo
Ronghua Gao
Rong Wang
Na Zhang
Yan Shi
Tonghui Wu
Weihong Ma
author_sort Qifeng Li
collection DOAJ
description Summary: Given that the pig behavior reflects their health status, continuous and precise monitoring of behavior is important for effective health management and welfare protection. To mitigate potential tracking failures during analysis of video footage, we introduced a novel multi-target pig tracking method that consisted of detection and tracking components. The detection model was enhanced with an efficient attention mechanism and a Cross Stage Partial Darknet backbone network, which significantly improved detection accuracy. The tracking component used the Bytetrack algorithm to accurately track the movement trajectories of individual pigs. Together, these components were combined into the Dual-YOLOX-Tiny-ByteTrack (DYTB) model, which demonstrated superior performance in automatic monitoring of pig behaviors compared to previously published approaches. We established multi-object pig tracking datasets with 180,321 images to evaluate this method. The DYTB method achieved a pig detection accuracy of 98.3% and tracking accuracies of 95.3% and 97.1%. Compared to the YOLOX-Tiny-ByteTrack base model, DYTB showed a 3.4% improvement in multiple object tracking accuracy, making it a robust method for non-contact, intelligent monitoring of pig health and contributing to advances in precision livestock farming.
format Article
id doaj-art-d7ccbcc3b0064c8e851e6389f7d2dfc6
institution Kabale University
issn 2949-7981
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Agriculture Communications
spelling doaj-art-d7ccbcc3b0064c8e851e6389f7d2dfc62024-12-25T04:21:43ZengElsevierAgriculture Communications2949-79812024-12-0124100062A pig behavior-tracking method based on a multi-channel high-efficiency attention mechanismQifeng Li0Zhenyuan Zhuo1Ronghua Gao2Rong Wang3Na Zhang4Yan Shi5Tonghui Wu6Weihong Ma7Information Technology Research Centre, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China; Beijing University of Agriculture, Beijing 102206, ChinaInformation Technology Research Centre, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China; Beijing University of Agriculture, Beijing 102206, ChinaInformation Technology Research Centre, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China; Beijing University of Agriculture, Beijing 102206, China; Corresponding author. Information Technology Research Centre, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China.Information Technology Research Centre, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaBeijing University of Agriculture, Beijing 102206, ChinaInformation Technology Research Centre, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China; Northwest Agriculture and Forestry University, Yangling, 712100, ChinaInformation Technology Research Centre, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China; Shanxi Agricultural University, Jinzhong, 030801, ChinaInformation Technology Research Centre, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China; Beijing University of Agriculture, Beijing 102206, ChinaSummary: Given that the pig behavior reflects their health status, continuous and precise monitoring of behavior is important for effective health management and welfare protection. To mitigate potential tracking failures during analysis of video footage, we introduced a novel multi-target pig tracking method that consisted of detection and tracking components. The detection model was enhanced with an efficient attention mechanism and a Cross Stage Partial Darknet backbone network, which significantly improved detection accuracy. The tracking component used the Bytetrack algorithm to accurately track the movement trajectories of individual pigs. Together, these components were combined into the Dual-YOLOX-Tiny-ByteTrack (DYTB) model, which demonstrated superior performance in automatic monitoring of pig behaviors compared to previously published approaches. We established multi-object pig tracking datasets with 180,321 images to evaluate this method. The DYTB method achieved a pig detection accuracy of 98.3% and tracking accuracies of 95.3% and 97.1%. Compared to the YOLOX-Tiny-ByteTrack base model, DYTB showed a 3.4% improvement in multiple object tracking accuracy, making it a robust method for non-contact, intelligent monitoring of pig health and contributing to advances in precision livestock farming.http://www.sciencedirect.com/science/article/pii/S2949798124000383Multi-objectBehavioural trackingTarget detectionByteTrackEfficient attention mechanism
spellingShingle Qifeng Li
Zhenyuan Zhuo
Ronghua Gao
Rong Wang
Na Zhang
Yan Shi
Tonghui Wu
Weihong Ma
A pig behavior-tracking method based on a multi-channel high-efficiency attention mechanism
Agriculture Communications
Multi-object
Behavioural tracking
Target detection
ByteTrack
Efficient attention mechanism
title A pig behavior-tracking method based on a multi-channel high-efficiency attention mechanism
title_full A pig behavior-tracking method based on a multi-channel high-efficiency attention mechanism
title_fullStr A pig behavior-tracking method based on a multi-channel high-efficiency attention mechanism
title_full_unstemmed A pig behavior-tracking method based on a multi-channel high-efficiency attention mechanism
title_short A pig behavior-tracking method based on a multi-channel high-efficiency attention mechanism
title_sort pig behavior tracking method based on a multi channel high efficiency attention mechanism
topic Multi-object
Behavioural tracking
Target detection
ByteTrack
Efficient attention mechanism
url http://www.sciencedirect.com/science/article/pii/S2949798124000383
work_keys_str_mv AT qifengli apigbehaviortrackingmethodbasedonamultichannelhighefficiencyattentionmechanism
AT zhenyuanzhuo apigbehaviortrackingmethodbasedonamultichannelhighefficiencyattentionmechanism
AT ronghuagao apigbehaviortrackingmethodbasedonamultichannelhighefficiencyattentionmechanism
AT rongwang apigbehaviortrackingmethodbasedonamultichannelhighefficiencyattentionmechanism
AT nazhang apigbehaviortrackingmethodbasedonamultichannelhighefficiencyattentionmechanism
AT yanshi apigbehaviortrackingmethodbasedonamultichannelhighefficiencyattentionmechanism
AT tonghuiwu apigbehaviortrackingmethodbasedonamultichannelhighefficiencyattentionmechanism
AT weihongma apigbehaviortrackingmethodbasedonamultichannelhighefficiencyattentionmechanism
AT qifengli pigbehaviortrackingmethodbasedonamultichannelhighefficiencyattentionmechanism
AT zhenyuanzhuo pigbehaviortrackingmethodbasedonamultichannelhighefficiencyattentionmechanism
AT ronghuagao pigbehaviortrackingmethodbasedonamultichannelhighefficiencyattentionmechanism
AT rongwang pigbehaviortrackingmethodbasedonamultichannelhighefficiencyattentionmechanism
AT nazhang pigbehaviortrackingmethodbasedonamultichannelhighefficiencyattentionmechanism
AT yanshi pigbehaviortrackingmethodbasedonamultichannelhighefficiencyattentionmechanism
AT tonghuiwu pigbehaviortrackingmethodbasedonamultichannelhighefficiencyattentionmechanism
AT weihongma pigbehaviortrackingmethodbasedonamultichannelhighefficiencyattentionmechanism