Small Target Ewe Behavior Recognition Based on ELFN-YOLO

In response to the poor performance of long-distance small target recognition tasks and real-time intelligent monitoring, this paper proposes a deep learning-based recognition method aimed at improving the ability to recognize and monitor various behaviors of captive ewes. Additionally, we have deve...

Full description

Saved in:
Bibliographic Details
Main Authors: Jianglin Wu, Shufeng Li, Baoqin Wen, Jing Nie, Na Liu, Honglei Cen, Jingbin Li, Shuangyin Liu
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Agriculture
Subjects:
Online Access:https://www.mdpi.com/2077-0472/14/12/2272
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846106439450361856
author Jianglin Wu
Shufeng Li
Baoqin Wen
Jing Nie
Na Liu
Honglei Cen
Jingbin Li
Shuangyin Liu
author_facet Jianglin Wu
Shufeng Li
Baoqin Wen
Jing Nie
Na Liu
Honglei Cen
Jingbin Li
Shuangyin Liu
author_sort Jianglin Wu
collection DOAJ
description In response to the poor performance of long-distance small target recognition tasks and real-time intelligent monitoring, this paper proposes a deep learning-based recognition method aimed at improving the ability to recognize and monitor various behaviors of captive ewes. Additionally, we have developed a system platform based on ELFN-YOLO to monitor the behaviors of ewes. ELFN-YOLO enhances the overall performance of the model by combining ELFN with the attention mechanism CBAM. ELFN strengthens multiple layers with fewer parameters, while the attention mechanism further emphasizes the channel information interaction based on ELFN. It also improves the ability of ELFN to extract spatial information in small target occlusion scenarios, leading to better recognition results. The proposed ELFN-YOLO achieved an accuracy of 92.5%, an F1 score of 92.5%, and a mAP@0.5 of 94.7% on the ewe behavior dataset built in commercial farms, which outperformed YOLOv7-Tiny by 1.5%, 0.8%, and 0.7% in terms of accuracy, F1 score, and mAP@0.5, respectively. It also outperformed other baseline models such as Faster R-CNN, YOLOv4-Tiny, and YOLOv5s. The obtained results indicate that the proposed approach outperforms existing methods in scenarios involving multi-scale detection of small objects. The proposed method is of significant importance for strengthening animal welfare and ewe management, and it provides valuable data support for subsequent tracking algorithms to monitor the activity status of ewes.
format Article
id doaj-art-bafa1f94e9f84d218ee7a3c3109635af
institution Kabale University
issn 2077-0472
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Agriculture
spelling doaj-art-bafa1f94e9f84d218ee7a3c3109635af2024-12-27T14:03:13ZengMDPI AGAgriculture2077-04722024-12-011412227210.3390/agriculture14122272Small Target Ewe Behavior Recognition Based on ELFN-YOLOJianglin Wu0Shufeng Li1Baoqin Wen2Jing Nie3Na Liu4Honglei Cen5Jingbin Li6Shuangyin Liu7College of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, ChinaCollege of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, ChinaCollege of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, ChinaCollege of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, ChinaCollege of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, ChinaCollege of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, ChinaCollege of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, ChinaCollege of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, ChinaIn response to the poor performance of long-distance small target recognition tasks and real-time intelligent monitoring, this paper proposes a deep learning-based recognition method aimed at improving the ability to recognize and monitor various behaviors of captive ewes. Additionally, we have developed a system platform based on ELFN-YOLO to monitor the behaviors of ewes. ELFN-YOLO enhances the overall performance of the model by combining ELFN with the attention mechanism CBAM. ELFN strengthens multiple layers with fewer parameters, while the attention mechanism further emphasizes the channel information interaction based on ELFN. It also improves the ability of ELFN to extract spatial information in small target occlusion scenarios, leading to better recognition results. The proposed ELFN-YOLO achieved an accuracy of 92.5%, an F1 score of 92.5%, and a mAP@0.5 of 94.7% on the ewe behavior dataset built in commercial farms, which outperformed YOLOv7-Tiny by 1.5%, 0.8%, and 0.7% in terms of accuracy, F1 score, and mAP@0.5, respectively. It also outperformed other baseline models such as Faster R-CNN, YOLOv4-Tiny, and YOLOv5s. The obtained results indicate that the proposed approach outperforms existing methods in scenarios involving multi-scale detection of small objects. The proposed method is of significant importance for strengthening animal welfare and ewe management, and it provides valuable data support for subsequent tracking algorithms to monitor the activity status of ewes.https://www.mdpi.com/2077-0472/14/12/2272intelligent supervision systemeweYOLOv7deep learning
spellingShingle Jianglin Wu
Shufeng Li
Baoqin Wen
Jing Nie
Na Liu
Honglei Cen
Jingbin Li
Shuangyin Liu
Small Target Ewe Behavior Recognition Based on ELFN-YOLO
Agriculture
intelligent supervision system
ewe
YOLOv7
deep learning
title Small Target Ewe Behavior Recognition Based on ELFN-YOLO
title_full Small Target Ewe Behavior Recognition Based on ELFN-YOLO
title_fullStr Small Target Ewe Behavior Recognition Based on ELFN-YOLO
title_full_unstemmed Small Target Ewe Behavior Recognition Based on ELFN-YOLO
title_short Small Target Ewe Behavior Recognition Based on ELFN-YOLO
title_sort small target ewe behavior recognition based on elfn yolo
topic intelligent supervision system
ewe
YOLOv7
deep learning
url https://www.mdpi.com/2077-0472/14/12/2272
work_keys_str_mv AT jianglinwu smalltargetewebehaviorrecognitionbasedonelfnyolo
AT shufengli smalltargetewebehaviorrecognitionbasedonelfnyolo
AT baoqinwen smalltargetewebehaviorrecognitionbasedonelfnyolo
AT jingnie smalltargetewebehaviorrecognitionbasedonelfnyolo
AT naliu smalltargetewebehaviorrecognitionbasedonelfnyolo
AT hongleicen smalltargetewebehaviorrecognitionbasedonelfnyolo
AT jingbinli smalltargetewebehaviorrecognitionbasedonelfnyolo
AT shuangyinliu smalltargetewebehaviorrecognitionbasedonelfnyolo