YOLOv8-CBAM: a study of sheep head identification in Ujumqin sheep
IntroductionThe facial coloration of sheep is not only a critical characteristic for breed and individual identification but also serves as a significant indicator for assessing genetic diversity and guiding selective breeding efforts.MethodsIn this study, 201 Ujumqin sheep were used as research obj...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-02-01
|
| Series: | Frontiers in Veterinary Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fvets.2025.1514212/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832086413946912768 |
|---|---|
| author | Qing Qin Qing Qin Qing Qin Xingyu Zhou Xingyu Zhou Xingyu Zhou Jiale Gao Jiale Gao Jiale Gao Zhixin Wang A. Naer Long Hai Suhe Alatan Haijun Zhang Zhihong Liu Zhihong Liu Zhihong Liu |
| author_facet | Qing Qin Qing Qin Qing Qin Xingyu Zhou Xingyu Zhou Xingyu Zhou Jiale Gao Jiale Gao Jiale Gao Zhixin Wang A. Naer Long Hai Suhe Alatan Haijun Zhang Zhihong Liu Zhihong Liu Zhihong Liu |
| author_sort | Qing Qin |
| collection | DOAJ |
| description | IntroductionThe facial coloration of sheep is not only a critical characteristic for breed and individual identification but also serves as a significant indicator for assessing genetic diversity and guiding selective breeding efforts.MethodsIn this study, 201 Ujumqin sheep were used as research objects and 1713 head image data were collected. We delineated feature points related to the facial coloration of Ujumqin sheep and successfully developed a head color recognition model (YOLOv8-CBAM) utilizing the YOLOv8 architecture in conjunction with the CBAM attention mechanism.ResultsThe model demonstrated impressive performance in recognizing four head color categories, achieving an average precision (mAP) of 97.7% and an F1 score of 0.94. In comparison to YOLOv8n, YOLOv8l, YOLOv8m, YOLOv8s, and YOLOv8x, the YOLOv8-CBAM model enhances average accuracy by 0.5%, 1%, 0.7%, 0.7%, and 1.6%, respectively. Furthermore, when compared to YOLOv3, the improvement is 1%, while YOLOv5n and YOLOv10n show increases of 1.4% and 2.4%, respectively.DiscussionThe findings indicate that the smaller model exhibited superior performance in the facial color recognition task for Ujumqin sheep. Overall, the YOLOv8-CBAM model achieved high accuracy in the head color recognition task, providing reliable technical support for automated sheep management systems. |
| format | Article |
| id | doaj-art-1ad2afb98f5e4b09b158e1f703953613 |
| institution | Kabale University |
| issn | 2297-1769 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Veterinary Science |
| spelling | doaj-art-1ad2afb98f5e4b09b158e1f7039536132025-02-06T15:08:25ZengFrontiers Media S.A.Frontiers in Veterinary Science2297-17692025-02-011210.3389/fvets.2025.15142121514212YOLOv8-CBAM: a study of sheep head identification in Ujumqin sheepQing Qin0Qing Qin1Qing Qin2Xingyu Zhou3Xingyu Zhou4Xingyu Zhou5Jiale Gao6Jiale Gao7Jiale Gao8Zhixin Wang9A. Naer10Long Hai11Suhe Alatan12Haijun Zhang13Zhihong Liu14Zhihong Liu15Zhihong Liu16Animal Science Department, Inner Mongolia Agricultural University, Hohhot City, ChinaKey Laboratory of Animal Genetics, Breeding and Reproduction in Inner Mongolia Autonomous Region, Inner Mongolia Agricultural University, Hohhot City, ChinaKey Laboratory of Mutton Sheep and Goat Genetics and Breeding, Ministry of Agriculture and Rural Affairs, Inner Mongolia Agricultural University, Hohhot City, ChinaAnimal Science Department, Inner Mongolia Agricultural University, Hohhot City, ChinaKey Laboratory of Animal Genetics, Breeding and Reproduction in Inner Mongolia Autonomous Region, Inner Mongolia Agricultural University, Hohhot City, ChinaKey Laboratory of Mutton Sheep and Goat Genetics and Breeding, Ministry of Agriculture and Rural Affairs, Inner Mongolia Agricultural University, Hohhot City, ChinaAnimal Science Department, Inner Mongolia Agricultural University, Hohhot City, ChinaKey Laboratory of Animal Genetics, Breeding and Reproduction in Inner Mongolia Autonomous Region, Inner Mongolia Agricultural University, Hohhot City, ChinaKey Laboratory of Mutton Sheep and Goat Genetics and Breeding, Ministry of Agriculture and Rural Affairs, Inner Mongolia Agricultural University, Hohhot City, ChinaAnimal Science Department, Inner Mongolia Agricultural University, Hohhot City, ChinaInner Mongolia Autonomous Region Agriculture and Animal Husbandry Technology Popularization Center, Hohhot City, ChinaInner Mongolia Autonomous Region Agriculture and Animal Husbandry Technology Popularization Center, Hohhot City, ChinaEast Ujumqin Banner Hishig Animal Husbandry Development Co., Ltd., East Ujumqin Banner, ChinaErdos Agricultural and Animal Husbandry Science Research Institute, Ordos City, ChinaAnimal Science Department, Inner Mongolia Agricultural University, Hohhot City, ChinaKey Laboratory of Animal Genetics, Breeding and Reproduction in Inner Mongolia Autonomous Region, Inner Mongolia Agricultural University, Hohhot City, ChinaKey Laboratory of Mutton Sheep and Goat Genetics and Breeding, Ministry of Agriculture and Rural Affairs, Inner Mongolia Agricultural University, Hohhot City, ChinaIntroductionThe facial coloration of sheep is not only a critical characteristic for breed and individual identification but also serves as a significant indicator for assessing genetic diversity and guiding selective breeding efforts.MethodsIn this study, 201 Ujumqin sheep were used as research objects and 1713 head image data were collected. We delineated feature points related to the facial coloration of Ujumqin sheep and successfully developed a head color recognition model (YOLOv8-CBAM) utilizing the YOLOv8 architecture in conjunction with the CBAM attention mechanism.ResultsThe model demonstrated impressive performance in recognizing four head color categories, achieving an average precision (mAP) of 97.7% and an F1 score of 0.94. In comparison to YOLOv8n, YOLOv8l, YOLOv8m, YOLOv8s, and YOLOv8x, the YOLOv8-CBAM model enhances average accuracy by 0.5%, 1%, 0.7%, 0.7%, and 1.6%, respectively. Furthermore, when compared to YOLOv3, the improvement is 1%, while YOLOv5n and YOLOv10n show increases of 1.4% and 2.4%, respectively.DiscussionThe findings indicate that the smaller model exhibited superior performance in the facial color recognition task for Ujumqin sheep. Overall, the YOLOv8-CBAM model achieved high accuracy in the head color recognition task, providing reliable technical support for automated sheep management systems.https://www.frontiersin.org/articles/10.3389/fvets.2025.1514212/fullattentioncomputer visionface recognitionhead colorsobject detection |
| spellingShingle | Qing Qin Qing Qin Qing Qin Xingyu Zhou Xingyu Zhou Xingyu Zhou Jiale Gao Jiale Gao Jiale Gao Zhixin Wang A. Naer Long Hai Suhe Alatan Haijun Zhang Zhihong Liu Zhihong Liu Zhihong Liu YOLOv8-CBAM: a study of sheep head identification in Ujumqin sheep Frontiers in Veterinary Science attention computer vision face recognition head colors object detection |
| title | YOLOv8-CBAM: a study of sheep head identification in Ujumqin sheep |
| title_full | YOLOv8-CBAM: a study of sheep head identification in Ujumqin sheep |
| title_fullStr | YOLOv8-CBAM: a study of sheep head identification in Ujumqin sheep |
| title_full_unstemmed | YOLOv8-CBAM: a study of sheep head identification in Ujumqin sheep |
| title_short | YOLOv8-CBAM: a study of sheep head identification in Ujumqin sheep |
| title_sort | yolov8 cbam a study of sheep head identification in ujumqin sheep |
| topic | attention computer vision face recognition head colors object detection |
| url | https://www.frontiersin.org/articles/10.3389/fvets.2025.1514212/full |
| work_keys_str_mv | AT qingqin yolov8cbamastudyofsheepheadidentificationinujumqinsheep AT qingqin yolov8cbamastudyofsheepheadidentificationinujumqinsheep AT qingqin yolov8cbamastudyofsheepheadidentificationinujumqinsheep AT xingyuzhou yolov8cbamastudyofsheepheadidentificationinujumqinsheep AT xingyuzhou yolov8cbamastudyofsheepheadidentificationinujumqinsheep AT xingyuzhou yolov8cbamastudyofsheepheadidentificationinujumqinsheep AT jialegao yolov8cbamastudyofsheepheadidentificationinujumqinsheep AT jialegao yolov8cbamastudyofsheepheadidentificationinujumqinsheep AT jialegao yolov8cbamastudyofsheepheadidentificationinujumqinsheep AT zhixinwang yolov8cbamastudyofsheepheadidentificationinujumqinsheep AT anaer yolov8cbamastudyofsheepheadidentificationinujumqinsheep AT longhai yolov8cbamastudyofsheepheadidentificationinujumqinsheep AT suhealatan yolov8cbamastudyofsheepheadidentificationinujumqinsheep AT haijunzhang yolov8cbamastudyofsheepheadidentificationinujumqinsheep AT zhihongliu yolov8cbamastudyofsheepheadidentificationinujumqinsheep AT zhihongliu yolov8cbamastudyofsheepheadidentificationinujumqinsheep AT zhihongliu yolov8cbamastudyofsheepheadidentificationinujumqinsheep |