The improved DeepSORT framework.
<div><p>Automatic detection and tracking of pig behaviors through video surveillance remain challenges due to farm demanding conditions, e.g., illumination conditions and occlusion of one pig from another. The main goal of this study is to develop a deep learning method based on the impr...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , , , , , |
| منشور في: |
2025
|
| الموضوعات: | |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1852015263619219456 |
|---|---|
| author | Tianyu Cheng (5075000) |
| author2 | Fujie Sun (22537638) Liang Mao (200719) Haoxuan Ou (22537641) Shuqin Tu (22537644) Fang Yuan (96264) Hairan Yang (22537647) |
| author2_role | author author author author author author |
| author_facet | Tianyu Cheng (5075000) Fujie Sun (22537638) Liang Mao (200719) Haoxuan Ou (22537641) Shuqin Tu (22537644) Fang Yuan (96264) Hairan Yang (22537647) |
| author_role | author |
| dc.creator.none.fl_str_mv | Tianyu Cheng (5075000) Fujie Sun (22537638) Liang Mao (200719) Haoxuan Ou (22537641) Shuqin Tu (22537644) Fang Yuan (96264) Hairan Yang (22537647) |
| dc.date.none.fl_str_mv | 2025-10-31T17:31:40Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0334783.g004 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/figure/The_improved_DeepSORT_framework_/30502617 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Ecology Sociology Science Policy Space Science Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Information Systems not elsewhere classified experimental results show farm demanding conditions false detection due accuracy improvement compared housed pigs attacking improved yolov5s adopts daily behaviors detection deepsort </ p improved deepsort model improved yolov5s pig detection missed detection high accuracy density conditions yolov5s model test videos special dataset pig behaviors one pig main goal experiments demonstrate different lighting comparison test behavior recognition attention mechanism 3 %, |
| dc.title.none.fl_str_mv | The improved DeepSORT framework. |
| dc.type.none.fl_str_mv | Image Figure info:eu-repo/semantics/publishedVersion image |
| description | <div><p>Automatic detection and tracking of pig behaviors through video surveillance remain challenges due to farm demanding conditions, e.g., illumination conditions and occlusion of one pig from another. The main goal of this study is to develop a deep learning method based on the improved YOLOv5s and DeepSORT to detect and track the behaviors of pigs, which has the advantages of stability and high accuracy. Firstly, YOLOv5s with the attention mechanism is used for pig detection and behavior recognition. To deal with the missed detection and false detection due to occlusion and overlapping between pigs and pigs, the improved YOLOv5s adopts the Shape-IoU to optimize the bounding box regression loss function, which improves the robustness of the model. Then, the improved DeepSORT model is proposed to track each pig behaviors including eat, stand, lie and attack four behavior types. Finally, we conduct a comparison test under different lighting and density conditions for pig detection and behavior tracking on special dataset. Experimental results show that the mAP@0.5% of improved YOLOv5s algorithm increases from 92.7% to 99.3%, which means 6.6% accuracy improvement compared with the YOLOv5s model. In terms of tracking, the values of MOTA and MOTP in all test videos are 94.5% and 94.9% respectively. These experiments demonstrate that the improved YOLOv5s and DeepSORT achieves high accuracy for both pig detection and behavior tracking. The proposed approach provides scalable technical support for contactless automatic pig monitoring.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_436f5bed1aa3e82deec72c2bcab93fb4 |
| identifier_str_mv | 10.1371/journal.pone.0334783.g004 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/30502617 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | The improved DeepSORT framework.Tianyu Cheng (5075000)Fujie Sun (22537638)Liang Mao (200719)Haoxuan Ou (22537641)Shuqin Tu (22537644)Fang Yuan (96264)Hairan Yang (22537647)EcologySociologyScience PolicySpace ScienceEnvironmental Sciences not elsewhere classifiedBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedexperimental results showfarm demanding conditionsfalse detection dueaccuracy improvement comparedhoused pigs attackingimproved yolov5s adoptsdaily behaviors detectiondeepsort </ pimproved deepsort modelimproved yolov5spig detectionmissed detectionhigh accuracydensity conditionsyolov5s modeltest videosspecial datasetpig behaviorsone pigmain goalexperiments demonstratedifferent lightingcomparison testbehavior recognitionattention mechanism3 %,<div><p>Automatic detection and tracking of pig behaviors through video surveillance remain challenges due to farm demanding conditions, e.g., illumination conditions and occlusion of one pig from another. The main goal of this study is to develop a deep learning method based on the improved YOLOv5s and DeepSORT to detect and track the behaviors of pigs, which has the advantages of stability and high accuracy. Firstly, YOLOv5s with the attention mechanism is used for pig detection and behavior recognition. To deal with the missed detection and false detection due to occlusion and overlapping between pigs and pigs, the improved YOLOv5s adopts the Shape-IoU to optimize the bounding box regression loss function, which improves the robustness of the model. Then, the improved DeepSORT model is proposed to track each pig behaviors including eat, stand, lie and attack four behavior types. Finally, we conduct a comparison test under different lighting and density conditions for pig detection and behavior tracking on special dataset. Experimental results show that the mAP@0.5% of improved YOLOv5s algorithm increases from 92.7% to 99.3%, which means 6.6% accuracy improvement compared with the YOLOv5s model. In terms of tracking, the values of MOTA and MOTP in all test videos are 94.5% and 94.9% respectively. These experiments demonstrate that the improved YOLOv5s and DeepSORT achieves high accuracy for both pig detection and behavior tracking. The proposed approach provides scalable technical support for contactless automatic pig monitoring.</p></div>2025-10-31T17:31:40ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0334783.g004https://figshare.com/articles/figure/The_improved_DeepSORT_framework_/30502617CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/305026172025-10-31T17:31:40Z |
| spellingShingle | The improved DeepSORT framework. Tianyu Cheng (5075000) Ecology Sociology Science Policy Space Science Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Information Systems not elsewhere classified experimental results show farm demanding conditions false detection due accuracy improvement compared housed pigs attacking improved yolov5s adopts daily behaviors detection deepsort </ p improved deepsort model improved yolov5s pig detection missed detection high accuracy density conditions yolov5s model test videos special dataset pig behaviors one pig main goal experiments demonstrate different lighting comparison test behavior recognition attention mechanism 3 %, |
| status_str | publishedVersion |
| title | The improved DeepSORT framework. |
| title_full | The improved DeepSORT framework. |
| title_fullStr | The improved DeepSORT framework. |
| title_full_unstemmed | The improved DeepSORT framework. |
| title_short | The improved DeepSORT framework. |
| title_sort | The improved DeepSORT framework. |
| topic | Ecology Sociology Science Policy Space Science Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Information Systems not elsewhere classified experimental results show farm demanding conditions false detection due accuracy improvement compared housed pigs attacking improved yolov5s adopts daily behaviors detection deepsort </ p improved deepsort model improved yolov5s pig detection missed detection high accuracy density conditions yolov5s model test videos special dataset pig behaviors one pig main goal experiments demonstrate different lighting comparison test behavior recognition attention mechanism 3 %, |