Research on Enhanced Dynamic Pig Counting Based on YOLOv8n and Deep SORT
Pig counting is an essential activity in the administration of pig farming. Currently, manual counting is inefficient, costly, and unsuitable for systematic analysis. However, research on dynamic pig counting encounters challenges, including inadequate detection accuracy stemming from crowding, occl...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/9/2680 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850032053108604928 |
|---|---|
| author | Peng Shen Keyu Mei Haori Xue Tenglong Li Guoqing Zhang Yongxiang Zhao Wei Luo Liang Mao |
| author_facet | Peng Shen Keyu Mei Haori Xue Tenglong Li Guoqing Zhang Yongxiang Zhao Wei Luo Liang Mao |
| author_sort | Peng Shen |
| collection | DOAJ |
| description | Pig counting is an essential activity in the administration of pig farming. Currently, manual counting is inefficient, costly, and unsuitable for systematic analysis. However, research on dynamic pig counting encounters challenges, including inadequate detection accuracy stemming from crowding, occlusion, deformation, and low-light conditions. Target tracking issues characterized by poor accuracy, frequent identity confusion, and false positive trajectories ultimately lead to diminished accuracy in the final counting outcomes. Given these existing limitations, this paper proposes an enhanced algorithm based on the YOLOv8n+Deep SORT model. The ELA attention mechanism, GSConv, and VoVGSCSP lightweight convolution modules are introduced in YOLOv8n, which improve detection accuracy and speed for pig target recognition. Additionally, Deep SORT is enhanced by integrating the DenseNet feature extraction network and CIoU matching algorithm, improving the accuracy and stability of target tracking. Experimental results indicate that the improved Deep SORT-P pig tracking algorithm attains MOTA and MOTP values of 89.2% and 90.4%, respectively, reflecting improvements of 4.2% and 1.7%, while IDSW is diminished by 25.5%. Finally, counting experiments were performed on videos of pigs traversing the farm passage using both the original and improved algorithms. The improved YOLOv8n-EGV+Deep SORT-P algorithm achieved a counting accuracy of 92.1%, reflecting a 17.5% improvement over the original algorithm. Meanwhile, the improved algorithm presented in this study successfully attained stable dynamic pig counting in practical environments, offering valuable data and references for research on dynamic pig counting. |
| format | Article |
| id | doaj-art-598dd0edca2b4c408625ea4e8b2a57c9 |
| institution | DOAJ |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-598dd0edca2b4c408625ea4e8b2a57c92025-08-20T02:58:47ZengMDPI AGSensors1424-82202025-04-01259268010.3390/s25092680Research on Enhanced Dynamic Pig Counting Based on YOLOv8n and Deep SORTPeng Shen0Keyu Mei1Haori Xue2Tenglong Li3Guoqing Zhang4Yongxiang Zhao5Wei Luo6Liang Mao7North China Institute of Aerospace Engineering, School of Aeronautics and Astronautics, Langfang 065000, ChinaNorth China Institute of Aerospace Engineering, School of Aeronautics and Astronautics, Langfang 065000, ChinaNorth China Institute of Aerospace Engineering, School of Aeronautics and Astronautics, Langfang 065000, ChinaNorth China Institute of Aerospace Engineering, School of Aeronautics and Astronautics, Langfang 065000, ChinaNorth China Institute of Aerospace Engineering, School of Remote Sensing and Information Engineering, Langfang 065000, ChinaNorth China Institute of Aerospace Engineering, School of Remote Sensing and Information Engineering, Langfang 065000, ChinaNorth China Institute of Aerospace Engineering, School of Remote Sensing and Information Engineering, Langfang 065000, ChinaGuangdong-Hong Kong-Macao Greater Bay Area Artificial Intelligence Application Technology Research Institute, Shenzhen Polytechnic University, Shenzhen 518055, ChinaPig counting is an essential activity in the administration of pig farming. Currently, manual counting is inefficient, costly, and unsuitable for systematic analysis. However, research on dynamic pig counting encounters challenges, including inadequate detection accuracy stemming from crowding, occlusion, deformation, and low-light conditions. Target tracking issues characterized by poor accuracy, frequent identity confusion, and false positive trajectories ultimately lead to diminished accuracy in the final counting outcomes. Given these existing limitations, this paper proposes an enhanced algorithm based on the YOLOv8n+Deep SORT model. The ELA attention mechanism, GSConv, and VoVGSCSP lightweight convolution modules are introduced in YOLOv8n, which improve detection accuracy and speed for pig target recognition. Additionally, Deep SORT is enhanced by integrating the DenseNet feature extraction network and CIoU matching algorithm, improving the accuracy and stability of target tracking. Experimental results indicate that the improved Deep SORT-P pig tracking algorithm attains MOTA and MOTP values of 89.2% and 90.4%, respectively, reflecting improvements of 4.2% and 1.7%, while IDSW is diminished by 25.5%. Finally, counting experiments were performed on videos of pigs traversing the farm passage using both the original and improved algorithms. The improved YOLOv8n-EGV+Deep SORT-P algorithm achieved a counting accuracy of 92.1%, reflecting a 17.5% improvement over the original algorithm. Meanwhile, the improved algorithm presented in this study successfully attained stable dynamic pig counting in practical environments, offering valuable data and references for research on dynamic pig counting.https://www.mdpi.com/1424-8220/25/9/2680pig countingobject detectionmulti-object trackingYOLOv8nDeep SORT |
| spellingShingle | Peng Shen Keyu Mei Haori Xue Tenglong Li Guoqing Zhang Yongxiang Zhao Wei Luo Liang Mao Research on Enhanced Dynamic Pig Counting Based on YOLOv8n and Deep SORT Sensors pig counting object detection multi-object tracking YOLOv8n Deep SORT |
| title | Research on Enhanced Dynamic Pig Counting Based on YOLOv8n and Deep SORT |
| title_full | Research on Enhanced Dynamic Pig Counting Based on YOLOv8n and Deep SORT |
| title_fullStr | Research on Enhanced Dynamic Pig Counting Based on YOLOv8n and Deep SORT |
| title_full_unstemmed | Research on Enhanced Dynamic Pig Counting Based on YOLOv8n and Deep SORT |
| title_short | Research on Enhanced Dynamic Pig Counting Based on YOLOv8n and Deep SORT |
| title_sort | research on enhanced dynamic pig counting based on yolov8n and deep sort |
| topic | pig counting object detection multi-object tracking YOLOv8n Deep SORT |
| url | https://www.mdpi.com/1424-8220/25/9/2680 |
| work_keys_str_mv | AT pengshen researchonenhanceddynamicpigcountingbasedonyolov8nanddeepsort AT keyumei researchonenhanceddynamicpigcountingbasedonyolov8nanddeepsort AT haorixue researchonenhanceddynamicpigcountingbasedonyolov8nanddeepsort AT tenglongli researchonenhanceddynamicpigcountingbasedonyolov8nanddeepsort AT guoqingzhang researchonenhanceddynamicpigcountingbasedonyolov8nanddeepsort AT yongxiangzhao researchonenhanceddynamicpigcountingbasedonyolov8nanddeepsort AT weiluo researchonenhanceddynamicpigcountingbasedonyolov8nanddeepsort AT liangmao researchonenhanceddynamicpigcountingbasedonyolov8nanddeepsort |