An Improved Pig Counting Algorithm Based on YOLOv5 and DeepSORT Model
Pig counting is an important task in pig sales and breeding supervision. Currently, manual counting is low-efficiency and high-cost and presents challenges in terms of statistical analysis. In response to the difficulties faced in pig part feature detection, the loss of tracking due to rapid movemen...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/14/6309 |
| _version_ | 1797587515292516352 |
|---|---|
| author | Yigui Huang Deqin Xiao Junbin Liu Zhujie Tan Kejian Liu Miaobin Chen |
| author_facet | Yigui Huang Deqin Xiao Junbin Liu Zhujie Tan Kejian Liu Miaobin Chen |
| author_sort | Yigui Huang |
| collection | DOAJ |
| description | Pig counting is an important task in pig sales and breeding supervision. Currently, manual counting is low-efficiency and high-cost and presents challenges in terms of statistical analysis. In response to the difficulties faced in pig part feature detection, the loss of tracking due to rapid movement, and the large counting deviation in pig video tracking and counting research, this paper proposes an improved pig counting algorithm (Mobile Pig Counting Algorithm with YOLOv5xpig and DeepSORTPig (MPC-YD)) based on YOLOv5 + DeepSORT model. The algorithm improves the detection rate of pig body parts by adding two different sizes of SPP networks and using SoftPool instead of MaxPool operations in YOLOv5x. In addition, the algorithm includes a pig reidentification network, a pig-tracking method based on spatial state correction, and a pig counting method based on frame number judgment on the DeepSORT algorithm to improve pig tracking accuracy. Experimental analysis shows that the MPC-YD algorithm achieves an average precision of 99.24% in pig object detection and an accuracy of 85.32% in multitarget pig tracking. In the aisle environment of the slaughterhouse, the MPC-YD algorithm achieves a correlation coefficient (R<sup>2</sup>) of 98.14% in pig counting from video, and it achieves stable pig counting in a breeding environment. The algorithm has a wide range of application prospects. |
| first_indexed | 2024-03-11T00:41:00Z |
| format | Article |
| id | doaj.art-5f9e9c9526f14f8da9510c73b9bb9a02 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T00:41:00Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-5f9e9c9526f14f8da9510c73b9bb9a022023-11-18T21:15:56ZengMDPI AGSensors1424-82202023-07-012314630910.3390/s23146309An Improved Pig Counting Algorithm Based on YOLOv5 and DeepSORT ModelYigui Huang0Deqin Xiao1Junbin Liu2Zhujie Tan3Kejian Liu4Miaobin Chen5College of Mathematics Informatics, South China Agricultural University, Guangzhou 510642, ChinaCollege of Mathematics Informatics, South China Agricultural University, Guangzhou 510642, ChinaCollege of Mathematics Informatics, South China Agricultural University, Guangzhou 510642, ChinaCollege of Mathematics Informatics, South China Agricultural University, Guangzhou 510642, ChinaCollege of Mathematics Informatics, South China Agricultural University, Guangzhou 510642, ChinaCollege of Mathematics Informatics, South China Agricultural University, Guangzhou 510642, ChinaPig counting is an important task in pig sales and breeding supervision. Currently, manual counting is low-efficiency and high-cost and presents challenges in terms of statistical analysis. In response to the difficulties faced in pig part feature detection, the loss of tracking due to rapid movement, and the large counting deviation in pig video tracking and counting research, this paper proposes an improved pig counting algorithm (Mobile Pig Counting Algorithm with YOLOv5xpig and DeepSORTPig (MPC-YD)) based on YOLOv5 + DeepSORT model. The algorithm improves the detection rate of pig body parts by adding two different sizes of SPP networks and using SoftPool instead of MaxPool operations in YOLOv5x. In addition, the algorithm includes a pig reidentification network, a pig-tracking method based on spatial state correction, and a pig counting method based on frame number judgment on the DeepSORT algorithm to improve pig tracking accuracy. Experimental analysis shows that the MPC-YD algorithm achieves an average precision of 99.24% in pig object detection and an accuracy of 85.32% in multitarget pig tracking. In the aisle environment of the slaughterhouse, the MPC-YD algorithm achieves a correlation coefficient (R<sup>2</sup>) of 98.14% in pig counting from video, and it achieves stable pig counting in a breeding environment. The algorithm has a wide range of application prospects.https://www.mdpi.com/1424-8220/23/14/6309computer visionobject detectionmultiobject trackingpig |
| spellingShingle | Yigui Huang Deqin Xiao Junbin Liu Zhujie Tan Kejian Liu Miaobin Chen An Improved Pig Counting Algorithm Based on YOLOv5 and DeepSORT Model Sensors computer vision object detection multiobject tracking pig |
| title | An Improved Pig Counting Algorithm Based on YOLOv5 and DeepSORT Model |
| title_full | An Improved Pig Counting Algorithm Based on YOLOv5 and DeepSORT Model |
| title_fullStr | An Improved Pig Counting Algorithm Based on YOLOv5 and DeepSORT Model |
| title_full_unstemmed | An Improved Pig Counting Algorithm Based on YOLOv5 and DeepSORT Model |
| title_short | An Improved Pig Counting Algorithm Based on YOLOv5 and DeepSORT Model |
| title_sort | improved pig counting algorithm based on yolov5 and deepsort model |
| topic | computer vision object detection multiobject tracking pig |
| url | https://www.mdpi.com/1424-8220/23/14/6309 |
| work_keys_str_mv | AT yiguihuang animprovedpigcountingalgorithmbasedonyolov5anddeepsortmodel AT deqinxiao animprovedpigcountingalgorithmbasedonyolov5anddeepsortmodel AT junbinliu animprovedpigcountingalgorithmbasedonyolov5anddeepsortmodel AT zhujietan animprovedpigcountingalgorithmbasedonyolov5anddeepsortmodel AT kejianliu animprovedpigcountingalgorithmbasedonyolov5anddeepsortmodel AT miaobinchen animprovedpigcountingalgorithmbasedonyolov5anddeepsortmodel AT yiguihuang improvedpigcountingalgorithmbasedonyolov5anddeepsortmodel AT deqinxiao improvedpigcountingalgorithmbasedonyolov5anddeepsortmodel AT junbinliu improvedpigcountingalgorithmbasedonyolov5anddeepsortmodel AT zhujietan improvedpigcountingalgorithmbasedonyolov5anddeepsortmodel AT kejianliu improvedpigcountingalgorithmbasedonyolov5anddeepsortmodel AT miaobinchen improvedpigcountingalgorithmbasedonyolov5anddeepsortmodel |