A Novel Improved YOLOv3-SC Model for Individual Pig Detection
Pork is the most widely consumed meat product in the world, and achieving accurate detection of individual pigs is of great significance for intelligent pig breeding and health monitoring. Improved pig detection has important implications for improving pork production and quality, as well as economi...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-11-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/22/22/8792 |
_version_ | 1797463991806590976 |
---|---|
author | Wangli Hao Wenwang Han Meng Han Fuzhong Li |
author_facet | Wangli Hao Wenwang Han Meng Han Fuzhong Li |
author_sort | Wangli Hao |
collection | DOAJ |
description | Pork is the most widely consumed meat product in the world, and achieving accurate detection of individual pigs is of great significance for intelligent pig breeding and health monitoring. Improved pig detection has important implications for improving pork production and quality, as well as economics. However, most of the current approaches are based on manual labor, resulting in unfeasible performance. In order to improve the efficiency and effectiveness of individual pig detection, this paper describes the development of an attention module enhanced YOLOv3-SC model (YOLOv3-SPP-CBAM. SPP denotes the Spatial Pyramid Pooling module and CBAM indicates the Convolutional Block Attention Module). Specifically, leveraging the attention module, the network will extract much richer feature information, leading the improved performance. Furthermore, by integrating the SPP structured network, multi-scale feature fusion can be achieved, which makes the network more robust. On the constructed dataset of 4019 samples, the experimental results showed that the YOLOv3-SC network achieved 99.24% mAP in identifying individual pigs with a detection time of 16 ms. Compared with the other popular four models, including YOLOv1, YOLOv2, Faster-RCNN, and YOLOv3, the mAP of pig identification was improved by 2.31%, 1.44%, 1.28%, and 0.61%, respectively. The YOLOv3-SC proposed in this paper can achieve accurate individual detection of pigs. Consequently, this novel proposed model can be employed for the rapid detection of individual pigs on farms, and provides new ideas for individual pig detection. |
first_indexed | 2024-03-09T18:01:34Z |
format | Article |
id | doaj.art-f45341df5a34483e93f251528ca12792 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-09T18:01:34Z |
publishDate | 2022-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-f45341df5a34483e93f251528ca127922023-11-24T09:56:05ZengMDPI AGSensors1424-82202022-11-012222879210.3390/s22228792A Novel Improved YOLOv3-SC Model for Individual Pig DetectionWangli Hao0Wenwang Han1Meng Han2Fuzhong Li3School of Software, Shanxi Agricultural University, Jinzhong 030801, ChinaSchool of Software, Shanxi Agricultural University, Jinzhong 030801, ChinaSchool of Software, Shanxi Agricultural University, Jinzhong 030801, ChinaSchool of Software, Shanxi Agricultural University, Jinzhong 030801, ChinaPork is the most widely consumed meat product in the world, and achieving accurate detection of individual pigs is of great significance for intelligent pig breeding and health monitoring. Improved pig detection has important implications for improving pork production and quality, as well as economics. However, most of the current approaches are based on manual labor, resulting in unfeasible performance. In order to improve the efficiency and effectiveness of individual pig detection, this paper describes the development of an attention module enhanced YOLOv3-SC model (YOLOv3-SPP-CBAM. SPP denotes the Spatial Pyramid Pooling module and CBAM indicates the Convolutional Block Attention Module). Specifically, leveraging the attention module, the network will extract much richer feature information, leading the improved performance. Furthermore, by integrating the SPP structured network, multi-scale feature fusion can be achieved, which makes the network more robust. On the constructed dataset of 4019 samples, the experimental results showed that the YOLOv3-SC network achieved 99.24% mAP in identifying individual pigs with a detection time of 16 ms. Compared with the other popular four models, including YOLOv1, YOLOv2, Faster-RCNN, and YOLOv3, the mAP of pig identification was improved by 2.31%, 1.44%, 1.28%, and 0.61%, respectively. The YOLOv3-SC proposed in this paper can achieve accurate individual detection of pigs. Consequently, this novel proposed model can be employed for the rapid detection of individual pigs on farms, and provides new ideas for individual pig detection.https://www.mdpi.com/1424-8220/22/22/8792pig detectionYOLOv3Convolutional Block Attention ModuleSpatial Pyramid Pooling |
spellingShingle | Wangli Hao Wenwang Han Meng Han Fuzhong Li A Novel Improved YOLOv3-SC Model for Individual Pig Detection Sensors pig detection YOLOv3 Convolutional Block Attention Module Spatial Pyramid Pooling |
title | A Novel Improved YOLOv3-SC Model for Individual Pig Detection |
title_full | A Novel Improved YOLOv3-SC Model for Individual Pig Detection |
title_fullStr | A Novel Improved YOLOv3-SC Model for Individual Pig Detection |
title_full_unstemmed | A Novel Improved YOLOv3-SC Model for Individual Pig Detection |
title_short | A Novel Improved YOLOv3-SC Model for Individual Pig Detection |
title_sort | novel improved yolov3 sc model for individual pig detection |
topic | pig detection YOLOv3 Convolutional Block Attention Module Spatial Pyramid Pooling |
url | https://www.mdpi.com/1424-8220/22/22/8792 |
work_keys_str_mv | AT wanglihao anovelimprovedyolov3scmodelforindividualpigdetection AT wenwanghan anovelimprovedyolov3scmodelforindividualpigdetection AT menghan anovelimprovedyolov3scmodelforindividualpigdetection AT fuzhongli anovelimprovedyolov3scmodelforindividualpigdetection AT wanglihao novelimprovedyolov3scmodelforindividualpigdetection AT wenwanghan novelimprovedyolov3scmodelforindividualpigdetection AT menghan novelimprovedyolov3scmodelforindividualpigdetection AT fuzhongli novelimprovedyolov3scmodelforindividualpigdetection |