Detection of Cattle Key Parts Based on the Improved Yolov5 Algorithm
Accurate detection of key body parts of cattle is of great significance to Precision Livestock Farming (PLF), using artificial intelligence for video analysis. As the background image in cattle livestock farms is complex and the target features of the cattle are not obvious, traditional object-detec...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-05-01
|
Series: | Agriculture |
Subjects: | |
Online Access: | https://www.mdpi.com/2077-0472/13/6/1110 |
_version_ | 1797596664487215104 |
---|---|
author | Dangguo Shao Zihan He Hongbo Fan Kun Sun |
author_facet | Dangguo Shao Zihan He Hongbo Fan Kun Sun |
author_sort | Dangguo Shao |
collection | DOAJ |
description | Accurate detection of key body parts of cattle is of great significance to Precision Livestock Farming (PLF), using artificial intelligence for video analysis. As the background image in cattle livestock farms is complex and the target features of the cattle are not obvious, traditional object-detection algorithms cannot detect the key parts of the image with high precision. This paper proposes the Filter_Attention attention mechanism to detect the key parts of cattle. Since the image is unstable during training and initialization, particle noise is generated in the feature graph after convolution calculation. Therefore, this paper proposes an attentional mechanism based on bilateral filtering to reduce this interference. We also designed a Pooling_Module, based on the soft pooling algorithm, which facilitates information loss relative to the initial activation graph compared to maximum pooling. Our data set contained 1723 images of cattle, in which labels of the body, head, legs, and tail were manually entered. This dataset was divided into a training set, verification set, and test set at a ratio of 7:2:1 for training the model proposed in this paper. The detection effect of our proposed module is proven by the ablation experiment from mAP, the AP value, and the F1 value. This paper also compares other mainstream object detection algorithms. The experimental results show that our model obtained 90.74% mAP, and the F1 value and AP value of the four parts were improved. |
first_indexed | 2024-03-11T02:53:22Z |
format | Article |
id | doaj.art-ff0acbe53a4e4a729f0b96d8eb4f3856 |
institution | Directory Open Access Journal |
issn | 2077-0472 |
language | English |
last_indexed | 2024-03-11T02:53:22Z |
publishDate | 2023-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Agriculture |
spelling | doaj.art-ff0acbe53a4e4a729f0b96d8eb4f38562023-11-18T08:50:29ZengMDPI AGAgriculture2077-04722023-05-01136111010.3390/agriculture13061110Detection of Cattle Key Parts Based on the Improved Yolov5 AlgorithmDangguo Shao0Zihan He1Hongbo Fan2Kun Sun3Faculty of Information Engineering and Automation, Yunnan Province Key Laboratory of Computer, Kunming University of Science and Technology, Kunming 650500, ChinaFaculty of Information Engineering and Automation, Yunnan Province Key Laboratory of Computer, Kunming University of Science and Technology, Kunming 650500, ChinaFaculty of Modern Agricultural Engineering, Kunming University of Science and Technology, Kunming 650300, ChinaFaculty of Information Engineering and Automation, Yunnan Province Key Laboratory of Computer, Kunming University of Science and Technology, Kunming 650500, ChinaAccurate detection of key body parts of cattle is of great significance to Precision Livestock Farming (PLF), using artificial intelligence for video analysis. As the background image in cattle livestock farms is complex and the target features of the cattle are not obvious, traditional object-detection algorithms cannot detect the key parts of the image with high precision. This paper proposes the Filter_Attention attention mechanism to detect the key parts of cattle. Since the image is unstable during training and initialization, particle noise is generated in the feature graph after convolution calculation. Therefore, this paper proposes an attentional mechanism based on bilateral filtering to reduce this interference. We also designed a Pooling_Module, based on the soft pooling algorithm, which facilitates information loss relative to the initial activation graph compared to maximum pooling. Our data set contained 1723 images of cattle, in which labels of the body, head, legs, and tail were manually entered. This dataset was divided into a training set, verification set, and test set at a ratio of 7:2:1 for training the model proposed in this paper. The detection effect of our proposed module is proven by the ablation experiment from mAP, the AP value, and the F1 value. This paper also compares other mainstream object detection algorithms. The experimental results show that our model obtained 90.74% mAP, and the F1 value and AP value of the four parts were improved.https://www.mdpi.com/2077-0472/13/6/1110key parts detection of cattleYoloFilter_AttentionSoftpoolingdeep learning |
spellingShingle | Dangguo Shao Zihan He Hongbo Fan Kun Sun Detection of Cattle Key Parts Based on the Improved Yolov5 Algorithm Agriculture key parts detection of cattle Yolo Filter_Attention Softpooling deep learning |
title | Detection of Cattle Key Parts Based on the Improved Yolov5 Algorithm |
title_full | Detection of Cattle Key Parts Based on the Improved Yolov5 Algorithm |
title_fullStr | Detection of Cattle Key Parts Based on the Improved Yolov5 Algorithm |
title_full_unstemmed | Detection of Cattle Key Parts Based on the Improved Yolov5 Algorithm |
title_short | Detection of Cattle Key Parts Based on the Improved Yolov5 Algorithm |
title_sort | detection of cattle key parts based on the improved yolov5 algorithm |
topic | key parts detection of cattle Yolo Filter_Attention Softpooling deep learning |
url | https://www.mdpi.com/2077-0472/13/6/1110 |
work_keys_str_mv | AT dangguoshao detectionofcattlekeypartsbasedontheimprovedyolov5algorithm AT zihanhe detectionofcattlekeypartsbasedontheimprovedyolov5algorithm AT hongbofan detectionofcattlekeypartsbasedontheimprovedyolov5algorithm AT kunsun detectionofcattlekeypartsbasedontheimprovedyolov5algorithm |