Research on Cone Bucket Detection Algorithm Based on Improved YOLOv5s
In order to address the problems associated with low detection accuracy, weak detection ability of small targets, insufficiently obvious differentiation of colors, and inability to accurately locate the actual position of the target object in the Formula Student Autonomous China, the YOLOv5s algorit...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-09-01
|
Series: | World Electric Vehicle Journal |
Subjects: | |
Online Access: | https://www.mdpi.com/2032-6653/14/10/269 |
_version_ | 1797571950167457792 |
---|---|
author | Jiyue Zhuo Gang Li Yang He |
author_facet | Jiyue Zhuo Gang Li Yang He |
author_sort | Jiyue Zhuo |
collection | DOAJ |
description | In order to address the problems associated with low detection accuracy, weak detection ability of small targets, insufficiently obvious differentiation of colors, and inability to accurately locate the actual position of the target object in the Formula Student Autonomous China, the YOLOv5s algorithm is improved by adding coordinate attention, modifying the color space transformation module, and adding a normalized Gaussian Wasserstein distance module and a monocular camera distance measurement module. Finally, it is experimentally verified that by adding and modifying the above modules, the YOLOv5s algorithm’s precision is improved by 6.9%, recall by 4.4%, and mean average precision by 4.9%; although the detection frame rate decreases, it still meets the requirement. Monocular camera distance measurement has a maximum error of 5.64% within 20 m in the Z-direction and 5.33% in the X-direction. |
first_indexed | 2024-03-10T20:48:51Z |
format | Article |
id | doaj.art-6ed6f0d984964cf6a894d065ecd24288 |
institution | Directory Open Access Journal |
issn | 2032-6653 |
language | English |
last_indexed | 2024-03-10T20:48:51Z |
publishDate | 2023-09-01 |
publisher | MDPI AG |
record_format | Article |
series | World Electric Vehicle Journal |
spelling | doaj.art-6ed6f0d984964cf6a894d065ecd242882023-11-19T18:31:47ZengMDPI AGWorld Electric Vehicle Journal2032-66532023-09-01141026910.3390/wevj14100269Research on Cone Bucket Detection Algorithm Based on Improved YOLOv5sJiyue Zhuo0Gang Li1Yang He2School of Automobile and Traffic Engineering, Liaoning University of Technology, Jinzhou 121001, ChinaSchool of Automobile and Traffic Engineering, Liaoning University of Technology, Jinzhou 121001, ChinaSchool of Automobile and Traffic Engineering, Liaoning University of Technology, Jinzhou 121001, ChinaIn order to address the problems associated with low detection accuracy, weak detection ability of small targets, insufficiently obvious differentiation of colors, and inability to accurately locate the actual position of the target object in the Formula Student Autonomous China, the YOLOv5s algorithm is improved by adding coordinate attention, modifying the color space transformation module, and adding a normalized Gaussian Wasserstein distance module and a monocular camera distance measurement module. Finally, it is experimentally verified that by adding and modifying the above modules, the YOLOv5s algorithm’s precision is improved by 6.9%, recall by 4.4%, and mean average precision by 4.9%; although the detection frame rate decreases, it still meets the requirement. Monocular camera distance measurement has a maximum error of 5.64% within 20 m in the Z-direction and 5.33% in the X-direction.https://www.mdpi.com/2032-6653/14/10/269deep learningtarget detectionYOLOv5attention mechanismmonocular camera distance measurement |
spellingShingle | Jiyue Zhuo Gang Li Yang He Research on Cone Bucket Detection Algorithm Based on Improved YOLOv5s World Electric Vehicle Journal deep learning target detection YOLOv5 attention mechanism monocular camera distance measurement |
title | Research on Cone Bucket Detection Algorithm Based on Improved YOLOv5s |
title_full | Research on Cone Bucket Detection Algorithm Based on Improved YOLOv5s |
title_fullStr | Research on Cone Bucket Detection Algorithm Based on Improved YOLOv5s |
title_full_unstemmed | Research on Cone Bucket Detection Algorithm Based on Improved YOLOv5s |
title_short | Research on Cone Bucket Detection Algorithm Based on Improved YOLOv5s |
title_sort | research on cone bucket detection algorithm based on improved yolov5s |
topic | deep learning target detection YOLOv5 attention mechanism monocular camera distance measurement |
url | https://www.mdpi.com/2032-6653/14/10/269 |
work_keys_str_mv | AT jiyuezhuo researchonconebucketdetectionalgorithmbasedonimprovedyolov5s AT gangli researchonconebucketdetectionalgorithmbasedonimprovedyolov5s AT yanghe researchonconebucketdetectionalgorithmbasedonimprovedyolov5s |