A Vehicle Recognition Model Based on Improved YOLOv5
The rapid development of the automobile industry has made life easier for people, but traffic accidents have increased in frequency in recent years, making vehicle safety particularly important. This paper proposes an improved YOLOv5s algorithm for vehicle identification and detection to reduce vehi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/6/1323 |
| _version_ | 1797612194148384768 |
|---|---|
| author | Lei Shao Han Wu Chao Li Ji Li |
| author_facet | Lei Shao Han Wu Chao Li Ji Li |
| author_sort | Lei Shao |
| collection | DOAJ |
| description | The rapid development of the automobile industry has made life easier for people, but traffic accidents have increased in frequency in recent years, making vehicle safety particularly important. This paper proposes an improved YOLOv5s algorithm for vehicle identification and detection to reduce vehicle driving safety issues based on this problem. In order to solve the problems of a disappearing model training gradient in the YOLOv5s algorithm, difficulty in recognizing small objects and poor recognition accuracy caused by the boundary frame regression function, it is necessary to implement a new function. These aspects have been enhanced in this article. On the basis of the traditional YOLOv5s algorithm, the ELU activation function is used to replace the original activation function. The attention mechanism module is then added to the YOLOv5s algorithm’s backbone network to improve the feature extraction of small and medium-sized objects. The CIoU Loss function replaces the original regression function of YOLOv5s, thereby enhancing the convergence rate and measurement precision of the loss function. In this paper, the constructed dataset is utilized to conduct pertinent experiments. The experimental results demonstrate that, compared to the previous algorithm, the mAP of the enhanced YOLOv5s is 3.1% higher, the convergence rate is 0.8% higher, and the loss is 2.5% lower. |
| first_indexed | 2024-03-11T06:38:52Z |
| format | Article |
| id | doaj.art-6b867a28b0df4f73b0cedff5d158ac06 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T06:38:52Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-6b867a28b0df4f73b0cedff5d158ac062023-11-17T10:43:55ZengMDPI AGElectronics2079-92922023-03-01126132310.3390/electronics12061323A Vehicle Recognition Model Based on Improved YOLOv5Lei Shao0Han Wu1Chao Li2Ji Li3School of Electrical Engineering and Automation, Tianjin University of Technology, Tianjin 300384, ChinaSchool of Electrical Engineering and Automation, Tianjin University of Technology, Tianjin 300384, ChinaSchool of Electrical Engineering and Automation, Tianjin University of Technology, Tianjin 300384, ChinaSchool of Electrical Engineering and Automation, Tianjin University of Technology, Tianjin 300384, ChinaThe rapid development of the automobile industry has made life easier for people, but traffic accidents have increased in frequency in recent years, making vehicle safety particularly important. This paper proposes an improved YOLOv5s algorithm for vehicle identification and detection to reduce vehicle driving safety issues based on this problem. In order to solve the problems of a disappearing model training gradient in the YOLOv5s algorithm, difficulty in recognizing small objects and poor recognition accuracy caused by the boundary frame regression function, it is necessary to implement a new function. These aspects have been enhanced in this article. On the basis of the traditional YOLOv5s algorithm, the ELU activation function is used to replace the original activation function. The attention mechanism module is then added to the YOLOv5s algorithm’s backbone network to improve the feature extraction of small and medium-sized objects. The CIoU Loss function replaces the original regression function of YOLOv5s, thereby enhancing the convergence rate and measurement precision of the loss function. In this paper, the constructed dataset is utilized to conduct pertinent experiments. The experimental results demonstrate that, compared to the previous algorithm, the mAP of the enhanced YOLOv5s is 3.1% higher, the convergence rate is 0.8% higher, and the loss is 2.5% lower.https://www.mdpi.com/2079-9292/12/6/1323deep learningvehicle detectionYOLOv5attention mechanismartificial intelligence |
| spellingShingle | Lei Shao Han Wu Chao Li Ji Li A Vehicle Recognition Model Based on Improved YOLOv5 Electronics deep learning vehicle detection YOLOv5 attention mechanism artificial intelligence |
| title | A Vehicle Recognition Model Based on Improved YOLOv5 |
| title_full | A Vehicle Recognition Model Based on Improved YOLOv5 |
| title_fullStr | A Vehicle Recognition Model Based on Improved YOLOv5 |
| title_full_unstemmed | A Vehicle Recognition Model Based on Improved YOLOv5 |
| title_short | A Vehicle Recognition Model Based on Improved YOLOv5 |
| title_sort | vehicle recognition model based on improved yolov5 |
| topic | deep learning vehicle detection YOLOv5 attention mechanism artificial intelligence |
| url | https://www.mdpi.com/2079-9292/12/6/1323 |
| work_keys_str_mv | AT leishao avehiclerecognitionmodelbasedonimprovedyolov5 AT hanwu avehiclerecognitionmodelbasedonimprovedyolov5 AT chaoli avehiclerecognitionmodelbasedonimprovedyolov5 AT jili avehiclerecognitionmodelbasedonimprovedyolov5 AT leishao vehiclerecognitionmodelbasedonimprovedyolov5 AT hanwu vehiclerecognitionmodelbasedonimprovedyolov5 AT chaoli vehiclerecognitionmodelbasedonimprovedyolov5 AT jili vehiclerecognitionmodelbasedonimprovedyolov5 |