A Lightweight Traffic Sign Recognition Model Based on Improved YOLOv5
Traffic sign recognition and detection is a key technology in automatic vehicle driving and driver assistance systems. However, existing traffic sign recognition algorithms suffer from problems such as large model size, complex computation, high computational cost, which make it difficult to achieve...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10287975/ |
| _version_ | 1797649761204961280 |
|---|---|
| author | Jie Yang Ting Sun Wenchao Zhu Zonghao Li |
| author_facet | Jie Yang Ting Sun Wenchao Zhu Zonghao Li |
| author_sort | Jie Yang |
| collection | DOAJ |
| description | Traffic sign recognition and detection is a key technology in automatic vehicle driving and driver assistance systems. However, existing traffic sign recognition algorithms suffer from problems such as large model size, complex computation, high computational cost, which make it difficult to achieve an effective balance between detection speed and detection accuracy. This paper proposed an improved lightweight recognition algorithm, which is based on YOLOv5. This algorithm replaces the convolutional structure in the original YOLOv5 neck network with Ghost Module and C3Ghost Module, thereby reducing redundant features in the feature fusion process, lowering computational cost and the number of parameters. The structure of the PAN network was improved and the hybrid attention mechanism module CBAM was introduced to capture key information in traffic signs. Cross-layer connections were added to shorten the path of information transfer in feature pyramid network, which fused more features and improved the network feature recognition accuracy. In addition, the EIoU_Loss function was adopted as the bounding box regression loss function to improve the localization accuracy of the algorithm. The performance of the improved algorithm was also verified on the Chinese traffic sign dataset. Experimental results showed that the improved algorithm’s detection accuracy was enhanced by 1.2%, while mAP@0.5 and mAP@0.5:0.95 were enhanced by 1.5% and 3.4% respectively over the existing YOLOv5 algorithm, and the overall parameter numbers and computational cost of the model were reduced by 14.5% and 16%. The proposed algorithm performs better than the current mainstream detection algorithms, has higher recognition accuracy in multiple environments, and meets the demand for real-time traffic sign recognition. |
| first_indexed | 2024-03-11T15:50:40Z |
| format | Article |
| id | doaj.art-240f5c763cb9418f82f40d2c4aba660a |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-11T15:50:40Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-240f5c763cb9418f82f40d2c4aba660a2023-10-25T23:01:16ZengIEEEIEEE Access2169-35362023-01-011111599811601010.1109/ACCESS.2023.332600010287975A Lightweight Traffic Sign Recognition Model Based on Improved YOLOv5Jie Yang0https://orcid.org/0000-0003-2134-7700Ting Sun1https://orcid.org/0000-0002-7304-3795Wenchao Zhu2https://orcid.org/0000-0003-0590-8168Zonghao Li3https://orcid.org/0009-0003-5401-7043School of Machinery and Transportation, Southwest Forestry University, Kunming, ChinaSchool of Machinery and Transportation, Southwest Forestry University, Kunming, ChinaSchool of Machinery and Transportation, Southwest Forestry University, Kunming, ChinaChina Beijing Jinzhi Tianzheng Intelligent Control Company, Beijing, ChinaTraffic sign recognition and detection is a key technology in automatic vehicle driving and driver assistance systems. However, existing traffic sign recognition algorithms suffer from problems such as large model size, complex computation, high computational cost, which make it difficult to achieve an effective balance between detection speed and detection accuracy. This paper proposed an improved lightweight recognition algorithm, which is based on YOLOv5. This algorithm replaces the convolutional structure in the original YOLOv5 neck network with Ghost Module and C3Ghost Module, thereby reducing redundant features in the feature fusion process, lowering computational cost and the number of parameters. The structure of the PAN network was improved and the hybrid attention mechanism module CBAM was introduced to capture key information in traffic signs. Cross-layer connections were added to shorten the path of information transfer in feature pyramid network, which fused more features and improved the network feature recognition accuracy. In addition, the EIoU_Loss function was adopted as the bounding box regression loss function to improve the localization accuracy of the algorithm. The performance of the improved algorithm was also verified on the Chinese traffic sign dataset. Experimental results showed that the improved algorithm’s detection accuracy was enhanced by 1.2%, while mAP@0.5 and mAP@0.5:0.95 were enhanced by 1.5% and 3.4% respectively over the existing YOLOv5 algorithm, and the overall parameter numbers and computational cost of the model were reduced by 14.5% and 16%. The proposed algorithm performs better than the current mainstream detection algorithms, has higher recognition accuracy in multiple environments, and meets the demand for real-time traffic sign recognition.https://ieeexplore.ieee.org/document/10287975/Traffic sign detectiondeep learningattention mechanismlightweight |
| spellingShingle | Jie Yang Ting Sun Wenchao Zhu Zonghao Li A Lightweight Traffic Sign Recognition Model Based on Improved YOLOv5 IEEE Access Traffic sign detection deep learning attention mechanism lightweight |
| title | A Lightweight Traffic Sign Recognition Model Based on Improved YOLOv5 |
| title_full | A Lightweight Traffic Sign Recognition Model Based on Improved YOLOv5 |
| title_fullStr | A Lightweight Traffic Sign Recognition Model Based on Improved YOLOv5 |
| title_full_unstemmed | A Lightweight Traffic Sign Recognition Model Based on Improved YOLOv5 |
| title_short | A Lightweight Traffic Sign Recognition Model Based on Improved YOLOv5 |
| title_sort | lightweight traffic sign recognition model based on improved yolov5 |
| topic | Traffic sign detection deep learning attention mechanism lightweight |
| url | https://ieeexplore.ieee.org/document/10287975/ |
| work_keys_str_mv | AT jieyang alightweighttrafficsignrecognitionmodelbasedonimprovedyolov5 AT tingsun alightweighttrafficsignrecognitionmodelbasedonimprovedyolov5 AT wenchaozhu alightweighttrafficsignrecognitionmodelbasedonimprovedyolov5 AT zonghaoli alightweighttrafficsignrecognitionmodelbasedonimprovedyolov5 AT jieyang lightweighttrafficsignrecognitionmodelbasedonimprovedyolov5 AT tingsun lightweighttrafficsignrecognitionmodelbasedonimprovedyolov5 AT wenchaozhu lightweighttrafficsignrecognitionmodelbasedonimprovedyolov5 AT zonghaoli lightweighttrafficsignrecognitionmodelbasedonimprovedyolov5 |