Vehicle Logo Detection Method Based on Improved YOLOv4
A vehicle logo occupies a small proportion of a car and has different shapes. These characteristics bring difficulties to machine-vision-based vehicle logo detection. To improve the accuracy of vehicle logo detection in complex backgrounds, an improved YOLOv4 model was presented. Firstly, the CSPDen...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/20/3400 |
| _version_ | 1797473572117020672 |
|---|---|
| author | Xiaoli Jiang Kai Sun Liqun Ma Zhijian Qu Chongguang Ren |
| author_facet | Xiaoli Jiang Kai Sun Liqun Ma Zhijian Qu Chongguang Ren |
| author_sort | Xiaoli Jiang |
| collection | DOAJ |
| description | A vehicle logo occupies a small proportion of a car and has different shapes. These characteristics bring difficulties to machine-vision-based vehicle logo detection. To improve the accuracy of vehicle logo detection in complex backgrounds, an improved YOLOv4 model was presented. Firstly, the CSPDenseNet was introduced to improve the backbone feature extraction network, and a shallow output layer was added to replenish the shallow information of small target. Then, the deformable convolution residual block was employed to reconstruct the neck structure to capture the various and irregular shape features. Finally, a new detection head based on a convolutional transformer block was proposed to reduce the influence of complex backgrounds on vehicle logo detection. Experimental results showed that the average accuracy of all categories in the VLD-45 dataset was 62.94%, which was 5.72% higher than the original model. It indicated that the improved model could perform well in vehicle logo detection. |
| first_indexed | 2024-03-09T20:18:20Z |
| format | Article |
| id | doaj.art-577bf15a6b0443df9bc9a3a6750a2e79 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T20:18:20Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-577bf15a6b0443df9bc9a3a6750a2e792023-11-23T23:54:31ZengMDPI AGElectronics2079-92922022-10-011120340010.3390/electronics11203400Vehicle Logo Detection Method Based on Improved YOLOv4Xiaoli Jiang0Kai Sun1Liqun Ma2Zhijian Qu3Chongguang Ren4School of Computer Science and Technology, Shandong University of Technology, Zibo 255000, ChinaSchool of Computer Science and Technology, Shandong University of Technology, Zibo 255000, ChinaSchool of Computer Science and Technology, Shandong University of Technology, Zibo 255000, ChinaSchool of Computer Science and Technology, Shandong University of Technology, Zibo 255000, ChinaSchool of Computer Science and Technology, Shandong University of Technology, Zibo 255000, ChinaA vehicle logo occupies a small proportion of a car and has different shapes. These characteristics bring difficulties to machine-vision-based vehicle logo detection. To improve the accuracy of vehicle logo detection in complex backgrounds, an improved YOLOv4 model was presented. Firstly, the CSPDenseNet was introduced to improve the backbone feature extraction network, and a shallow output layer was added to replenish the shallow information of small target. Then, the deformable convolution residual block was employed to reconstruct the neck structure to capture the various and irregular shape features. Finally, a new detection head based on a convolutional transformer block was proposed to reduce the influence of complex backgrounds on vehicle logo detection. Experimental results showed that the average accuracy of all categories in the VLD-45 dataset was 62.94%, which was 5.72% higher than the original model. It indicated that the improved model could perform well in vehicle logo detection.https://www.mdpi.com/2079-9292/11/20/3400vehicle logosmall object detectionDenseNetdeformable convolutionVision Transformer |
| spellingShingle | Xiaoli Jiang Kai Sun Liqun Ma Zhijian Qu Chongguang Ren Vehicle Logo Detection Method Based on Improved YOLOv4 Electronics vehicle logo small object detection DenseNet deformable convolution Vision Transformer |
| title | Vehicle Logo Detection Method Based on Improved YOLOv4 |
| title_full | Vehicle Logo Detection Method Based on Improved YOLOv4 |
| title_fullStr | Vehicle Logo Detection Method Based on Improved YOLOv4 |
| title_full_unstemmed | Vehicle Logo Detection Method Based on Improved YOLOv4 |
| title_short | Vehicle Logo Detection Method Based on Improved YOLOv4 |
| title_sort | vehicle logo detection method based on improved yolov4 |
| topic | vehicle logo small object detection DenseNet deformable convolution Vision Transformer |
| url | https://www.mdpi.com/2079-9292/11/20/3400 |
| work_keys_str_mv | AT xiaolijiang vehiclelogodetectionmethodbasedonimprovedyolov4 AT kaisun vehiclelogodetectionmethodbasedonimprovedyolov4 AT liqunma vehiclelogodetectionmethodbasedonimprovedyolov4 AT zhijianqu vehiclelogodetectionmethodbasedonimprovedyolov4 AT chongguangren vehiclelogodetectionmethodbasedonimprovedyolov4 |