Liqun Ma
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Liqun Ma has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Chongguang Ren
School of Computer Science and Technology, Shandong University of Technology, Zibo, China
1 shared publication - Kai Sun
Zibo Special Equipment Inspection Institute, Zibo 255000, China
1 shared publication - Xiaoli Jiang
School of Computer Science and Technology, Shandong University of Technology, Zibo 255000, China
1 shared publication - Zhijian Qu
School of Computer Science and Technology, Shandong University of Technology, Zibo 255000, China
1 shared publication
Latest Publications
- Open Access
- 20 October 2022
- Published by MDPI AG in Electronics
- Vol. 11 (20) , 3400
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 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.
- 20 October 2022
- Published by MDPI AG in Electronics
- Vol. 11 (20) , 3400
Open AccessVehicle 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 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.