Academic Journal of Engineering and Technology Science, 2024, 7(3); doi: 10.25236/AJETS.2024.070303.
Junhua Xu1, Jiawei Luo1, Jintu Wei1, Yiwen Luo1, Minhua Ye2, Junpeng Tang1, Ruihan Chen1, Xuewen Chen1, Di Ning3, Zhi Li1
1School of Mathematics and Computer, Guangdong Ocean University, Zhanjiang, 524088, China
2College of Ocean Engineering and Energy, Guangdong Ocean University, Zhanjiang, 524088, China
3School of Economics, Guangdong Ocean University, Zhanjiang, 524088, China
To detect common types of license plate, this paper proposes the LPD-YOLO algorithm based on YOLOv7 for license plate classification detection. The LPD -YOLO algorithm adopts the Content-Aware Reassembly of Features (CARAFE) upsampling operator to replace the nearest-neighbor interpolation method in YOLOv7, thereby improving the accuracy of object detection. Additionally, it introduces the Distribution Shifting Convolution (DSConv) module to replace some traditional convolutions in the YOLOv7 head network, achieving model lightweighting. Experimental results show that the LPD-YOLO algorithm achieves an mAP value of 91.72%, with a model computation of only 96G. This method features high accuracy and robustness, making it highly valuable in practical scenarios for license plate classification detection.
Deep learning, License plate detection, YOLOv7, CARAFE, DSConv
Junhua Xu, Jiawei Luo, Jintu Wei, Yiwen Luo, Minhua Ye, Junpeng Tang, Ruihan Chen, Xuewen Chen, Di Ning, Zhi Li. LPD-YOLO: A Lightweight License Plate Detection Method with Strong Generalization Ability. Academic Journal of Engineering and Technology Science (2024) Vol. 7, Issue 3: 12-16. https://doi.org/10.25236/AJETS.2024.070303.
[1] Abeid E E S, Mosa A M, Tabakh E M A M, et al. Antifungal activity of copper oxide nanoparticles derived from Zizyphus spina leaf extract against Fusarium root rot disease in tomato plants.[J]. Journal of Nanobiotechnology, 2024, 22(1), 28.
[2] Ruihan C, Minhua Y, Zhi L, et al. Empirical assessment of carbon emissions in Guangdong Province within the framework of carbon peaking and carbon neutrality: a lasso-TPE-BP neural network approach. [J]. Environmental science and pollution research international, 2023, 30(58):121647-121665.
[3] Wen Y, Chen Y, Wang K, et al. A Review of Pest Detection Based on Machine Vision [J]. Journal of China Oils and Grains Society, 2022, 37(10): 271-279.
[4] Cai P, Yang D, Zou Y, et al. Reconsidering Multi-Branch Aggregation for Semantic Segmentation[J]. Electronics, 2023, 12(15).