ABSTRACT
The recognition of tire sidewall text refers to the technology that automatically detects and extracts textual information on tire sidewalls in dark background. This article explores the importance of tire sidewall text recognition and proposes a lightweight network for detecting key imprint text regions based on You Only Look Once v5 (YOLOv5). To enhance detection accuracy whilst minimizing parameter and computational complexity, this article replaces the backbone network of YOLOv5 with the EMO network and introduces the C3Faster module proposed in this article to replace the original C3 module in YOLOv5's Neck network, because convolution operations in the C3 module introduce a lot of computation. This accelerates inference while mitigating parameters and computational complexity. Additionally, the number of detection heads is changed to provide more suitable scale outputs on the dataset. Experimental results demonstrate that the refined algorithm yields a 12.1% enhancement in accuracy when compared to YOLOv5s.
- Zeng Y, Xiang A, Mou X. Research on an image acquisition System based on Camera Link [J]. Computer Application and Software, 2010, 27(11): 245-249.Google Scholar
- Florian Spiess, Lucas Reinhart, Norbert Strobel, Dennis Kaiser, Samuel Kounev, and Tobias Kaupp, "People Detection with Depth Silhouettes and Convolutional Neural Networks on a Mobile Robot," Journal of Image and Graphics, Vol. 9, No. 4, pp. 135-139, December 2021. doi: 10.18178/joig.9.4.135-139Google ScholarCross Ref
- Edisanter Lo, "Target Detection Algorithms in Hyperspectral Imaging Based on Discriminant Analysis," Journal of Image and Graphics, Vol. 7, No. 4, pp. 140-144, December 2019. doi: 10.18178/joig.7.4.140-144Google ScholarCross Ref
- Girshick R, Donahue J, Darrell T, Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2014: 580-587.Google Scholar
- Ren S, He K, Girshick R, (2015)Faster r-cnn: Towards real-time object detection with region proposal networks[J]. Advances in neural information processing systems. 9199(10.5555): 2969239-2969250.Google Scholar
- Cai Z, Vasconcelos N.(2018) Cascade r-cnn: Delving into high quality object detection[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 6154-6162.Google Scholar
- Liu W, Anguelov D, Erhan D, Ssd: Single shot multibox detector[C]//Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14. Springer International Publishing, 2016: 21-37.doi: 10.1007/978-3-319-46448-0_2Google ScholarCross Ref
- Redmon J, Divvala S, Girshick R, You only look once: Unified, real-time object detection[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 779-788,doi: 10.1109/CVPR.2016.91..Google ScholarCross Ref
- Zhao J, Zhang X, Yan J, A wheat spike detection method in UAV images based on improved YOLOv5[J]. Remote Sensing, 2021, 13(16): 3095.Google ScholarCross Ref
- Zhu L, Geng X, Li Z, Improving YOLOv5 with attention mechanism for detecting boulders from planetary images[J]. Remote Sensing, 2021, 13(18): 3776.Google ScholarCross Ref
- Zhang K; Zhang P; Chen J; Long M; Lin W. Dangerous Goods Detection based on improved YOLOv5s X-ray image [J]. Journal of Shaanxi University of Science and Technology, 2023, 41 (06): 176-183+200. doi:10.19481/j.cnki.issn2096-398x.2023.06.006Google ScholarCross Ref
- Liu Z, Lin Y, Cao Y, Swin transformer: Hierarchical vision transformer using shifted windows[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2021: 10012-10022.doi: 10.1109/ICCV48922.2021.00986.Google ScholarCross Ref
- Li J, Xia X, Li W, Next-vit: Next generation vision transformer for efficient deployment in realistic industrial scenarios[J]. arXiv preprint arXiv:2207.05501, 2022.Google Scholar
- Zhang J, Li X, Li J, Rethinking mobile block for efficient neural models[J]. arXiv preprint arXiv:2301.01146, 2023.Google Scholar
- Chen J, Kao S, He H, Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023: 12021-12031.doi: 10.1109/CVPR52729.2023.01157.Google ScholarCross Ref
- Chollet F. Xception: Deep learning with depthwise separable convolutions[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 1251-1258.Google Scholar
Index Terms
- The Tire Sidewall Key Information Region Detection Algorithm based on the Improvement of YOLOv5
Recommendations
Anomaly Detection Model for Key Places Based on Improved YOLOv5
Artificial Intelligence and SecurityAbstractIn recent years, key places such as underground stations and train stations, which are crowded and highly mobile, have become key targets for abnormal behaviour such as violence by some extremists or violent elements. The public safety risks in ...
Small-object detection based on YOLOv5 in autonomous driving systems
Highlights- We discuss the benefits of accurate detection of small objects like traffic signs and traffic lights in autonomous driving.
- We analyze the practical limitations of the original YOLOv5 structure.
- We propose novel architectural ...
AbstractWith the rapid advancements in the field of autonomous driving, the need for faster and more accurate object detection frameworks has become a necessity. Many recent deep learning-based object detectors have shown compelling performance for the ...
UAV small target detection algorithm based on an improved YOLOv5s model
AbstractThe targets of UAV target detection are usually small targets, and the backgrounds are complex. In this work, aiming at the problem that small targets are easy to be missed or misdetected during the UAV detection, an improved YOLOv5s_MSES target ...
Highlights- Improved YOLOv5s_MSES algorithm for small target detection in UAV aerial photography.
- Introduction of Small target detection module STD to enhance detection of small targets.
- Multi-scale feature fusion module for improved accuracy ...
Comments