ABSTRACT
To address the technical shortcomings of current autonomous driving systems for traffic sign recognition, this paper proposes a traffic sign recognition system based on the improved YOLOv5 algorithm. The system uses the pytorch deep learning framework as the system substrate to ensure a larger focus on the effective features without increasing the computational power of the network, and the deep learning system can speed up the recognition speed and improve the accuracy of the recognition system during the system iteration. For the training process of the system, firstly, various traffic sign icons in different situations are selected for data set creation and image pre-processing; secondly, the recognition network of the recognition system is established by using the pytorch deep learning framework, and the initial network recognition effect is poor, only 20.7%; and then the database is imported for model training, and the recognition accuracy and recognition speed of the system are improved in the process of multiple iterations. The database is then imported and the model is trained to improve the recognition accuracy and speed of the system in several iterations. Finally, the recognition ability of the system is enhanced in various environments and the average recognition accuracy of not less than 80% is achieved.
- Deng Kaiwen, Ge Chenyang. Improve YOLOv5 lightweight traffic infrared target detection [J/OL]. Computer engineering and application: 1-13 [2023-04-03]. http://kns.cnki.net/kcms/detail/11.2127.TP.20230329.0923.006.html.Google Scholar
- Wu Jingwen, Bruce Lee, Liang Xiangyang. Target tracking algorithm based on YOLOv5 to wear a face mask face recognition system [J]. Journal of modern information technology, 2023, 7 (6): 61-64. The DOI: 10.19850 / j.carol carroll nki. 2096-4706.2023.06.016.Google Scholar
- KAPLAN B, SELCAN G, HUSEYIN O, On circular traffic sign detection and recognition [J]. Expert Systems with Applications, 2016, 48: 67-75.Google ScholarDigital Library
- LI H J, QIU T S, SONG H Y, A fast traffic signs detection method based on color segmentation and improved radial symmetry [J]. ICIC Express Letters, 2014, 8(8): 2175-2180.Google Scholar
- WANG J G, ZHOU L B. Traffic light recognition with high dynamic range imaging and deep learning [J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(4): 1341-1352.Google ScholarCross Ref
- Wang Yaru, Liu Yuqing, Huang Luyao, Li Zhihao. Research on underwater image enhancement technology based on convolutional neural network [J]. Manufacturing Automation, 2023, 45(02):65-68+92.Google Scholar
- Wang Han-han, Wang Guo-dong, Zhang Chan-yue, Dong Hao. Of underwater image enhancement based on the red channel attention mechanism [J]. Journal of digital ocean and underwater offensive and defensive, 2023, 6 (01): 48-55, DOI: 10.19838 / j.i SSN. 2096-5753.2023.01.006.Google Scholar
- Zhou Ting, Du Jianqiang, Zhu Yanchen, Feng Zhenqian. Image recognition of ethnomedicine plants with embedded compression-incentive mechanism ResNet [J]. Software Guide,2023,22(02):1-7. (in Chinese)Google Scholar
- Lu Qi, Yu Yuanqiang, Xu Daoming, etc Improved YOLOv5 small rotor unmanned aerial vehicle target detection algorithm [J] Computer Science, 2023, 50 (S2): 212-219Google Scholar
- Luo Zhuangzhi, Liang Shuai, Yang Jingxin, etc A sitting posture detection method based on improved YOLOv5 face and binocular vision [J] Foreign Electronic Measurement Technology, 2023, 42 (11): 143-151 DOI: 10.19652/j.cnki.femt2305091Google ScholarCross Ref
Recommendations
Research Progress of Facial Expression Recognition Based on Deep Learning
CAIH2020: Proceedings of the 2020 Conference on Artificial Intelligence and HealthcareFacial expression recognition is a practical application in the field of artificial intelligence. This article focuses on the introduction of the principles of each facial expression recognition method based on deep learning in chronological order, as ...
A Traffic Sign Recognition Method Based on YOLOv5 Deep Learning Algorithm
ICMLSC '23: Proceedings of the 2023 7th International Conference on Machine Learning and Soft ComputingAiming at the problems of low accuracy and slow recognition efficiency of the traditional traffic sign recognition algorithm in complex environment, a deep learning traffic sign recognition method based on YOLOv5 is proposed. Firstly, the Chinese ...
Facial expression recognition with Convolutional Neural Networks
Facial expression recognition has been an active research area in the past 10 years, with growing application areas including avatar animation, neuromarketing and sociable robots. The recognition of facial expressions is not an easy problem for machine ...
Comments