Analysis of Sidewalk Traffic Lights Setting Modes Optimization
Abstract
There are often some problems with the traditional setting mode of traffic lights, especially on some non-main roads. The unreasonable setting of pedestrian traffic lights can easily lead to empty spaces for people and vehicles, waste resources, and increase the risks of traffic congestion, Although the push-button traffic lights improves traffic efficiency, there is still a waste of waiting time for pedestrians and vehicles due to the fixed setting of the traffic time. This article mainly studies the use of machine learning to solve the recognition, motion direction, and time models of people and vehicles, and optimize pedestrian traffic light signals. By identifying pedestrians and vehicles and allocating release signal time reasonably, the waiting time of pedestrians and vehicles crossing the road can be reduced, and traffic accidents can be minimized. The optimized traffic system is applied to sidewalks on non-main roads, it can replace the push-button traffic lights, reduce manual intervention, save construction costs, and improve traffic efficiency.
References
- Wei Min Talks About Things. (2020) Why is the push-button traffic light not promoted in China, this is the original reason. September 14. https://baijiahao.baidu.com/s?id=1677774612046534092&wfr=spider&for=pc,.
- Dongming Xu. (2020) A face age recognition method based on cost sensitive convolutional neural networks [J]. Computer application research, (11):3516-3520.
- Haiyang Chen. (2014) Autonomous intelligent decision-making of traffic lights based on dynamic Bayesian networks [J]. Journal of Xi'an Engineering University, (4):474-479.
- Song Jiuqing, Huang Yalou, Kang Yewei, et al. (2006) Data Processing and Analysis in Intelligent Transportation Systems [J]. Computer Engineering and Applications, 42(8):5. DOI:10.3321/j.issn:1002-8331.2006.08.064.
- Jinpeng Li. (2019) Intelligent Traffic Light Scheduling Method Based on GA and LSTM [J]. Internet of Things Technology, (12):50-54.
- Zhihua Zhou. (2016) Machine Learning, Tsinghua University Press: Chapter 6 Support Vector Machines, Integrated Learning, pp.137-180, Chapter 5: Neural Networks. pp.114.
- Redmon, J., Divvala, S., Girshick, R. and Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 779-788.
- Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R. and Fei-Fei, L. (2014). Large-scale video classification with convolutional neural networks. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 1725-1732.
- Tran, D., Bourdev, L., Fergus, R., Torresani, L. and Paluri, M. (2015). Learning spatiotemporal features with 3d convolutional networks. In Proceedings of the IEEE international conference on computer vision, pp. 4489-4497.
- Donahue, J., Anne Hendricks, L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K. and Darrell, T., (2015). Long-term recurrent convolutional networks for visual recognition and description. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2625-2634.
- Xipeng Qiu. (2020) Neural Networks and Deep Learning, Chapter 6: Recurrent Neural Networks,Chapter 14, Deep Reinforcement Learning. Github Inc., June 14.
- Fern, X. (2008) Reinforcement Learning. In CS 434: Machine Learning and Data Mining. School of Electrical Engineering and Computer Science, Oregon State University.
- Panin, A. and Shvechikov, P. (2017) Practical Reinforcement Learning. Coursera and National Research University Higher School of Economics.