基于深度学习的道路交通拥堵检测

Road traffic congestion detection based on deep learning

近年来,随着我国经济的快速发展,城市车辆拥有量急剧增加。人民在享受拥有车辆带来的极大方便的同时也受到了交通拥堵这一交通问题的困扰。如何实时有效地检测道路交通拥堵,以便及时采取交通拥堵治理措施,也成了当前智能交通领域研究的热点。文章提出了一种基于道路监控视频的深度学习算法去进行道路交通拥堵事件的检测。检测算法通过车辆检测,结合车辆速度、道路车道数以及车辆密度等因素,建立了一种道路交通拥堵检测模型。通过实验表明,本检测算法模型在交通拥堵检测的实时性及准确性方面得到了较高的提升。

In recent years,with the rapid development of China's economy,the ownership of urban vehicles has increased dramatically.People enjoy the great convenience of owning vehicles,and at the same time enjoy the trouble of traffic congestion.How to detect road traffic congestion in real time and effectively,so as to take timely measures to deal with traffic congestion,has become a hot research topic in the field of intelligent transportation.In this paper,a depth learning algorithm based on road surveillance video is proposed to detect traffic congestion.Through vehicle detection,combined with the factors of vehicle speed,road lane number,and vehicle density,a road traffic congestion detection model is established.Experiments show that the proposed algorithm model can improve the real-time performance and accuracy of traffic congestion detection.