Real-time bicycle detection at signalized intersections using thermal imaging technology Topic: Safety and traffic management Subtopic: vulnerable road users (cyclists, pedestrians, elderly, disabled, etc.)

摘要

Governments and authorities worldwide are promoting bicycle use in cities, as this improves health and the quality of life in general. Safety and efficiency of bicyclists has become a major focus. To achieve this, a smarter approach towards the control of signalized intersections is needed. Various traditional detection technologies, such as video, microwave radar and electromagnetic loops, can be used to detect vehicles at signalized intersections, but none of these can consistently separate bicycles from other traffic, day and night, in various weather conditions and in multiple dedicated and/or mixed traffic lanes. As bicycles should get a higher priority and also require longer green time to safely cross the signalized intersection, traffic managers are looking for alternative detection systems that can make the distinction between bicycles and other vehicles near the stop bar. In this paper, the advantages and disadvantages of video image and thermal image based approaches are explored and compared. Also, the specific technical challenges are highlighted for the development of a system that combines thermal image capturing, image processing and output triggering to the traffic light controller in near real-time and in a single housing.