A Multi-Loop Vehicle-Counting Method under Gray Mode and RGB Mode

With the rapid development of road traffic, real-time vehicle counting is very important in construction intelligent transportation systems (ITSs). Compared with traditional technologies, video-based method for shows great importance and huge advantages its low cost, high efficiency, flexibility. However, many methods find difficulty balancing accuracy complexity algorithm. For example, compared simple methods, deep learning may achieve higher precision, but they also greatly increase In addition to that, most only work under one mode color, which a waste available information. Considering above, multi-loop vehicle-counting gray RGB was proposed this paper. Under modes, moving can be detected more completely; help multiple loops, could better deal different influencing factors, such as driving behavior, traffic environment, shooting angle, etc. The experimental results show that able count vehicles than 98.5% while dealing scenes.