In order to alleviate urban traffic pressure and improve road service level, this paper proposes a traffic signal timing scheme based on video identification technology, which dynamically adjusts the traffic light time by detecting the number of pedestrians waiting at the intersection. Meanwhile, Vissim micro-traffic simulation is presented to compare the fixed timing scheme implemented at the current intersection with the optimized timing scheme proposed in this paper. The experimental results show that the optimizing approach proposed here can on average shorten the delay time and the maximum queue length of vehicles by 29.13% and 32.93% separately, and the delay time of pedestrians by 12.03% in rush hours as well. Keywords: Traffic signal; Dynamic timing; Video recognition; Delay time; Service level

CICTP