Queue length detection method and device and server

Abstract

The invention provides a queue length detection method and device and a server. The method comprises the following steps of initially dividing the monitoring image into an upper detection region and alower detection region, and automatically adjusting the boundary between the upper detection region and the lower detection region; carrying out vehicle positioning on the image of the lower detection area, obtaining the lane where the corresponding vehicle is located, and judging whether the vehicle is stationary or not; if the vehicle is stationary, processing the image of the lane in each section in the upper detection area to obtain the position coordinates of the tail of the queue when the vehicle is queued; according to the coordinates of the tail position and the starting coordinate ofthe lane, obtaining the length of the lane line between the two coordinates, and converting the corresponding queue length according to the coordinate mapping relationship. The vehicle has low misjudgment rate, short detection time, low consumption of human resources, low queuing misdetection rate, high accuracy of queuing length, and good robustness, and can automatically adjust the boundary line of two detection areas, improve the interference problem of adjacent lanes, and realize good queuing length detection.

Description

technical field [0001] The present invention relates to the field of intelligent transportation, in particular to a queue length detection method, device and server. Background technique [0002] With the rapid development of the transportation industry, traffic congestion has become more and more serious, especially the congestion in front of expressway toll stations and urban traffic lights. Therefore, for an intelligent transportation system (Intelligent Transportation System, ITS) that can reasonably divert urban road vehicles, control traffic, and alleviate urban traffic congestion, how to obtain high-accuracy vehicle queuing lengths at traffic intersections in real time is an extremely important task. important technical issues. [0003] For now, the existing vehicle queuing length detection scheme is to directly calculate and process the frame difference value of the monitoring image, and analyze the change of the frame difference value, so as to judge the start and ...

AI Technical Summary

Problems solved by technology

However, this scheme has a high misjudgment rate of vehicles, a long detection time, and consumes a lot of human resources. It does not take into account the impact of vehicles in the adjacent lane on the vehicles in the current lane. The queuing false detection rate is high, and the overall queuing judgment accuracy is low. not tall

Images