Vehicle counting method and system based on multiplex detection area

Abstract

The invention provides a vehicle counting method and system based on a multiplex detection area. The method comprises the steps of aiming at a current frame for counting vehicles in a target traffic video, obtaining the state of a first detection area and the state of a second detection area of a target lane in the current frame; if the first detection area is in an occupied state and the second detection area is in an idle state, according to the time sequence of the frame, judging whether subsequent frames of the current frame satisfy a first preset condition or not in sequence until the subsequent frame satisfying the first preset condition is obtained, wherein the first preset condition is that the first detection area of the target lane is in the idle state and the second detection area is in the occupied state; adding 1 to the counting value of the vehicles in the first direction of the target lane, and regarding the next frame which is adjacent to the subsequent frame and satisfies the first preset condition as the next current frame for vehicle counting. By means of the vehicle counting method and system, the accuracy of vehicle counting is improved, and the influence of shadows is lowered.

Description

technical field [0001] The invention belongs to the technical field of intelligent transportation, and more specifically relates to a vehicle counting method and system based on multiple detection areas. Background technique [0002] In intelligent transportation, real-time collection of vehicle flow in traffic is of great significance. For example, the optimal control of traffic lights is realized through vehicle flow, so that the traffic flow can be reasonably adjusted according to the on-site traffic flow conditions. The green light release time is increased in the direction of large traffic flow, and the green light release time is reduced in the direction of relatively small traffic flow, and there will be no empty lanes occupying the time, slowing down the stagnation phenomenon, increasing the traffic rate of highway traffic, and optimizing urban traffic. [0003] There are generally two ways to calculate traffic flow through video, one is based on the identification ...

AI Technical Summary

Problems solved by technology

[0004] The single-area detection method in the prior art is prone to false detection in the case of shadows or when the vehicle is traveling in reverse, resulting in inaccurate vehicle counting

Images