Passenger flow detection method and detection system thereof

Abstract

The invention discloses a passenger flow detection method and a detection system thereof. The method includes: firstly, continuously reading images from surveillance video sources of vehicles; secondly, preprocessing the read images, and converting obtained gray images into a binary threshold form; detecting whether door opening and closing dual-detection parameters are changed or not from the video images so as to judge door open and closed states; when the door opening and closing dual-detection parameters are changed, judging the state as the door open state, and starting to detect passenger flow; when parameters of an identification detection line and a judgment detection line are changed, making statistics on number of the passengers and entry-exit directions of the passengers according to a parameter value range. An intelligent vehicle management system capable of realizing passenger flow detection and analysis is created by combining video cameras of the vehicles (such as buses) and taking the image processing technique as a core. Besides, statistical data detected by the system are transmitted to a vehicle supervision and management center in an Ethernet way for analysis, statistics and storage, so that intelligent dispatching of the vehicles is realized.

Description

technical field [0001] The invention relates to the technical field of passenger flow statistics, in particular to a passenger flow detection method and a detection system thereof. Background technique [0002] With the rapid development of the economy, the number of urban motor vehicles has increased sharply, and public transportation has become one of the priorities of urban construction. Bus passenger flow statistics, as the basis of the entire bus system management, can provide a reliable basis for the daily dispatch of the traffic system management, and can also provide a reference for the long-term planning of the bus management, which is of great significance to the coordinated control of urban traffic. [0003] At present, the bus passenger flow detection technology is mainly divided into the following categories: [0004] 1. Bus IC card passenger flow counting: This method counts the number of boarding passengers through the number of IC card punches. However, sinc...

AI Technical Summary

Problems solved by technology

[0004] 1. Bus IC card passenger flow counting: This method counts the number of boarding passengers through the number of IC card punches, but since IC cards are not necessary for every passenger, it is impossible to count all the number of boarding passengers and the number of people getting off at each station

[0005] 2. Pedal plate counting: the pressure sensor is triggered to automatically record the number of people when passengers get on and off the bus, but this type of counter cannot distinguish the direction of passengers getting on and off the bus and is easy to be damaged, and the maintainability is poor

[0006] 3. Passive infrared passenger flow counting: detect the thermal infrared signal emitted by the human body through the pyro-infrared probe, but because it is greatly affected by the passenger's clothing and the ambient temperature, the overall detection cannot be realized

[0007] 4. Active infrared passenger flow counting: using infrared r

Images