Public-transport people flow counting method and system based on optical-flow counting

Abstract

The invention discloses a public-transport people flow counting method based on optical-flow counting. The method includes the following steps: 1, carrying out compression and format unification on acquired surveillance video images; 2, preprocessing the surveillance video images after format unification; and 3, obtaining, by counting, the number of people getting on/off a bus. A public-transportpeople flow counting system based on optical-flow counting disclosed by the invention includes an image collection unit, a video compression unit, an image preprocessing unit and a moving-target detection unit. According to the counting system and method, noises pollution generated by a bus surveillance system due to bus body shaking or illumination shadow changing in shooting and acquiring the images is eliminated through preprocessing the color surveillance video images, an area where a moving target is located is obtained by calibration through utilizing a moving-target area locating algorithm, optical-flow calculation is carried out on the calibrated area, and an optical-flow solving operation amount is greatly decreased.

Description

technical field [0001] The invention relates to the field of passenger flow statistics, in particular to a bus passenger flow statistics method and system based on optical flow counting. Background technique [0002] As an important part of urban traffic, public transport is an important way to solve urban traffic congestion. The quality of its operation directly affects the operating efficiency of social and economic life and people's quality of life. At present, there are many problems that need to be solved urgently in my country's urban public transportation, such as: unreasonable planning of urban bus routes, low train density during peak passenger flow, lack of scientificity in the setting of BRT transfer stations, low bus transportation efficiency, and lagging route configuration, etc. . [0003] As an important part of intelligent public transportation, the passenger flow statistics system can quickly and accurately obtain the real-time number of passengers on the bu...

AI Technical Summary

Problems solved by technology

4. There are large individual differences among passengers on board

5. It is difficult to count the number of people in the car

However, there are still the following disadvantages in using the optical flow method to detect objects in video images: 1. The traditional optical flow detection algorithm has a large amount of calculation and takes a long time, which is not applicable in the case of strict real-time requirements.

2. Since changing light will be mistakenly identified as optical flow, this method is sensitive to light, which will affect the recognition effect

Therefore, it is difficult to accurately identify the flow of people in some extreme lighting environments

Images