Multi-scene pedestrian volume counting method and system based on stereoscopic vision and binocular camera

Abstract

The invention provides a multi-scene pedestrian volume counting method and system based on stereoscopic vision and a binocular camera. The pedestrian volume counting method is based on binocular stereoscopic vision, and comprises the following steps: firstly, correcting a binocular image shot by a row-parallel binocular camera to obtain an epipolar-line-parallel binocular image; secondly, performing stereo matching on the corrected binocular image to obtain a parallax image; thirdly, detecting pedestrian targets in the obtained parallax image; and lastly, tracking and counting the targets according to the attribute features of the detection targets. The pedestrian volume counting system consists of the binocular camera, a DSP binocular acquisition and video processing module, a network transmission module and a terminal data analysis module. Through adoption of the pedestrian volume counting method and system provided by the invention, the number of people in different pedestrian volume entrance and exit scenes can be accurately counted, and data support is provided for a decision maker.

Description

technical field [0001] The invention relates to image monitoring and processing technology, in particular to a people flow counting technology based on image processing. Background technique [0002] The statistics of the flow of people can be widely used in public transportation, buses, shopping malls, exhibition halls, building passages and other places that need to count the flow of people, so as to provide indispensable data support for management and decision makers. For places such as buses and buses, the flow of people can assist functional departments to optimize their settings. For the retail industry, the flow of people can be linked with the sales volume, which can be used as a commercial basis for business decision makers. [0003] The current people counting methods are mainly divided into manual, mechanical, infrared and monocular video. These kinds of people counting methods have corresponding problems in practical application: [0004] Manual work is ineffi...

AI Technical Summary

Problems solved by technology

[0004] Manual work is inefficient and wastes human resources;

[0005] The mechanical type needs to bury the induction pedal under the passage, and touch the counter to count when people pass by. This method is easy to miss and miscount when people pass through densely;

[0006] Infrared type is to use infrared sensor to sense people when people pass by, and this method is difficult to be sensed by infrared sensor when the flow of people is blocked; at the same time, mechanical and infrared methods can only count the number of people in a single direction , cannot distinguish the two directions of in and out;

[0007] The method of monocular video mainly collects the video of the flow of people in the application place, scans the human body template, and judges the direction for counting. This method has poor environmental adaptability and is difficult to apply in mobile places

Images