Cross-multi-camera pedestrian track recognition method

Abstract

The invention discloses a cross-multi-camera pedestrian track recognition method. The method comprises: building a multi-camera pedestrian track recognition system; acquiring all pedestrian tracking tracks of each camera; converting the position coordinates of the overlapped coverage area between the two adjacent cameras into a unified world coordinate system; marking pedestrians at the same position at the same time in a unified world coordinate system; converting the track data of the camera associated with the marked pedestrian track into a unified world coordinate system; combining the pedestrian tracks in a unified world coordinate system; identifying and calibrating pedestrians in the selected area; and repeating the steps to complete cross-multi-camera pedestrian trajectory trackingand recognition. The method is low in operation complexity, and can simply, reliably, efficiently and accurately identify and track the pedestrian trajectory.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to a pedestrian trajectory recognition method across multiple cameras. Background technique [0002] With the development of economy and technology, the identification of moving objects (such as pedestrians, vehicles, etc.) has been widely used. In a multi-camera surveillance system, a basic task is to connect cross-camera pedestrians at different times and locations, which is pedestrian re-identification technology. Specifically, re-identification is a process of visually matching single or multiple pedestrians in different scenes based on a series of data obtained by cameras distributed in different scenes at different times. The main purpose of "pedestrian re-identification" is to determine whether a pedestrian in a camera has appeared in other cameras, that is, it is necessary to compare the characteristics of a pedestrian with other pedestrians to determine whether ...

AI Technical Summary

Problems solved by technology

In the process of pedestrian recognition, usually due to the influence of multiple factors such as pedestrian posture, illumination, camera angle, etc., the characteristics of different pedestrians may be more similar than those of the same pedestrian, which makes it difficult to search for pedestrians.

[0004] Existing pedestrian re-identification technologies focus on how a single camera or multiple cameras can enhance the recognition rate of a single algorithm for pedestrian re-identification. There are no references and references for the system recognition rate of pedestrian recognition systems.

Images