Method and device for acquiring target object behavior data based on video

Abstract

The invention provides a method for acquiring behavior data of a target object based on video. First, play the video to be processed; then, according to the predetermined target recognition algorithm and target tracking algorithm, identify and track the target object in the video, and calculate the The physical coordinates of the target object; finally, calculate and obtain the behavior data of the target object according to the physical coordinates, the corresponding frame number, and the frame rate of the video. Compared with the prior art, the present invention is based on video, and uses the target recognition algorithm, target tracking algorithm, and the corresponding relationship between video pixel coordinates and physical coordinates to realize the acquisition of the physical coordinates of the target object in the video, and then according to the frame of the video Rate and number of frames, calculate and obtain the behavior data of the target object, so as to provide real, effective, objective and large amount of data support for the study of the micro behavior of pedestrians.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a video-based acquisition method of target object behavior data and a video-based target object behavior data acquisition device. Background technique [0002] With the rapid development of the economy and the acceleration of urbanization, the rapid growth of travel demand has increasingly diversified and complicated the requirements of the passenger transport system. The advantages of frequency, high efficiency, and large capacity have gradually become one of the important components of the urban public transport system. As a node with a strong radiation effect in the urban rail transit network, the urban rail transit hub has always regarded passenger transport organization and service as the core task of station operation, and the issue of passenger flow line organization is also an important indicator to measure the passenger transport capacity of the hub and ...

AI Technical Summary

Problems solved by technology

[0003] At present, most of the pedestrian behavior research at home and abroad is based on mathematical theory and computer means. Although some achievements have been achieved, because the pedestrian behavior data generally come from experiments or simulations, the amount of data is small, and it is difficult to be true, effective, and accurate. Objectively reflect the behavior of pedestrians

Images