People flow analysis method and device based on depth camera

Abstract

The invention is suitable for the field of machine vision, and provides a pedestrian flow analysis method and device based on a depth camera, and the method comprises the steps: obtaining a pedestrian image set of a target detection region through the depth camera, wherein the pedestrian image set comprises multiple frames of pedestrian images; importing the pedestrian images into a human body detection network, and outputting a human body detection image corresponding to each frame of pedestrian image; determining motion tracking data of a plurality of pedestrian objects contained in the target detection area based on the human body detection images corresponding to the multi-frame continuous pedestrian images; and based on the motion tracking data of the plurality of pedestrian objects, generating pedestrian flow analysis information about the target detection area. According to the invention, the human body detection network is obtained through deep learning training, pedestrians can be accurately tracked, and the pedestrian image is a depth image, so that the problem that the privacy of the pedestrians is invaded by a color image is avoided, and information except a plane dimension is also displayed.

Description

technical field [0001] The present application belongs to the field of machine vision, and in particular relates to a method and device for analyzing people flow based on a depth camera. Background technique [0002] With the improvement of public security awareness, public security management and public security early warning are an indispensable part, and people flow analysis is widely used in shopping malls, scenic spots, airports and other public places with large pedestrian flow, which provides great support for public security management, It provides an important basis for public safety early warning and business decision-making. [0003] At present, the main method of people flow analysis is to use a three-color camera to obtain the pedestrian image set in the area where the people flow analysis needs to be performed, and to achieve the purpose of pedestrian detection by identifying a single human feature (such as a face or head) contained in the pedestrian image set,...

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present application provides a depth camera-based pedestrian flow analysis method and device, which can obtain a pedestrian image set through the depth camera, and import the multi-frame pedestrian images in the pedestrian image set into the human body detection network, so as to determine the target of the depth camera Detect the motion tracking data of pedestrian objects in the area, and further generate crowd flow analysis information. The human detection network is obtained through deep learning training, which can accurately track pedestrians, and the input of the human detection network is acquired by the depth camera. Pedestrian images, that is, depth images, thereby avoiding the problem of color images violating the privacy of pedestrians, and solving the problem that color images in the prior art can only reflect information in the plane dimension and cannot accurately track pedestrians

Images