Human flow statistics method, device and system

Abstract

The embodiment of the invention provides a human flow statistics method, device and system. The method comprises a step of acquiring continuous frames of images collected by an image acquisition device, a step of inputting the continuous frames of images into a full convolutional neural network obtained by training and generating a head confidence distribution map of each frame of image in the continuous frames of images, a step of determining at least one human head detection target in each frame of image by using a preset target determination method for the head confidence distribution map of each frame of image, a step of obtaining a feature matching result and motion smoothness of any human head detection target in each frame of image, carrying out target association on the current frame and a previous frame of the current frame to obtain tracking targets according to the feature matching result and the motion smoothness of any human head detection target in each frame of image, distributing tracking identifiers to the tracking targets, and a step of counting the number of all tracking identifiers to obtain a result of human flow statistics. Through the method, the device and the system, the accuracy and operational efficiency of the human flow statistics can be improved.

Description

technical field [0001] The invention relates to the technical field of machine vision, in particular to a method, device and system for counting people flow. Background technique [0002] With the continuous progress of society, the application scope of video surveillance system is more and more extensive. The flow of people in and out of supermarkets, shopping malls, gymnasiums, airports, stations and other places is of great significance to the operators or managers of the above places. By counting the flow of people, it is possible to effectively monitor and organize the operation of public activity areas in real time Work. In traditional video surveillance, the counting of people flow is mainly realized through manual counting by monitoring personnel. This method is more reliable when the monitoring time is short and the flow of people is sparse. However, due to the limitation of the biological characteristics of human eyes, when the monitoring time When the time is lo...

AI Technical Summary

Problems solved by technology

[0004] Since the multi-class classifier parallel structure detection process needs to set the detection order of various classifiers, each classifier is used to detect the head of the current image in turn according to the detection order. The selection of classifiers directly affects the accuracy of people flow statistics, and parallel The training samples of the multi-class classifier need to collect and calibrate the positive and negative samples of multiple categories and calibrate the head target frame respectively according to the classifier category and the specific scene, which leads to the complexity of head target recognition is too high, which affects the flow of people statistics. Computing efficiency

Images