Method and system for passenger flow statistics based on cameras with intelligent analysis function

Abstract

The invention discloses a method for passenger flow statistics based on cameras with the intelligent analysis function. The method comprises the following steps that video series images are obtained, graying is conduced, and then images with a corresponding gray scale are obtained; an image detecting area is set, and a marking line for counting triggering is set in the image detection area in the statistics direction; a moving target position area in the video series images is determined; target detection is conducted on the moving target area, and the position information of targets obtained through identification is stored; movement predication and tracking are conducted on the detected targets, and passenger flow statistics is triggered according to the movement trails of the targets and the marking line. The invention further discloses a system for passenger flow statistics based on the cameras with the intelligent analysis function. By the adoption of the method and system for passenger flow statistics based on the cameras with the intelligent analysis function, a classifier is obtained through training and learning of machines and used for detecting the targets, the problems that the recognition rate is low, and missing detection and false detection are caused are effectively solved, operation cost is small, and the demand for real-time performance can be met; the method and system for passenger flow statistics based on the cameras with the intelligent analysis function are suitable for passenger flow statistics in various scenes.

Description

technical field [0001] The invention relates to the technical field of image processing and video intelligent analysis, in particular to a method and system for passenger flow statistics based on intelligent analysis cameras in multiple scenarios. Background technique [0002] With the continuous maturity and progress of modern technology, the concept of "safe city" and "smart city" has been put forward. direction development. Passenger flow detection and statistics belong to the category of video intelligent analysis. Passenger flow statistical analysis based on surveillance video has important practical significance in many different occasions. In commercial applications, for large shopping malls, supermarkets, gymnasiums, tourist attractions and other places, different time periods And passenger flow statistics in different regions can be used as an important basis for operators and managers to conduct market research and analysis. For public transportation places such ...

AI Technical Summary

Problems solved by technology

[0004] Video-based passenger flow statistics is mainly to analyze the pedestrian movement trajectory in the video, and accumulate the number of passengers entering and leaving in two directions. At present, there are still some problems and deficiencies in the technology of passenger flow statistics based on video analysis, mainly due to insufficient robustness. Well, affected by the environment and light conditions, it may have better results in some occasions, but the statistical accuracy in some occasions cannot meet the requirements

For special situations such as pedestrians wearing hats, white hair, backpacks, and dark floor backgrounds, they do not have a good ability to distinguish, resulting in statistical errors

In addition, video-based passenger flow statistics mainly rely on the back-end video analysis server to process and analyze video images. The more video monitoring points, the greater the computing pressure on the background server when analyzing multiple videos at the same time, and even more server equipment is required. Increased cost input, and not easy to expand

Images