Infrared-based automatic classification method and channel device for people and vehicles

Abstract

The invention relates to the technical field of access control management, in particular to an infrared-based automatic classification method for people and vehicles and a channel device, which is characterized in that it is equipped with a host computer, a controller, an infrared detection mechanism, an alarm, and a display screen, wherein the host computer It is connected with the controller through the network communication circuit, the infrared detection mechanism is connected with the data acquisition circuit in the controller, the alarm is connected with the output terminal of the alarm circuit in the controller, and the display screen is connected with the display circuit in the controller , the infrared detection mechanism is provided with three infrared through-beam sensors arranged sequentially along the passing direction of people and vehicles, and the distance between adjacent infrared through-beam sensors is 60cm. Compared with the prior art, the present invention can quickly detect the Classify people / objects entering and leaving, and judge their passing direction at the same time.

Description

technical field [0001] The invention relates to the technical field of access control management, in particular to an infrared-based automatic classification method for people / vehicles and a channel device that can quickly classify people / objects entering and leaving the monitoring field and judge their passing direction. Background technique [0002] In the existing field of human-vehicle classification technology, video technology is mostly used for automatic human-vehicle classification. For example, the complex scene human-vehicle classification method based on multi-granularity perceptual SVM (support vector machine) is adopted. This method first analyzes the motion area of ​​the video scene. , Combined with the corner detection method to extract the visual perception information of the moving area, the Kalman filter is used in the time-space domain to carry out correlation reasoning on the perception information and remove the noise interference. Then, with the centroi...

AI Technical Summary

Problems solved by technology

[0003] This method is mainly analyzed through video, but there are obvious shortcomings such as: it is greatly affected by rain, fog and snow, and rain, fog and snow will also be recorded in the video screen, which will have a certain impact on the accurate judgment of the classification of people and vehicles

It is greatly affected by the speed of people and vehicles, especially when the speed is slow or when it stops and goes, it is difficult to classify people and vehicles through video images

It is greatly affected by the specific use environment. If it is necessary to classify passing people and vehicles at a 50-meter-wide entrance and exit, it is difficult to cover all the videos and accurately classify people and vehicles.

Images