High-altitude parabolic detection method and system based on computer vision

Abstract

The invention discloses a high-altitude parabolic detection method and system based on computer vision. a ViBe algorithm is used as a detection means of a moving object; in the process of detecting the moving object by using the ViBe; A mechanism for detecting whether the camera shakes or not is added, the situation that the image position shifts due to shaking or moving of the camera is fully considered, a background model is updated by adopting a current frame of high-altitude parabolic monitoring image when the camera shakes, the accuracy of detecting a moving object through ViBe is improved, and therefore the false detection rate of high-altitude parabolic is reduced. The moving object is tracked by combining the Hungarian algorithm and the Kalman filtering algorithm, the running speedof the system is greatly increased through Hungarian algorithm tracking, the loss rate of parabolic tracking is greatly reduced through Kalman filtering algorithm tracking, and the parabolic trackingeffect is guaranteed. The method has a good detection effect on a moving object of a small target, and can adapt to the situations that the target is temporarily shielded or missed, the background environment slowly changes and the like.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, and more specifically relates to a computer vision-based high-altitude parabolic detection method and system. Background technique [0002] High-altitude parabolic is called "the pain hanging over the city". It is not only an uncivilized behavior, but also a great hidden danger to social security. Due to the fact that most of the incidents occurred on high-altitude floors, there were few witnesses, and the throwing time was short, it was difficult for law enforcement agencies to pursue the legal responsibility of the throwers. Therefore, it is very important to realize intelligent detection of high-altitude parabolic objects. [0003] The background difference method is the most common moving object detection method. The overall idea is: subtract the background image from the current frame to obtain the background difference image, and then use the threshold judgment method to bi...

AI Technical Summary

Problems solved by technology

[0004] However, the existing high-altitude parabolic detection has the defects of high false detection rate, difficulty in detecting small moving objects, and slow detection speed

Images