High-altitude parabolic object detection method and device based on mixed vision

Abstract

The invention discloses a high-altitude throwing detection method and device based on mixed vision, an event camera and a conventional camera are carried and registered at the same time to monitor a monitored building in real time, the event camera detects a moving target based on a generated event sequence, the position of the moving target is obtained, and the position of the moving target is detected; performing tracking correction on the position of the moving target by adopting a Kalman filtering algorithm, associating the detected moving target with a known moving target, establishing a tracking list of the moving target, judging whether the moving target is a high-altitude parabolic object, if so, reporting the position and time of the moving target, and according to the reported time of the moving target, determining whether the moving target is a high-altitude parabolic object. And intercepting and storing video images shot by the conventional camera. According to the invention, mixed vision of the event camera and the conventional camera is combined, the influence of illumination is small, and the false alarm rate is low and the positioning performance is high when a parabolic object is similar to a background in color, small in size, too fast in movement or at night.

Description

technical field [0001] The present application belongs to the technical field of target detection, and in particular relates to a hybrid vision-based high-altitude parabolic detection method and device. Background technique [0002] Along with more and more high-rise residences, the phenomenon of high-altitude parabolic and falling objects seriously threatens the life and property safety of the people. Timely detection of high-altitude parabolic objects and accountability are the prerequisites for preventing and controlling such uncivilized behavior. However, high-altitude parabolic objects are still one of the most difficult points in community management due to the difficulty of finding, obtaining evidence, and chasing blame. [0003] The existing method is to look up and install a camera for video image acquisition under the building, and conduct 24-hour real-time video monitoring of the real-time conditions of each monitoring site within the monitoring range. When an ab...

AI Technical Summary

Problems solved by technology

[0004] It is difficult to detect and is greatly affected by light. When the parabola is similar to the background color, small in size, moving too fast or in dark conditions, the positioning performance is poor and the false alarm rate is high;

[0005] High cost, high resolution and high frame rate guns are very expensive. If artificial intelligence methods are used, sufficient GPUs must be purchased on demand. Although autonomous monitoring can be achieved, the cost is mentioned

Images