High-altitude parabolic detection method and device based on trajectory analysis

Abstract

The invention discloses a high-altitude parabolic detection method and device based on trajectory analysis, wherein the method comprises the following steps: acquiring multiple frames of images of a current monitoring video, moving object detection is carried out on the multiple frames of images; determining a moving object on each frame of image; and processing each frame of image of the determined moving object, determining a central coordinate of the moving object on each frame of image, performing linear fitting according to the central coordinate of the moving object on each frame of image to obtain a motion trail equation of the moving object, and verifying the motion trail equation of the moving object to determine the object of the high-altitude parabolic object. Motion detection is carried out on each frame of image. According to the method, the moving object on each frame of image is obtained, then the motion trail equation is verified according to the motion trail equation of the coordinates of the moving object on each frame of image, so that the object of high-altitude parabolic motion is determined; the high-altitude parabola can be actively detected; the problem thatdeep learning is difficult to identify is solved; and the detection accuracy is improved.

Description

technical field [0001] The embodiment of the present invention relates to the field of smart home technology, in particular to a method and device for detecting high-altitude parabolic objects based on trajectory analysis. Background technique [0002] High-altitude parabolic objects are called "urban cancer". In recent years, incidents of high-altitude parabolic objects hurting people have occurred frequently, which not only harm the physical and mental health of others, but also affect the public's sense of security and happiness. Smart communities have higher and higher requirements for high-altitude parabolic objects. . The current high-altitude parabolic detection method mainly uses high-frequency cameras and infrared cameras for video recording, and then manually traces it afterwards. The way to actively detect high-altitude parabolic objects is to conduct training and learning through deep learning, and then use the trained model to identify high-altitude parabolic o...

AI Technical Summary

Problems solved by technology

The way to actively detect high-altitude parabolic objects is to conduct training and learning through deep learning, and then use the trained model to identify high-altitude parabolic objects. However, the reason why this active detection method of high-altitude parabolic objects limits its detection success rate is that the interference is too strong, such as flying birds, Or if a person appears on the window, it may be recognized

Therefore, there is still a lack of an effective active detection scheme for high-altitude parabolic objects.

Images