Multi-target UAV tracking and identification method, device, electronic equipment and storage medium

Abstract

The present invention provides a multi-target unmanned aerial vehicle tracking and identification method, device, electronic equipment and storage medium. By periodically acquiring image information collected by a binocular camera; inputting current image information into a pre-trained deep learning model Obtain the target detection image in Status information and predicted status information, match each tracking target at the current moment with each tracking target at the previous moment to determine the identity information of each tracking target at the current moment; obtain the depth information and position information of the points in the corresponding tracking target frame As the distance information and position information of each tracking target; update the tracking identification information of each tracking target; thus can accurately track and identify multiple UAVs.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a multi-target UAV tracking and identification method, device, electronic equipment and storage medium. Background technique [0002] Due to the continuous improvement and maturity of UAV technology, UAV has gradually become a new type of intelligent equipment. Due to its dexterity, small size, ability to realize trajectory patrol, fixed-point hovering and other characteristics, it is more and more used. In daily life, the phenomenon of unmanned drones flying in black occurs from time to time, which not only easily violates people's privacy, but also adds many risk factors to daily travel. Therefore, how to deal with the abnormal flight of drones has become the top priority of the current society. [0003] In order to take countermeasures against abnormally flying drones, it is first necessary to track and identify the drones. At present, radar perception and vi...

AI Technical Summary

Problems solved by technology

Among them, since the radar cannot distinguish drones, balloons, birds and other targets, and is easily disturbed by the environment, the radar sensing method is likely to bring a large number of false detection results; and the video monitoring method requires the staff to undertake all the work task, this method is both labor-intensive and unstable

[0004] In addition, when there are multiple UAVs flying abnormally, it is more difficult to effectively track and identify multiple UAVs using traditional radar perception and video surveillance methods

Images