Unmanned aerial vehicle ground target tracking method

Abstract

The invention discloses an unmanned aerial vehicle ground target tracking method, which comprises the following steps: high-altitude locking: an unmanned aerial vehicle shoots an image and identifies object characteristics in the image; image annotation: annotating above the object, and regenerating the annotated image; tracking: generating object coordinates according to the object features, and sending the object coordinates to the unmanned aerial vehicle; and low-point monitoring: sending own coordinates outwards by taking the unmanned aerial vehicle as a center, and rotating a low-point camera towards the unmanned aerial vehicle. According to the method for tracking the target to the ground by the unmanned aerial vehicle, firstly, the position of an object can be tracked and images around the object can be shot by performing high-altitude locking and then calling low-point monitoring equipment, so that various data of the object can be acquired more comprehensively, and the comprehensiveness of data acquisition is improved; secondly, the information of the object is marked in the image, so that the information of the object can be conveniently confirmed in real time; and thirdly, laser indication is adopted, so that object tracking loss is prevented.

Description

technical field [0001] The invention relates to the technical field of tracking, in particular to a method for tracking a ground target by an unmanned aerial vehicle. Background technique [0002] Unmanned aircraft is referred to as "unmanned aerial vehicle" or "UAV" in English. It is an unmanned aircraft operated by radio remote control equipment and self-contained program control device, or completely or intermittently operated autonomously by an on-board computer; [0003] Target tracking is a method for locating objects and recording the corresponding parameters of objects. Target tracking refers to detecting targets in a single frame. The purpose of target tracking is to connect multiple frames of detected targets in series; [0004] At present, when the existing UAV ground target tracking method is in use, it is difficult to distinguish objects with similar shapes and postures through image recognition, resulting in deviation or loss of object tracking, which seriously...

AI Technical Summary

Problems solved by technology

[0004] At present, when the existing UAV ground target tracking method is in use, it is difficult to distinguish objects with similar shapes and postures through image recognition, resulting in deviation or loss of object tracking, which seriously affects the quality of objects. Secondly, during object tracking, only the external image of the object can be taken at close range, but the environment around the object cannot be monitored, which makes the target tracking vulnerable to environmental factors (such as billboards, etc., low-altitude objects) , In addition, the trajectory of the object cannot be detected, resulting in the inability of personnel to assist in tracking. Therefore, we propose a UAV tracking method for ground targets

Images