Method and system for tracking ground vehicle by unmanned aerial vehicle based on image

Abstract

The invention discloses an image-based method and system for tracking a ground vehicle by an unmanned aerial vehicle, relates to the technical field of unmanned aerial vehicle tracking, and aims to solve the problem that the ground vehicle cannot be effectively tracked in real time in the prior art. The method is characterized by comprising the following steps: acquiring an image containing a ground vehicle by using an airborne camera of an unmanned aerial vehicle, and obtaining position information of the ground vehicle in the image through image processing, so as to calculate and obtain a sight angle of the ground vehicle relative to the unmanned aerial vehicle; controlling a holder to rotate according to the sight angle so as to enable the ground vehicle to be always in the view field of the camera, and achieving the tracking of the ground vehicle; and further, according to the sight angle and the attitude information of the holder, the position of the ground vehicle under the NED coordinate system is calculated, so that the relative distance between the unmanned aerial vehicle and the ground vehicle is obtained, and the flight speed of the unmanned aerial vehicle is adjusted according to the relative distance. According to the invention, a ground target vehicle can be well locked, an accurate target positioning result is given, and a vehicle target which moves rapidly can be tracked.

Description

technical field [0001] The invention relates to the technical field of UAV tracking, in particular to an image-based UAV tracking method and system for ground vehicles. Background technique [0002] With the rapid development of rotor UAV technology, its advantages of easy control, good stability, and flexible maneuvering have prompted rotor UAVs to play an increasingly important role in performing diverse tasks. A very important task of the rotor UAV is to detect and track suspicious ground vehicle targets. The quadrotor UAV has low-altitude hovering and omnidirectional maneuverability, and is suitable for tracking and monitoring specific ground targets and approaching confirmation tasks. [0003] In terms of sensing ground vehicle targets, commonly used sensors include monocular cameras, binocular cameras, lidar, etc. Among them, monocular cameras are the most suitable sensors for this mission scenario because of their low price, rich information, and easy-to-use advantage...

AI Technical Summary

Problems solved by technology

[0004] In view of the above problems, the present invention proposes an image-based UAV tracking method and system for ground vehicles to solve the problem that the prior art cannot effectively track ground vehicles in real time

Images