Target state estimation method and device and unmanned aerial vehicle

Abstract

The embodiment of the invention relates to a target state estimation method and device and an unmanned aerial vehicle, and the method comprises the steps: obtaining a target image collected by a camera device, and carrying out the image recognition of the target image, so as to obtain a target image region of a target in the target image; obtaining an original point cloud of the surrounding environment of the unmanned aerial vehicle, and obtaining a first target position according to the target image area and the original point cloud; acquiring attitude information of the camera device, acquiring a first image position based on the target image area, and acquiring a second target position according to the first image position and the attitude information; acquiring a second image positionbased on the target image area; initializing a target state according to the first target position or the second target position; and taking the first target position and / or the second target positionand / or the second image position as a measurement value of an extended Kalman filter to obtain a target state. According to the embodiment of the invention, strong hypothesis conditions are not needed, and the state estimation precision is high.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of unmanned aerial vehicles, in particular to a target state estimation method, device and unmanned aerial vehicle. Background technique [0002] The use of unmanned aerial vehicles to track moving targets has been widely used. When using unmanned aerial vehicles to track targets, it is necessary to plan an appropriate path according to the position of the target, and to avoid obstacles while maintaining tracking. Therefore, in the process of UAV tracking the target, it is very important to obtain the precise state of the target. [0003] At present, the commonly used method is to assume that the ground is a plane, and assume that the height of the UAV to the ground is the height of the UAV relative to the target, and then obtain the height to the ground through the flight control or other modules. Under the above assumptions, use Specific geometric relations estimate the target state....

AI Technical Summary

Problems solved by technology

[0004] In the process of realizing the present invention, the inventor found that the above-mentioned method has at least the following problems: in the occasion of non-ground (such as hills, stairs) below the UAV, the assumption condition is not established, and there is an error in the altitude obtained by the UAV, so The accuracy of the target state estimation based on the altitude of the ground is poor

Images