A method and system for monitoring the speed of an unmanned aerial vehicle

Abstract

The invention provides a method and system for monitoring the speed of an unmanned plane, and the method comprises the steps: obtaining the current flight altitude and angular velocity and an image; obtaining feature points of the image, and calculating the optical flow of each feature point; carrying out the counting of the optical flows of all feature points, and selecting the optical flow with the maximum optical flow repetitive rate in the same direction as the optical flow of the image; and calculating the current flight velocity according to the current flight altitude and angular velocity and the optical flow of the image. The invention also relates to a system corresponding to the above method. The method obtains the feature points of the current image through calculation, calculates the optical flows of all feature points, and selects the optical flow with the maximum optical flow repetitive rate in the same direction as the optical flow of the image. Afterwards, the method carries out the calculation of the current flight velocity according to the optical flow of the image and the current flight altitude and angular velocity. The method is simple in calculation, is small in calculation burden, gives consideration to the influence of a plurality of factors, and is precise in calculation result.

Description

technical field [0001] The invention relates to the technical field of unmanned aerial vehicles, in particular to a method and system for monitoring the speed of an unmanned aerial vehicle. Background technique [0002] At present, in the UAV industry, the use of computer vision for speed monitoring has received extensive attention, especially in terms of speed monitoring based on image optical flow algorithms. For example, the Chinese invention patent with the publication number CN102298070B discloses a method for estimating the horizontal velocity of a drone, especially a drone capable of performing hovering flight under automatic driving. The method includes: estimating the continuous The movement of the scene between images and applying a scaling factor as a function of the measured height to the estimated movement, the estimation of the movement consists of periodically and continuously updating a multi-resolution representation of the image type pyramid in different G...

AI Technical Summary

Problems solved by technology

Although the above scheme can estimate the horizontal speed of the drone performing hovering flight, the calculation process is relatively complicated and requires high processor chips.

Images