A method for positioning and navigation of UAV based on binocular vision

Abstract

The invention discloses a binocular vision-based positioning and navigation method for UAVs. According to the binocular camera of the UAV-borne control system, the left and right views of the image are obtained and the left and right views after the camera parameters have been corrected to obtain the depth information of the corresponding pixels. ; Extract the key points of the left view for filtering and screening; then find the matching key point set through optical flow tracking in the current frame, and obtain the matching key point pair; calculate the cost function according to the matching key point pair, and obtain the final pose result; The input continuous image frames are screened to obtain the key image frames, the joint cost function is calculated for the key point set and the pose of the key image frames, and the cost function is optimized to obtain the updated pose. The invention can quickly obtain reliable depth data through the binocular camera, and at the same time use the optical flow method to quickly calculate the matching relationship, with strong real-time performance and high algorithm robustness, and can complete UAV positioning and navigation work in indoor and outdoor large and medium-sized scenes .

Description

technical field [0001] The invention belongs to the technical field of unmanned aerial vehicles, and in particular relates to a method for positioning and navigating an unmanned aerial vehicle based on binocular vision. Background technique [0002] Visual positioning and navigation technology is a key technology in the field of computer vision, and has important applications in surveying and mapping, control, military and other fields. At the same time, it involves a number of core technologies in the field of computer vision, such as image processing, pattern recognition, automatic control, feature engineering, etc. It is a comprehensive technology. [0003] When UAVs are used to observe the ground in the air, it is often necessary to solve the problem of positioning and navigation when the UAV moves in an unknown environment, that is, how to determine its own movement through the observation of the environment when a UAV moves in an unknown environment trajectories while...

AI Technical Summary

Problems solved by technology

In the process of positioning and navigation based on vision, since the scene observed by the camera is a two-dimensional scene and lacks height information, there is great uncertainty in building and navigating a three-dimensional map through a two-dimensional scene alone.

Images