Indoor and independent drone navigation method based on three-dimensional vision SLAM

Abstract

The invention provides an indoor and independent drone navigation method based on three-dimensional vision SLAM. The indoor and independent drone navigation method comprises the steps that an RGB-D camera obtains a colored image and depth data of a drone surrounding environment; a drone operation system extracts characteristic points; the drone operation system judges whether enough characteristicpoints exist or not, if the quantity of the characteristic points is larger than 30, it shows that enough characteristic points exist, the drone attitude calculation process is conducted, or, relocating is conducted; a bundling optimizing method is used for global optimization; an incremental map is built. Drone attitude information is given with only one RGB-D camera, a three-dimensional surrounding environment is rebuilt, the complex process that a monocular camera solves depth information is avoided, and the problems of complexity and robustness of a matching algorithm in a binocular camera are solved; an iterative nearest-point method is combined with a reprojection error algorithm, so that drone attitude estimation is more accurate; a drone is located and navigated and independentlyflies indoors and in other unknown environments, and the problem that locating cannot be conducted when no GPS signal exists is solved.

Description

technical field [0001] The invention belongs to the technical field of indoor positioning and navigation of unmanned aerial vehicles, and in particular relates to an indoor autonomous navigation method for unmanned aerial vehicles based on three-dimensional vision SLAM. Background technique [0002] At present, the mainstream navigation system for UAV positioning is the integrated navigation system of GPS and inertial navigation system, but this method cannot be used indoors or in unknown environments where GPS cannot be used. The problem of SLAM research is that the robot performs its own positioning according to the position estimation and the map while moving in the unknown environment, and at the same time constructs an incremental map on the basis of its own positioning to realize the autonomous positioning and navigation of the robot. [0003] The sensors used to study SLAM are usually lasers and cameras. Laser positioning is more accurate, but the cost is high, and ri...

AI Technical Summary

Problems solved by technology

[0003] The sensors used to study SLAM are usually lasers and cameras. Laser positioning is more accurate, but the cost is high, and rich features cannot be recognized. Ordinary cameras are sensitive to light intensity and cannot be used in weak light

Usually, UAV pose estimation based on image feature points only uses a feature matching method, which is prone to feature loss or inaccurate pose estimation.

Images