
基于视觉图像的无人直升机位姿估计算法实现与验证
ABSTRACT
The classic GPS/INS combined navigation system cannot be able to provide accurate navigation
information for the UAV autonomous flight in all cases, so we attach great importance to computer
vision which has been considered as the secondary navigation technology for unmanned helicopter
autonomous flight control and become the research priority. In this paper, the author regards
unmanned helicopter visual landing as the research object, designs the image processing algorithm
and pose estimation algorithm and completes the estimation of position and attitude of unmanned
helicopter.
Firstly, the thesis introduces the principle of unmanned helicopter visual landing, designs a
landing target, analyzes the intrinsic parameters difference of commonly used camera models and
provides the unmanned helicopter position and attitude representation using camera perspective
projection relationship.
Secondly, for the characteristics of landing target image, the paper gives the image processing
algorithm based on point features. A CCD camera is used to get the video image, then the landing
target and background is separated during image preprocessing step. Four square’s edges of landing
target can be detected with Canny algorithm, after a corner detection algorithm based on global and
local curvature properties, the characterized corners can be marked in counterclockwise order.
In the end, the camera intrinsic parameters are obtained through calibration, the linear position
and attitude estimation algorithm is designed according to camera perspective projection relationship
and dislinearized.Unmanned helicopter landing status monitoring software is designed by Matlab/GUI
development tools which can realize estimation algorithms. In order to visually observe the motion
state of unmanned helicopter, the three-dimensional visualization simulation can be implemented
using FlightGear flight simulators which is regarded as the visual system. The Unmanned helicopter
movement is also simulated using Ground trolley, the simulation result shows that the image
processing algorithm, position and attitude estimation algorithm could be used for vision-based
unmanned helicopter landing.
Key Words: unmanned helicopter,visual landing,image processing,position and attitude estimate
algorithm,GUI