A method of short-distance aircraft pose measurement based on parallax method

Abstract

The invention relates to a short-distance aircraft position and attitude measurement method based on the parallax method, which is used for aircraft position positioning and attitude calculation under high-altitude and short-distance conditions, and can be used for the position and attitude calculation of a refueling aircraft in the process of aerial refueling, including: parallel two Calibration of the internal and external parameters of each camera and image correction; After obtaining the initial positioning area of ​​the aircraft through the detection and tracking algorithm, perform stereo matching to solve the 3D point cloud; classify and mark the 2D feature points by edge features and other methods, and combine with the 3D point cloud to form several 3D points Feature point set, solve the plane equation of the 3D point set. After filtering out background points and noise points, the plane equation combines the shape characteristics of the aircraft to solve the spatial attitude of the aircraft; this method uses the combination of image features and shape features, which can effectively realize the close-range aircraft pose measurement, reducing the three-dimensional The time-consuming visual matching algorithm does not need to add cooperation signs on the aircraft. It has the characteristics of fast and effective, convenient implementation, strong practicability, and easy transplantation of the algorithm, and is easy to use in actual projects.

Description

technical field [0001] The method relates to an aircraft pose measurement method, in particular to an aircraft pose measurement method based on a parallax method and combining two-dimensional images and three-dimensional point clouds. Background technique [0002] The parallax method is one of the commonly used algorithms for stereo vision. The parallax method is actually a method of simulating the principle of human vision and using a computer to passively perceive distance. Observe an object from two or more points, obtain images under different viewing angles, and calculate the offset between pixels according to the matching relationship between the pixels in the images to obtain the three-dimensional information of the object. [0003] In the process of matching the corresponding pixels of the parallax method, since the parallax search range is not easy to determine, the matching is prone to errors. An inappropriate disparity search range can easily make the stereo mat...

AI Technical Summary

Problems solved by technology

Although the ICP (Iterative Closest Point Method) proposed by Besl and Mckay has been continuously improved and supplemented after years of development, it is also one of the main means to solve registration problems based on free-form surfaces. It requires a large amount of calculation and multiple iterations, and does not have an advantage in calculation time

Images