Monocular camera-based planar moving target visual navigation method and system

Abstract

The invention relates to a monocular camera-based planar moving target visual navigation method and system. The method comprises the following steps of establishing a world coordinate system, a cameracoordinate system, a moving target coordinate system and a picture plane coordinate system, enabling the monocular camera to form a 2D-3D point pair by acquiring a control point and an image point pair of the control point falling on an image plane physical coordinate system in real time in the advancing process of the moving target, conducting coordinate transformation on the 2D-3D point pairs according to a coordinate system, and solving the pose of a moving target, and assisting the moving target to move forward according to the moving target pose. According to the method, an idea method of space geometry modeling and an RANSAC algorithm are adopted, a set of all possible positions of a camera optical center is modeled into a space circle with a control point as the circle center and the distance from the control point to the optical center as the radius, unknown position parameters and attitude parameters in a collinear equation are decoupled and then solved respectively, and meanwhile, the RANSAC algorithm is used for eliminating outliers; and the method is a high-speed, high-robustness and high-precision real-time visual navigation method.

Description

technical field [0001] The invention belongs to the field of visual navigation, in particular to a method and system for visual navigation of a plane moving target based on a monocular camera. Background technique [0002] The visual navigation method has attracted more and more attention due to its characteristics of non-contact, high precision, and low cost. Compared with laser and radar navigation methods, the visual navigation information acquisition stage only uses optical cameras to obtain images without actively firing lasers to the target. Electromagnetic waves and receive the returned information; compared with global satellite navigation system navigation, visual navigation is not limited by the coverage of satellite signals and has very strong anti-interference performance, while radio and GPS signals are susceptible to interference and blocking, visual navigation It can be carried out indoors or even underground, and there is no need to establish a satellite navi...

AI Technical Summary

Problems solved by technology

[0004] The current absolute pose estimation method based on two pairs of 2D-3D point pairs is difficult to meet the real-time requirements due to its complicated calculation and long pose estimation time; there are also methods that do not consider the distance between the camera optical center and the moving target. In an ideal situation, the center of the moving target is equal to the optical center and the optical axis of the camera is parallel to the plane where the movement is located. Therefore, in practical applications, the error is large and the positioning is inaccurate.

Images