Method for detecting vehicle motion information based on integration of binocular stereoscopic vision and optical flow

Abstract

The invention relates to a method for detecting vehicle motion information based on integration of binocular stereoscopic vision and optical flow, and the method comprises the following steps of: analyzing and processing left and right image sequences taken by a binocular stereoscopic camera, and acquiring motion information of the three-dimensional space velocity and angle velocity of the car body through feature matching, three-dimensional reconstruction, feature extraction and optical flow estimation, in order to estimate motion information of the car body. As a new method for detecting car motion parameters, it is simply installed, applied to the actual operating environment of the car, high in precision and strong in real time. By the method, inaccurate reading numbers and measuring errors occurred by environmental factors can be effectively reduced, and the visual sensor has the advantages of simple structure and much information and can provide a mass of other information. The system selects ground points as interested feature points to effectively reduce interference of the motion object and improve estimation precision. At the same time, by the method, steadiness and robustness of the algorithm can be enhanced by fully utilizing depth information.

Description

technical field [0001] The invention relates to a motion vision processing technology, in particular to a vehicle motion information detection method based on binocular stereo vision and optical flow fusion. Background technique [0002] In the field of smart cars, in order to realize the perception of the surrounding environment of the vehicle, it is necessary to know the motion information of the vehicle itself, including the three-dimensional translational movement velocity and the three-dimensional rotational angular velocity. [0003] A common method is to use a special gyro inertial navigation device to obtain this information. This method adds an additional device to the vehicle, and the data it provides also has problems of low accuracy and stability. Another method is the visual odometry method using monocular vision images, which obtains the vehicle's own motion information by calculating the optical flow of the feature points of a specific moving object. This met...

AI Technical Summary

Problems solved by technology

[0004] The present invention aims at the problem of low accuracy of traditional visual odometer positioning due to changing complex backgrounds, and proposes a vehicle motion information detection method based on binocular stereo vision and optical flow fusion, which analyzes and processes binocular stereo cameras The left and right image sequences, through the steps of feature matching, 3D reconstruction, feature extraction, and optical flow calculation, etc., obtain the motion information of the three-dimensional space velocity and three-dimensional angular velocity of the car body, and realize the motion information estimation of the car body

Images