Visual odometer rotational motion processing method based on pause information supplement mechanism

Abstract

The invention discloses a visual odometer rotational motion processing method based on a pause information supplement mechanism. The method comprises the following steps: step 1, monitoring an image frame and judging the motion category of the image frame; step 2, switching the flow direction of the data flow according to the judgment result in the step 1; dividing the image frames into three types: a rotation initial frame RB, rotation process frames R1, R2,..., Rn and a rotation end frame RE, wherein the rotating initial frame RB is used for inheriting current camera pose information and providing initialization for subsequent frames, the rotation process frames R1, R2,..., Rn are used for integrating the rotation images for calculation, the rotation ending frame RE is used for processing accumulated errors of each rotation and is connected to a common calculation process; step 3, carrying out image frame matching and pose calculation, and completing image processing of camera rotation; performing error optimization processing on the pose calculation result according to the number of the image frames; and step 4, optimizing back-end data.

Description

technical field [0001] The invention belongs to the field of image / graphic processing, relates to target positioning, camera pose calculation and environment map representation, and can maintain the robustness of the visual mileage calculation method in the case of rotational motion. Background technique [0002] Simultaneous Localization and Mapping (SLAM) means that under the condition that there is no prior information of the environment and its own pose information is uncertain, the unmanned platform performs pose estimation based on the sensors carried during the movement process, and at the same time The process of incrementally perceiving the surrounding environment and constructing a specific form of map. With the advancement of computer vision technology and the rapid improvement of computing power, the research on SLAM technology based on visual sensors has developed rapidly. Researchers have proposed a series of representative methods including feature point metho...

AI Technical Summary

Problems solved by technology

Visual odometry cannot directly solve the problem of DOF changes, which is a situation that most algorithms have not considered

Images