Pose prediction method, map construction method, mobile platform and storage medium

Abstract

The invention provides a pose prediction method, a map construction method, a mobile platform and a storage medium. The pose prediction method comprises the steps of obtaining a first time period according to a timestamp of a current image frame and a timestamp of a previous image frame (S101); acquiring measurement data of a first encoder and measurement data measured by a second encoder within the first time period (S102); obtaining a prediction transformation matrix of the current image frame relative to a previous image frame according to the measurement data of the first encoder and the measurement data of the second encoder in the first time period (S103); and obtaining a predicted pose of the current image frame according to the prediction change matrix and pose information of a previous image frame (S104). The encoder is applied to the visual SLAM, and the pose of the current image frame is predicted through the encoder measurement data, so that the accuracy of pose acquisitioncan be improved, the stability and robustness of the visual SLAM are improved, and the visual SLAM can still operate stably when vision fails.

Description

technical field [0001] Embodiments of the present invention relate to the field of machine vision, and in particular, relate to a pose prediction method, a map construction method, a movable platform, and a storage medium. Background technique [0002] Visual SLAM (Simultaneous Localization and Mapping, real-time positioning and map construction) refers to the fact that the robot creates a map based on the image collected by the camera in a completely unknown environment under the condition of its own uncertain position, and uses the map for autonomous positioning and navigation. [0003] In the existing visual SLAM method, when there are special problems such as few feature points (no texture) in the image or too many repetitions with the previous image frame, blurred or non-overlapping areas caused by high-speed motion, and occasional reduction of the camera frame rate, it will lead to The tracking function of visual SLAM fails, that is, the relative pose of the current im...

AI Technical Summary

Problems solved by technology

[0003] In the existing visual SLAM method, when there are special problems such as few feature points (no texture) in the image or too many repetitions with the previous image frame, blurred or non-overlapping areas caused by high-speed motion, and occasional reduction of the camera frame rate, it will lead to The tracking function of visual SLAM fails, that is, the relative pose of the current image frame relative to the previous image frame cannot be obtained, which makes visual SLAM unable to continue to work. It is necessary to restore the vision by repositioning when the closed loop is triggered.

[0004] The existing visual SLAM method has poor stability and robustness. When a visual failure occurs, the vision cannot be restored until a closed loop occurs. Therefore, visual SLAM will be interrupted when the visual failure occurs, and the map points and tracks during the visual failure process will be missing. , causing the map points and trajectories before and after the visual failure to fail to connect, resulting in the inability of the visual SLAM to run stably

Images