Three-dimensional map construction method and device, electronic equipment and storage medium

Abstract

The invention discloses a three-dimensional map construction method and device, electronic equipment and a storage medium. The three-dimensional map construction method comprises the following steps: acquiring at least one frame of image shot by a mobile camera device in a target area; performing semantic segmentation on each frame of image to obtain corresponding semantic segmentation information; performing pose estimation on each image according to the corresponding semantic segmentation information to obtain a pose estimation result; and constructing a three-dimensional map in combination with the semantic segmentation information and the pose estimation result corresponding to each frame of the image. According to the three-dimensional map construction method provided by the embodiment of the invention, a long-term vision SLAM method capable of effectively coping with the extreme appearance change of a scene is provided on the basis of the high-level cognitive information obtained by scene semantic segmentation; self-adaptive high-level cognition for a dynamic environment is formed through map representation fused with semantic information and updating and association of the map representation, and the active cognition ability of a robot system is improved.

Description

technical field [0001] The present application relates to the technical field of computer vision, and in particular to a method, device, electronic equipment and storage medium for constructing a three-dimensional map. Background technique [0002] Existing perception methods face the challenges of real dynamic scene applications with large time spans and large appearance changes, and there are limitations in robustness and long-term performance, making it difficult to detect dynamic objects under conditions such as dynamic objects, illumination changes, seasonal changes, and large viewing angle changes. Perceptual failure is easy to occur; semantic SLAM often only introduces semantic information into a certain link of SLAM, which can improve algorithm performance to a certain extent, but it is still not clear what role semantic information plays in SLAM, and how to make full use of it in each link of visual SLAM. , Reasonable and efficient use of semantic information; the r...

AI Technical Summary

Problems solved by technology

[0002] Existing perception methods face the challenges of real dynamic scene applications with large time spans and large appearance changes, and there are limitations in robustness and long-term performance, making it difficult to detect dynamic objects under conditions such as dynamic objects, illumination changes, seasonal changes, and large viewing angle changes. Perceptual failure is prone to occur; semantic SLAM often only introduces semantic information into a certain link of SLAM, which improves algorithm performance to a certain extent, but it is still unclear what role semantic information plays in SLAM, and how to make full use of it in each link of visual SLAM. , reasonable and efficient use of semantic information; the role of semantic maps for subsequent tasks is not clear, and the current research on semantic SLAM is completely out of the robot cognitive system, making it difficult for the developed system to face the challenges of real scenarios

Images