Dynamic scene vision SLAM method and system based on point-line complementation

By introducing a semantic module to detect dynamic feature points and culling them, combining point-line feature fusion and global optimization, the problem of reduced positioning and map building accuracy in dynamic scenarios is solved, and higher robustness and accuracy are achieved.

CN119722799AActive Publication Date: 2025-03-28CHONGQING UNIV OF POSTS & TELECOMM
9 Cites 5 Cited by

Patent Information

Application Number
CN202411877807.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-19
Publication Date
2025-03-28
Estimated Expiration
2044-12-19

AI Technical Summary

Technical Problem

The existing visual SLAM method is difficult to effectively deal with dynamic targets in dynamic scenarios, resulting in the system mistakenly considering static feature points and introducing incorrect constraint relationships, which affects the positioning and map building accuracy.

Method used

The dynamic scene visual SLAM method based on point-line complementation is adopted, dynamic feature points are detected through semantic modules, dynamic feature points are eliminated, static point features and line features are fused, keyframe screening and local map construction are carried out, and loop detection is used with the global BA optimization module.

Benefits of technology

It effectively avoids interference from dynamic feature points on static scene maps, improves the accuracy and robustness of map construction and positioning in dynamic scenes, and enhances the robustness of the system in weak texture situations.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to a dynamic scene vision SLAM method and system based on point-line complementation, and belongs to the field of simultaneous mapping and positioning of mobile robots. According to the method, target prior information monitoring is carried out on an image through a semantic module, and dynamic feature points inconsistent with camera motion are identified; visual feature extraction is carried out on the image through a tracking module, and the visual feature extraction comprises point feature extraction and line feature extraction; removing the point features preliminarily extracted by the tracking module according to the dynamic feature points identified by the semantic module, fusing the obtained static point features and line features, expanding the static point features according to the fused line feature constraints, and screening out key frames according to the point and line features; and finally, completing map construction and optimization updating through a local mapping module and a loopback detection and global BA optimization module. According to the method, mapping limitation and deviation possibly caused by single scene texture information can be overcome, and the real-time performance, the mapping precision and the robustness of mapping can be improved.
Need to check novelty before this filing date? Find Prior Art