SLAM dynamic point semantic filtering method based on DDMA-SAM

By employing a semantic filtering method based on DDMA-SAM, which combines semantic and geometric constraints, the robustness and efficiency issues of visual SLAM in dynamic environments are addressed. This approach achieves high-precision dynamic point removal and pose estimation, thereby improving the system's positioning accuracy and stability.

CN120931922APending Publication Date: 2025-11-11BEIJING INST OF TECH
0 Cites 2 Cited by

Patent Information

Application Number
CN202511030198.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-07-25
Publication Date
2025-11-11

AI Technical Summary

Technical Problem

Existing visual SLAM algorithms are not robust to fast-moving targets in dynamic environments, and are limited by the huge computational cost of semantic segmentation models, making it difficult to simultaneously achieve system accuracy and operational efficiency.

Method used

A semantic filtering method based on DDMA-SAM is adopted. By combining structural compression and multi-scale feature aggregation with semantic and geometric constraints, a dynamic point removal mechanism is constructed, including a decoupled distillation strategy, a lightweight adaptive extraction module, and a multi-path diversion feature matching module, to achieve efficient dynamic point removal.

Benefits of technology

It significantly improves the localization robustness and practicality of the visual SLAM system in dynamic environments, reduces the number of parameters, improves segmentation accuracy and inference speed, and enhances the system's adaptability and real-time processing capabilities.

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

Abstract

The invention discloses an SLAM dynamic point semantic filtering method based on DDMA-SAM, and belongs to the technical field of synchronous positioning and mapping. A decoupling distillation mechanism is introduced, an image encoder in an original SAM model is subjected to lightweight optimization, a DDMA-SAM semantic network integrating a multi-scale aggregation detection module and an efficient mask decoding module is constructed, and the SLAM dynamic point semantic filtering method based on DDMA-SAM is obtained. And the segmentation performance is improved while the model parameters are greatly compressed. Based on the semantic network, providing a semantic prior and geometric consistency combined-driven double filtering strategy; based on a semantic mask and a confidence threshold, carrying out preliminary dynamic point identification; in combination with the epipolar geometric constraint and the triangulation reprojection error of random sampling consistency estimation, fine elimination of dynamic feature points is realized, and only static points are reserved to participate in camera pose estimation. According to the method, the real-time performance of the system is kept, and meanwhile, the mapping quality and the track stability in a dynamic scene are effectively improved.
Need to check novelty before this filing date? Find Prior Art