Semantic Flow-guided Motion Removal Method for Robust Mapping

TL;DR

This paper introduces a novel semantic flow-guided motion removal method for SLAM that leverages optical flow and semantic segmentation to improve robustness in dynamic environments, outperforming previous approaches.

Contribution

The proposed method uniquely combines semantic information with optical flow comparison and K-means refinement, avoiding direct moving object prediction from image sequences.

Findings

Enhanced SLAM robustness in dynamic scenes

Improved accuracy of motion region extraction

Superior performance in indoor and outdoor tests

Abstract

Moving objects in scenes are still a severe challenge for the SLAM system. Many efforts have tried to remove the motion regions in the images by detecting moving objects. In this way, the keypoints belonging to motion regions will be ignored in the later calculations. In this paper, we proposed a novel motion removal method, leveraging semantic information and optical flow to extract motion regions. Different from previous works, we don't predict moving objects or motion regions directly from image sequences. We computed rigid optical flow, synthesized by the depth and pose, and compared it against the estimated optical flow to obtain initial motion regions. Then, we utilized K-means to finetune the motion region masks with instance segmentation masks. The ORB-SLAM2 integrated with the proposed motion removal method achieved the best performance in both indoor and outdoor dynamic environments.