GMC: Grid Based Motion Clustering in Dynamic Environment

Abstract

Conventional SLAM algorithms takes a strong assumption of scene motionlessness, which limits the application in real environments. This paper tries to tackle the challenging visual SLAM issue of complicated environments. We present GMC, grid-based motion clustering approach, a lightweight dynamic object filtering method that is free from high-power and expensive processors and is able to differentiate moving objects out of the surroundings. GMC encapsulates motion consistency as the statistical likelihood of detected key points within a certain region. Using this method can we provide real-time and robust correspondence algorithm that can differentiate dynamic objects with static backgrounds. Furthermore, we evaluate our system in the public TUM dataset. To compare with the state-of-the-art methods, our system can provide more accurate results by detecting dynamic objects.

@inproceedings{zhang2020gmc,
  title={GMC: Grid based motion clustering in dynamic environment},
  author={Zhang, Handuo and Hasith, Karunasekera and Zhou, Hui and Wang, Han},
  booktitle={Intelligent Systems and Applications: Proceedings of the 2019 Intelligent Systems Conference (IntelliSys) Volume 2},
  pages={1267--1280},
  year={2020},
  organization={Springer}
}