A Robust Deep Learning Enhanced Monocular SLAM System for Dynamic Environments

Yaoqing Li, Sheng Hua Zhong, Shuai Li, Yan Liu

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

Abstract

Simultaneous Localization and Mapping (SLAM) has developed as a fundamental method for intelligent robot perception over the past decades. Most of the existing feature-based SLAM systems relied on traditional hand-crafted visual features and a strong static world assumption, which makes these systems vulnerable in complex dynamic environments. In this paper, we propose a robust monocular SLAM system by combining geometry-based methods with two convolutional neural networks. Specifically, a lightweight deep local feature detection network is proposed as the system front-end, which can efficiently generate keypoints and binary descriptors robust against variations in illumination and viewpoint. Besides, we propose a motion segmentation and depth estimation network for simultaneously predicting pixel-wise motion object segmentation and depth map, so that our system can easily discard dynamic features and reconstruct 3D maps without dynamic objects. The comparison against state-of-the-art methods on publicly available datasets shows the effectiveness of our system in highly dynamic environments.

Original languageEnglish
Title of host publicationICMR 2023 - Proceedings of the 2023 ACM International Conference on Multimedia Retrieval
EditorsIoannis Kompatsiaris, Jiebo Luo, Nicu Sebe, Angela Yao, Vasileios Mezaris, Symeon Papadopoulos, Adrian Popescu, Zi Huang
PublisherAssociation for Computing Machinery ACM
Pages508-515
ISBN (Electronic)979-8-4007-0178-8
DOIs
Publication statusPublished - 12 Jun 2023
MoE publication typeA4 Article in a conference publication
Event2023 ACM International Conference on Multimedia Retrieval, ICMR 2023 - Thessaloniki, Greece
Duration: 12 Jun 202315 Jun 2023

Conference

Conference2023 ACM International Conference on Multimedia Retrieval, ICMR 2023
Country/TerritoryGreece
CityThessaloniki
Period12/06/2315/06/23

Keywords

  • deep local feature
  • monocular SLAM
  • motion segmentation

Fingerprint

Dive into the research topics of 'A Robust Deep Learning Enhanced Monocular SLAM System for Dynamic Environments'. Together they form a unique fingerprint.

Cite this