DIG-SLAM: an accurate RGB-D SLAM based on instance segmentation and geometric clustering for dynamic indoor scenes
- 27 September 2023
- journal article
- research article
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 35 (1) , 015401
Abstract
Simultaneous localization and mapping (SLAM) has emerged as a critical technology enabling robots to navigate in unknown environments, drawing extensive attention within the robotics research community. However, traditional visual SLAM ignores the presence of dynamic objects in indoor scenes, and dynamic point features of dynamic objects can lead to incorrect data correlation, making the traditional visual SLAM is difficult to accurately estimate the camera’s pose when the objects in the scenes are moving. Using only point features cannot fully extract geometric information in dynamic indoor scenes, reducing the system’s robustness. To solve this problem, we develop a RGB-D SLAM system called DIG-SLAM. Firstly, the objects’ contour regions are extracted using the YOLOv7 instance segmentation method, serving as a prerequisite for determining dynamic objects and constructing a semantic information map. Meanwhile, the line features are extracted using the line segment detector algorithm, and the redundant line features are optimized via K-means clustering. Secondly, moving consistency checks combined with instance partitioning determine dynamic regions, and the point and line features of the dynamic regions are removed. Finally, the combination of static line features and point features optimizes the camera pose. Meanwhile, a static semantic octree map is created to provide richer and higher-level scene understanding and perception capabilities for robots or autonomous systems. The experimental results on the Technische Universität München dataset show that the average absolute trajectory error of the developed DIG-SLAM is reduced by 28.68% compared with the dynamic semantic SLAM. Compared with other dynamic SLAM methods, the proposed system shows better camera pose estimation accuracy and system’s robustness in dynamic indoor environments and better map building in real indoor scenes.Keywords
Funding Information
- Natural Science Foundation of Xinjiang Uygur Autonomous Region (2022D01C53)
- Xiangyang Key R&D Project (2020ABH001799)
- National Natural Science Foundation of China (62263031)
This publication has 33 references indexed in Scilit:
- ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D CamerasIEEE Transactions on Robotics, 2017
- Fast odometry and scene flow from RGB-D cameras based on geometric clustering2017
- Improving RGB-D SLAM in dynamic environments: A motion removal approachRobotics and Autonomous Systems, 2017
- Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception AgeIEEE Transactions on Robotics, 2016
- Moving Object Detection in Real-Time Using Stereo from a Mobile PlatformUnmanned Systems, 2015
- LSD-SLAM: Large-Scale Direct Monocular SLAM2014
- An efficient and robust line segment matching approach based on LBD descriptor and pairwise geometric consistencyJournal of Visual Communication and Image Representation, 2013
- A benchmark for the evaluation of RGB-D SLAM systems2012
- LSD: a Line Segment DetectorImage Processing On Line, 2012
- Random sample consensusCommunications of the ACM, 1981