Stereo camera visual SLAM with hierarchical masking and motion-state classification at outdoor construction sites containing large dynamic objects. (16th February 2021)

• Record Type: Journal Article
• Authors: Bao, Runqiu; Komatsu, Ren; Miyagusuku, Renato; Chino, Masaki; Yamashita, Atsushi; Asama, Hajime
• Is Part Of: Advanced robotics. Volume 35:Number 3/4(2021)
• Page Start: 228
• Page End: 241
• Publication Date: 2021-02-16
• Subjects: Dynamic visual SLAM -- motion segmentation -- hierarchical masking -- object motion-state classification -- ego-motion tracking; Robotics -- Periodicals; Robotics -- Japan -- Periodicals; Robotics; Japan; Periodicals; 629.89205
• DOI: 10.1080/01691864.2020.1869586
• Languages: English
• ISSNs: 0169-1864

Abstract

ABSTRACT: At modern construction sites, utilizing GNSS (Global Navigation Satellite System) to measure the real-time location and orientation (i.e. pose) of construction machines and navigate them is very common. However, GNSS is not always available. Replacing GNSS with on-board cameras and visual simultaneous localization and mapping (visual SLAM) to navigate the machines is a cost-effective solution. Nevertheless, at construction sites, multiple construction machines will usually work together and side-by-side, causing large dynamic occlusions in the cameras' view. Standard visual SLAM cannot handle large dynamic occlusions well. In this work, we propose a motion segmentation method to efficiently extract static parts from crowded dynamic scenes to enable robust tracking of camera ego-motion. Our method utilizes semantic information combined with object-level geometric constraints to quickly detect the static parts of the scene. Then, we perform a two-step coarse-to-fine ego-motion tracking with reference to the static parts. This leads to a novel dynamic visual SLAM formation. We test our proposals through a real implementation based on ORB-SLAM2, and datasets we collected from real construction sites. The results show that when standard visual SLAM fails, our method can still retain accurate camera ego-motion tracking in real-time. Comparing to state-of-the-art dynamic visual SLAM methods, ours shows outstanding efficiency and competitive result trajectory accuracy. GRAPHICAL ABSTRACT: UF0001