LSD-SLAM: Large-Scale Direct Monocular SLAM. We propose a direct (feature-less) monocular SLAM algorithm which, in contrast to current state-of-the-art regarding direct methods, allows to build large-scale, consistent maps of the environment. Along with highly accurate pose estimation based on direct image alignment, the 3D environment is reconstructed in real-time as pose-graph of keyframes with associated semi-dense depth maps. These are obtained by filtering over a large number of pixelwise small-baseline stereo comparisons. The explicitly scale-drift aware formulation allows the approach to operate on challenging sequences including large variations in scene scale. Major enablers are two key novelties: (1) a novel direct tracking method which operates on 𝔰𝔦𝔪(3), thereby explicitly detecting scale-drift, and (2) an elegant probabilistic solution to include the effect of noisy depth values into tracking. The resulting direct monocular SLAM system runs in real-time on a CPU.
Keywords for this software
References in zbMATH (referenced in 5 articles )
Showing results 1 to 5 of 5.
- Ardentov, Andrey A.; Karavaev, Yury L.; Yefremov, Kirill S.: Euler elasticas for optimal control of the motion of mobile wheeled robots: the problem of experimental realization (2019)
- Yu, Fangwen; Shang, Jianga; Hu, Youjian; Milford, Michael: NeuroSLAM: a brain-inspired SLAM system for 3D environments (2019)
- Özyeşil, Onur; Voroninski, Vladislav; Basri, Ronen; Singer, Amit: A survey of structure from motion (2017)
- Hollósi, Gergely; Lukovszki, Csaba; Moldován, István; Plósz, Sándor; Harasztos, Frigyes: Monocular indoor localization techniques for smartphones (2016)
- Engel, Jakob; Schöps, Thomas; Cremers, Daniel: LSD-SLAM: Large-scale direct monocular SLAM (2014) ioport