Journal
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
Volume 44, Issue 11, Pages 8403-8419Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2021.3106820
Keywords
Linear SLAM; manhattan world; atlanta world; RGB-D image; Bayesian filtering; scene understanding
Funding
- Institute of Information & communications Technology Planning & Evaluation (IITP) - Korea government (MSIT) [2020-0-01336]
- National Research Foundation of Korea (NRF) - Korea government (MSIT) [NRF-2021R1F1A1061397, NRF-2021R1C1C1005723]
- Sookmyung Women's University Research Grants [1-2003-2015]
Ask authors/readers for more resources
This paper proposes a linear RGB-D simultaneous localization and mapping (SLAM) formulation that utilizes planar features of structured environments. By understanding and exploiting structural regularities, the camera rotation can be decoupled, making SLAM problems linear. The approach employs a linear Kalman filter to estimate camera translation and planar landmarks. A tracking-by-detection scheme using Atlanta representation is introduced for understanding different types of scenes.
We propose a new linear RGB-D simultaneous localization and mapping (SLAM) formulation by utilizing planar features of the structured environments. The key idea is to understand a given structured scene and exploit its structural regularities such as the Manhattan world. This understanding allows us to decouple the camera rotation by tracking structural regularities, which makes SLAM problems free from being highly nonlinear. Additionally, it provides a simple yet effective cue for representing planar features, which leads to a linear SLAM formulation. Given an accurate camera rotation, we jointly estimate the camera translation and planar landmarks in the global planar map using a linear Kalman filter. Our linear SLAM method, called L-SLAM, can understand not only the Manhattan world but the more general scenario of the Atlanta world, which consists of a vertical direction and a set of horizontal directions orthogonal to the vertical direction. To this end, we introduce a novel tracking-by-detection scheme that infers the underlying scene structure by Atlanta representation. With efficient Atlanta representation, we formulate a unified linear SLAM framework for structured environments. We evaluate L-SLAM on a synthetic dataset and RGB-D benchmarks, demonstrating comparable performance to other state-of-the-art SLAM methods without using expensive nonlinear optimization. We assess the accuracy of L-SLAM on a practical application of augmented reality.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available