An indoor DSO-based ceiling-vision odometry system for indoor industrial environments
Abdelhak Bougouffa, Emmanuel Seignez, Samir Bouaziz, Florian Gardes
TL;DR
Ceiling-DSO introduces a generic ceiling-vision odometry approach based on Direct Sparse Odometry (DSO) for indoor industrial robots, avoiding assumptions about ceiling shapes or landmarks. It leverages a monocular upward camera and a simplified photometric model to estimate ego-motion in real time, validated against LiDAR-based SLAM ground truth in real-world industrial settings. A systematic study across image sizes, frame rates, and optimization window sizes demonstrates that 15fps with a window size of 7 provides a good trade-off between trajectory accuracy and computation time, while lower frame rates degrade performance. The work demonstrates the practicality of ceiling-vision odometry for robust localization in dynamic indoor environments and outlines directions for scaling to full SLAM with online scale estimation, map management, and loop closure, as well as releasing the curated dataset.
Abstract
Autonomous Mobile Robots operating in indoor industrial environments require a localization system that is reliable and robust. While Visual Odometry (VO) can offer a reasonable estimation of the robot's state, traditional VO methods encounter challenges when confronted with dynamic objects in the scene. Alternatively, an upward-facing camera can be utilized to track the robot's movement relative to the ceiling, which represents a static and consistent space. We introduce in this paper Ceiling-DSO, a ceiling-vision system based on Direct Sparse Odometry (DSO). Unlike other ceiling-vision systems, Ceiling-DSO takes advantage of the versatile formulation of DSO, avoiding assumptions about observable shapes or landmarks on the ceiling. This approach ensures the method's applicability to various ceiling types. Since no publicly available dataset for ceiling-vision exists, we created a custom dataset in a real-world scenario and employed it to evaluate our approach. By adjusting DSO parameters, we identified the optimal fit for online pose estimation, resulting in acceptable error rates compared to ground truth. We provide in this paper a qualitative and quantitative analysis of the obtained results.