CodedVO: Coded Visual Odometry

Abstract

Autonomous robots often rely on monocular cameras for odometry estimation and navigation. However, the scale ambiguity problem presents a critical barrier to effective monocular visual odometry. In this paper, we present CodedVO, a novel monocular visual odometry method that overcomes the scale ambiguity problem by employing custom optics to physically encode metric depth information into imagery. By incorporating this information into our odometry pipeline, we achieve state-of-the-art performance in monocular visual odometry with a known scale. We evaluate our method in diverse indoor environments and demonstrate its robustness and adaptability. We achieve a 0.08m average trajectory error in odometry evaluation on the ICL-NUIM indoor odometry dataset.

7 pages, 4 figures, IEEE ROBOTICS AND AUTOMATION LETTERS

References in corpus (7)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Faster and better: a machine learning approach to corner detection
• DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras
• ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth
• Deep Patch Visual Odometry
• MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation
• Simple model for the Darwinian transition in early evolution