Canny-VO: Visual Odometry with RGB-D Cameras based on Geometric 3D-2D Edge Alignment

Abstract

The present paper reviews the classical problem of free-form curve registration and applies it to an efficient RGBD visual odometry system called Canny-VO, as it efficiently tracks all Canny edge features extracted from the images. Two replacements for the distance transformation commonly used in edge registration are proposed: Approximate Nearest Neighbour Fields and Oriented Nearest Neighbour Fields. 3D2D edge alignment benefits from these alternative formulations in terms of both efficiency and accuracy. It removes the need for the more computationally demanding paradigms of datato-model registration, bilinear interpolation, and sub-gradient computation. To ensure robustness of the system in the presence of outliers and sensor noise, the registration is formulated as a maximum a posteriori problem, and the resulting weighted least squares objective is solved by the iteratively re-weighted least squares method. A variety of robust weight functions are investigated and the optimal choice is made based on the statistics of the residual errors. Efficiency is furthermore boosted by an adaptively sampled definition of the nearest neighbour fields. Extensive evaluations on public SLAM benchmark sequences demonstrate state-of-the-art performance and an advantage over classical Euclidean distance fields.

References in corpus (3)

• ORB-SLAM: a Versatile and Accurate Monocular SLAM System
• ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras
• Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration

Cited by in corpus (10)

• Event-based Stereo Visual Odometry
• An Object SLAM Framework for Association, Mapping, and High-Level Tasks
• RGB-D Odometry and SLAM
• FP-Loc: Lightweight and Drift-free Floor Plan-assisted LiDAR Localization
• Semantic Nearest Neighbor Fields Monocular Edge Visual-Odometry
• A Fast and Light-weight Non-Iterative Visual Odometry with RGB-D Cameras
• Edge Detection for Event Cameras using Intra-pixel-area Events
• Comparing Representations in Tracking for Event Camera-based SLAM
• Incorporating Learnt Local and Global Embeddings into Monocular Visual SLAM
• Robust Monocular Edge Visual Odometry through Coarse-to-Fine Data Association