SPLODE: Semi-Probabilistic Point and Line Odometry with Depth Estimation from RGB-D Camera Motion

TL;DR

This paper introduces SPLODE, a visual odometry method that combines depth sensor data and probabilistic depth estimates from camera motion to improve accuracy in challenging indoor and outdoor environments.

Contribution

It presents a novel probabilistic framework for depth estimation that explicitly models uncertainty and integrates both depth measurements and estimates for robust RGB-D odometry.

Findings

Outperforms traditional methods in environments with limited or noisy depth data

Effectively combines depth measurements and estimates for improved accuracy

Demonstrates robustness in large indoor and outdoor scenes

Abstract

Active depth cameras suffer from several limitations, which cause incomplete and noisy depth maps, and may consequently affect the performance of RGB-D Odometry. To address this issue, this paper presents a visual odometry method based on point and line features that leverages both measurements from a depth sensor and depth estimates from camera motion. Depth estimates are generated continuously by a probabilistic depth estimation framework for both types of features to compensate for the lack of depth measurements and inaccurate feature depth associations. The framework models explicitly the uncertainty of triangulating depth from both point and line observations to validate and obtain precise estimates. Furthermore, depth measurements are exploited by propagating them through a depth map registration module and using a frame-to-frame motion estimation method that considers 3D-to-2D and 2D-to-3D reprojection errors, independently. Results on RGB-D sequences captured on large indoor and outdoor scenes, where depth sensor limitations are critical, show that the combination of depth measurements and estimates through our approach is able to overcome the absence and inaccuracy of depth measurements.