Published on Wed Apr 03 2019

Continuous Direct Sparse Visual Odometry from RGB-D Images

Maani Ghaffari, William Clark, Anthony Bloch, Ryan M. Eustice, Jessy W. Grizzle

This paper reports on a novel formulation and evaluation of visual odometry from RGB-D images. The developed theoretical framework generalizes the widely used direct energy formulation (photometric error minimizing) technique.

0
0
0
Abstract

This paper reports on a novel formulation and evaluation of visual odometry from RGB-D images. Assuming a static scene, the developed theoretical framework generalizes the widely used direct energy formulation (photometric error minimization) technique for obtaining a rigid body transformation that aligns two overlapping RGB-D images to a continuous formulation. The continuity is achieved through functional treatment of the problem and representing the process models over RGB-D images in a reproducing kernel Hilbert space; consequently, the registration is not limited to the specific image resolution and the framework is fully analytical with a closed-form derivation of the gradient. We solve the problem by maximizing the inner product between two functions defined over RGB-D images, while the continuous action of the rigid body motion Lie group is captured through the integration of the flow in the corresponding Lie algebra. Energy-based approaches have been extremely successful and the developed framework in this paper shares many of their desired properties such as the parallel structure on both CPUs and GPUs, sparsity, semi-dense tracking, avoiding explicit data association which is computationally expensive, and possible extensions to the simultaneous localization and mapping frameworks. The evaluations on experimental data and comparison with the equivalent energy-based formulation of the problem confirm the effectiveness of the proposed technique, especially, when the lack of structure and texture in the environment is evident.

Tue Dec 15 2020
Computer Vision
Canny-VO: Visual Odometry with RGB-D Cameras based on Geometric 3D-2D Edge Alignment
The paper reviews the classical problem of free-form curve registration. It applies it to an efficient RGBD visual odometry system called Canny-VO. It efficiently tracks all Canny edge features extracted from the images.
0
0
0
Mon Feb 06 2017
Computer Vision
Semi-Dense Visual Odometry for RGB-D Cameras Using Approximate Nearest Neighbour Fields
This paper presents a robust and efficient semi-dense visual odometry solution for RGB-D cameras. The core of our method is a 2D-3D ICP pipeline which estimates the pose of the sensor. The processing is speeded up by efficiently implemented Euclidean distance criterion.
0
0
0
Mon Dec 02 2019
Computer Vision
A Keyframe-based Continuous Visual SLAM for RGB-D Cameras via Nonparametric Joint Geometric and Appearance Representation
This paper reports on a robust RGB-D SLAM system that performs well in textured and structured environments. We present a novel keyframe-based continuous visual odometry that builds on the recently developed continuous sensor registration framework.
0
0
0
Sat Jul 09 2016
Computer Vision
Direct Sparse Odometry
We propose a novel direct sparse visual odometry formulation. It combines afully direct probabilistic model (minimizing a photometric error) with joint optimization of all model parameters. This is achieved in real time by omitting the smoothness prior used in other direct methods.
0
0
0
Thu Nov 27 2014
Computer Vision
Bi-objective Optimization for Robust RGB-D Visual Odometry
This paper considers a new bi-objective optimization formulation for robust RGB-D visual odometry. The new formulation yields more accurate motion estimates and is more robust when textural or structural features in the image sequence are lacking.
0
0
0
Tue Oct 01 2019
Machine Learning
Adaptive Continuous Visual Odometry from RGB-D Images
We extend the recently developed continuous visual odometry framework for RGB-D cameras to an adaptive framework via online hyperparameter learning. We focus on the case of isotropic kernels with a scalar as the length-scale. The experimental evaluations using publicly available benchmarks show the proposed adaptive continuous
0
0
0