Published on Tue Jul 24 2018

A Synchronized Stereo and Plenoptic Visual Odometry Dataset

Niclas Zeller, Franz Quint, Uwe Stilla

The dataset comprises a set of synchronized image sequences recorded by a micro lens array (MLA) based plenoptic camera and a stereo camera system. All sequences are recorded in avery large loop, where beginning and end show the same scene.

0
0
0
Abstract

We present a new dataset to evaluate monocular, stereo, and plenoptic camera based visual odometry algorithms. The dataset comprises a set of synchronized image sequences recorded by a micro lens array (MLA) based plenoptic camera and a stereo camera system. For this, the stereo cameras and the plenoptic camera were assembled on a common hand-held platform. All sequences are recorded in a very large loop, where beginning and end show the same scene. Therefore, the tracking accuracy of a visual odometry algorithm can be measured from the drift between beginning and end of the sequence. For both, the plenoptic camera and the stereo system, we supply full intrinsic camera models, as well as vignetting data. The dataset consists of 11 sequences which were recorded in challenging indoor and outdoor scenarios. We present, by way of example, the results achieved by state-of-the-art algorithms.

Sat Jul 09 2016
Computer Vision
A Photometrically Calibrated Benchmark For Monocular Visual Odometry
We present a dataset for evaluating the tracking accuracy of monocular visual odometry and SLAM methods. It contains 50 real-world sequences comprising more than 100 minutes of video, recorded across dozens of different environments. All sequences are photometrically calibrated.
0
0
0
Tue Apr 17 2018
Computer Vision
The TUM VI Benchmark for Evaluating Visual-Inertial Odometry
Visual odometry and SLAM methods have a large variety of applications in domains such as augmented reality or robotics. Complementing vision sensors with inertial measurements tremendously improves tracking accuracy and robustness.
0
0
0
Wed Sep 19 2018
Computer Vision
DSVO: Direct Stereo Visual Odometry
This paper proposes a novel approach to stereo visual odometry without stereo matching. Referred to as DSVO (Direct Stereo Visual Odometry), it operates directly on pixel intensities, without any explicit feature matching. It is particularly robust in scenes of repetitive high-frequency textures.
0
0
0
Thu Oct 05 2017
Computer Vision
Online Photometric Calibration for Auto Exposure Video for Realtime Visual Odometry and SLAM
Algorithm recovers exposure times of consecutive frames, the camera response function, and the attenuation factors of the sensor due to vignetting. Gain robust KLT feature tracks are used to obtain scene point correspondences as input to a nonlinear optimization 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
Wed May 29 2019
Computer Vision
Extending Monocular Visual Odometry to Stereo Camera Systems by Scale Optimization
Proposed method uses an additional camera to estimate and optimize the scale of the monocular visual odometry. It is computationally efficient, adding minimal overhead to the stereo vision system compared to straightforward stereo matching.
0
0
0