• Corpus ID: 6639131

Towards a benchmark for RGB-D SLAM evaluation

  title={Towards a benchmark for RGB-D SLAM evaluation},
  author={J{\"u}rgen Sturm and St{\'e}phane Magnenat and Nikolas Engelhard and F. Pomerleau and Francis Colas and Wolfram Burgard and Daniel Cremers and Roland Y. Siegwart},
  booktitle={RSS 2011},
We provide a large dataset containing RGB-D image sequences and the ground-truth camera trajectories with the goal to establish a benchmark for the evaluation of visual SLAM systems. [] Key Method Further, we provide the accelerometer data from the Kinect. Finally, we propose an evaluation criterion for measuring the quality of the estimated camera trajectory of visual SLAM systems.

Figures from this paper

A benchmark for the evaluation of RGB-D SLAM systems
A large set of image sequences from a Microsoft Kinect with highly accurate and time-synchronized ground truth camera poses from a motion capture system is recorded for the evaluation of RGB-D SLAM systems.
An evaluation of the RGB-D SLAM system
We present an approach to simultaneous localization and mapping (SLAM) for RGB-D cameras like the Microsoft Kinect. Our system concurrently estimates the trajectory of a hand-held Kinect and
A benchmark for RGB-D visual odometry, 3D reconstruction and SLAM
This work introduces the Imperial College London and National University of Ireland Maynooth (ICL-NUIM) dataset and presents a collection of handheld RGB-D camera sequences within synthetically generated environments to provide a method to benchmark the surface reconstruction accuracy.
Evaluating Egomotion and Structure-from-Motion Approaches Using the TUM RGB-D Benchmark
The TUM RGB-D benchmark for visual odometry and SLAM evaluation is presented and the evaluation results of the first users from outside the group are discussed and briefly summarized.
Incremental registration of RGB-D images
This paper presents a real-time technique for 6-DoF camera pose estimation through the incremental registration of RGB-D images and shows that the proposed two-stage approach significantly reduces error in the pose estimation, compared to a state-of-the-art ICP registration technique.
Real-time visual odometry from dense RGB-D images
An energy-based approach to visual odometry from RGB-D images of a Microsoft Kinect camera is presented which is faster than a state-of-the-art implementation of the iterative closest point (ICP) algorithm by two orders of magnitude.
Adaptive RGB-D Localization
  • M. Paton, J. Kosecka
  • Computer Science
    2012 Ninth Conference on Computer and Robot Vision
  • 2012
An adaptive architecture which computes the pose estimate from the most reliable measurements in a given environment is proposed and thorough evaluation of the resulting algorithm is presented against a dataset of RGB-D benchmarks, demonstrating superior or comparable performance in the absence of the global optimization stage.
Improved-ORB-based SLAM Using RGB-D Data
An improved ORB features based SLAM framework with corresponding method using RGB-D data is proposed, which effectively reduces errors, enhances robustness, and builds a dense map of the environment.
Toward evaluation of visual navigation algorithms on RGB-D data from the first- and second-generation Kinect
A new RGB-D data set is described, which is a first attempt to systematically evaluate the indoor navigation algorithms on data from two different sensors in the same environment and along the same trajectories, and evaluates the visual odometry algorithm on the obtained sequences.
Survey and Evaluation of RGB-D SLAM
A large number of evaluation experiments are conducted on multiple RGB-D SLAM systems, and their advantages and disadvantages are analyzed, as well as performance differences in different application scenarios, and references are provided for researchers and developers.


RGB-D Mapping: Using Depth Cameras for Dense 3D Modeling of Indoor Environments
This paper presents RGB-D Mapping, a full 3D mapping system that utilizes a novel joint optimization algorithm combining visual features and shape-based alignment to achieve globally consistent maps.
Scale Drift-Aware Large Scale Monocular SLAM
This paper describes a new near real-time visual SLAM system which adopts the continuous keyframe optimisation approach of the best current stereo systems, but accounts for the additional challenges presented by monocular input and presents a new pose-graph optimisation technique which allows for the efficient correction of rotation, translation and scale drift at loop closures.
On measuring the accuracy of SLAM algorithms
A framework for analyzing the results of a SLAM approach based on a metric for measuring the error of the corrected trajectory is proposed, which overcomes serious shortcomings of approaches using a global reference frame to compute the error.
Parallel Tracking and Mapping for Small AR Workspaces
A system specifically designed to track a hand-held camera in a small AR workspace, processed in parallel threads on a dual-core computer, that produces detailed maps with thousands of landmarks which can be tracked at frame-rate with accuracy and robustness rivalling that of state-of-the-art model-based systems.
Real-Time Dense Geometry from a Handheld Camera
A novel variational approach to estimate dense depth maps from multiple images in real-time by using robust penalizers for both data term and regularizer, which preserves discontinuities in the depth map.
The New College Vision and Laser Data Set
In this paper we present a large dataset intended for use in mobile robotics research. Gathered from a robot driving several kilometers through a park and campus, it contains a five-degree-of-freedom
Real-time 3D motion and structure of point features: a front-end system for vision-based control and interaction
We present a system that consists of one camera connected to a personal computer that can (a) select and track a number of high-contrast point features on a sequence of images, (b) estimate their
Towards lifelong visual maps
  • K. Konolige, James Bowman
  • Computer Science
    2009 IEEE/RSJ International Conference on Intelligent Robots and Systems
  • 2009
This paper presents a system of visual mapping, using only input from a stereo camera, that continually updates an optimized metric map in large indoor spaces with movable objects: people, furniture, partitions, etc.
Outdoor Mapping and Navigation Using Stereo Vision
This work considers the problem of autonomous navigation in an unstructured outdoor environment, and uses stereo vision as the main sensor to use more distant objects as landmarks for navigation, and to learn and use color and texture models of the environment.
6D SLAM—3D mapping outdoor environments: Research Articles
This paper presents a robotic mapping method based on locally consistent 3D laser range scans that combines Iterative Closest Point scan matching, combined with a heuristic for closed loop detection and a global relaxation method, results in a highly precise mapping system.