ElasticFusion: Dense SLAM Without A Pose Graph

Whelan, Thomas J.; Leutenegger, Stefan; Salas-Moreno, Renato F.; Glocker, Ben; Davison, Andrew J.

doi:10.15607/rss.2015.xi.001

Cited by 681 publications

(689 citation statements)

References 26 publications

Supporting

Mentioning

686

Contrasting

Unclassified

Order By: Relevance

“…INTRODUCTION Most autonomous robots, including self-driving cars, must be able to reliably localize themselves, ideally by using only their own sensors without relying on external information such as GPS or other additional infrastructure placed in the environment. There has been significant advances in visionbased [6,7] and RGB-D-based [18,33,3] SLAM systems over the past few years. Most of these approaches use (semi-)dense reconstructions of the environment and exploit them for frameto-model tracking, either by jointly optimizing the map and pose estimates or by alternating pose estimation and map building [21].…”

mentioning

confidence: 99%

Efficient Surfel-Based SLAM using 3D Laser Range Data in Urban Environments

Behley¹,

Stachniss²

2018

Robotics: Science and Systems XIV

389

264

View full text Add to dashboard Cite

Abstract-Accurate and reliable localization and mapping is a fundamental building block for most autonomous robots. For this purpose, we propose a novel, dense approach to laserbased mapping that operates on three-dimensional point clouds obtained from rotating laser sensors. We construct a surfel-based map and estimate the changes in the robot's pose by exploiting the projective data association between the current scan and a rendered model view from that surfel map. For detection and verification of a loop closure, we leverage the map representation to compose a virtual view of the map before a potential loop closure, which enables a more robust detection even with low overlap between the scan and the already mapped areas. Our approach is efficient and enables real-time capable registration. At the same time, it is able to detect loop closures and to perform map updates in an online fashion. Our experiments show that we are able to estimate globally consistent maps in large scale environments solely based on point cloud data.I. INTRODUCTION Most autonomous robots, including self-driving cars, must be able to reliably localize themselves, ideally by using only their own sensors without relying on external information such as GPS or other additional infrastructure placed in the environment. There has been significant advances in visionbased [6,7] and RGB-D-based [18,33,3] SLAM systems over the past few years. Most of these approaches use (semi-)dense reconstructions of the environment and exploit them for frameto-model tracking, either by jointly optimizing the map and pose estimates or by alternating pose estimation and map building [21]. Dense approaches have a prospective advantage over feature-based and sparse approaches as they use all available information and thus do not depend on reliable feature extraction or availability of such features.In contrast to these developments, current 3D laser-based mapping systems mainly accomplish the estimation relying on feature-based solutions [34,35], reduced map representations [14,13], voxel grid-based methods [16], or point sub-sampling [30], which all effectively reduce the data used for alignment. Compared to most indoor applications using RGB-D sensors, we have to tackle additional challenges in outdoor applications using 3D laser sensors, i.e., (1) fast sensor movement resulting in large displacements between scans, (2) comparably sparse point clouds, and (3) large-scale environments.In this paper, we present a dense mapping approach called Surfel-based Mapping (SuMa), which builds globally consistent maps by tracking the pose, so-called odometry, and closing loops using a pose graph as illustrated in Figure 1. To this end, we employ a surfel map to efficiently generate synthetic views for projective data association and additional

show abstract

mentioning

confidence: 99%

Efficient Surfel-Based SLAM using 3D Laser Range Data in Urban Environments

Behley¹,

Stachniss²

2018

Robotics: Science and Systems XIV

389

264

View full text Add to dashboard Cite

show abstract

“…We compare our algorithm with three other real-time dense tracking and mapping approaches: KinectFusion [1] (PCL implementation [34]), the work of Zhou et al [22], and ElasticFusion [37] of Whelan et al Both [1] and [22] are pure depth camera tracking and reconstruction approaches. The ElasticFusion jointly aligns RGB and depth information, and represents the scene with surfels.…”

Section: Discussionmentioning

confidence: 99%

“…Zhou et al [22], (c) ElasticFusion [37], and (d) our approach. Row 1~3 are reconstructions of the synthetic data, row 4~9 are the real-world reconstructions (only the 3D printed objectives are evaluated, with other areas of the scenes grayed out).…”

Section: Kinectfusion [1]mentioning

confidence: 99%

See 1 more Smart Citation

CuFusion: Accurate Real‐time Camera Tracking and Volumetric Scene Reconstruction with a Cuboid

Zhang

2017

Preprint

View full text Add to dashboard Cite

Given a stream of depth images with a known cuboid reference object present in the scene, we propose a novel approach for accurate camera tracking and volumetric surface reconstruction in real-time. Our contribution in this paper is threefold: (a) utilizing a priori knowledge of the cuboid reference object, we keep drift-free camera tracking without explicit global optimization; (b) we improve the fineness of the volumetric surface representation by proposing a prediction-corrected data fusion strategy rather than simple moving average, which enables accurate reconstruction of high-frequency details such as sharp edges of objects and geometries of high curvature; (c) we introduce a benchmark dataset CU3D containing both synthetic and real-world scanning sequences with ground-truth camera trajectories and surface models for quantitative evaluation of 3D reconstruction algorithms. We test our algorithm on our dataset and demonstrate its accuracy compared with other state-of-the-art algorithms. We release both our dataset and code as opensource 1 for other researchers to reproduce and verify our results.

show abstract

“…For our real-world household datasets we have generated pseudo ground truth using the ElasticFusion system [14]. The rooms were scanned and reconstructed using a hand-held depth camera.…”

Section: B Household Datamentioning

confidence: 99%

Room layout estimation from rapid omnidirectional exploration

Lukierski

Leutenegger

Davison

2017

2017 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

Abstract-A new generation of practical, low-cost indoor robots is now using wide-angle cameras to aid navigation, but usually this is limited to position estimation via sparse featurebased SLAM. Such robots usually have little global sense of the dimensions, demarcation or identities of the rooms they are in, information which would be very useful to enable behaviour with much more high level intelligence.In this paper we show that we can augment an omnidirectional SLAM pipeline with straightforward dense stereo estimation and simple and robust room model fitting to obtain rapid and reliable estimation of the global shape of typical rooms from short robot motions. We have tested our method extensively in real homes, offices and on synthetic data. We also give examples of how our method can extend to making composite maps of larger rooms, and detecting room transitions.

show abstract

ElasticFusion: Dense SLAM Without A Pose Graph

Cited by 681 publications

References 26 publications

Efficient Surfel-Based SLAM using 3D Laser Range Data in Urban Environments

Efficient Surfel-Based SLAM using 3D Laser Range Data in Urban Environments

CuFusion: Accurate Real‐time Camera Tracking and Volumetric Scene Reconstruction with a Cuboid

Room layout estimation from rapid omnidirectional exploration

Contact Info

Product

Resources

About