Efficient Large-Scale Point Cloud Registration Using Loop Closures

Shiratori, Takaaki; Berclaz, Jérôme; Harville, M.; Shah, Chintan; Li, Taoyu; Matsushita, Yasuyuki; Shiller, Stephen

doi:10.1109/3dv.2015.33

Cited by 27 publications

(18 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The point clouds registration has been drawn considerable attention (Pomerleau et al, 2015;Cheng et al, 2018;Dong et al, 2020). Coarse-to-fine is a common strategy employed.…”

Section: Related Workmentioning

confidence: 99%

A Marker-Free Calibration Method for Mobile Laser Scanning Point Clouds Correction

Wang

Xiao-liang

et al. 2020

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Mobile laser scanning systems (MLS) have been widely used in collecting three-dimensional point clouds for many applications, such as 3D mapping, road facilities inventory and high definition map. Although MLS is calibrated accurately to obtain precise locations of point clouds, it is still challenging to obtain precise locations of point clouds in the areas of GPS signal denied or narrow streets with high dense buildings, resulting in uneven position deviations of point clouds between the overlapping trajectory areas. In this paper, a marker-free calibration method is proposed to solve the above problems. The proposed method firstly partitions the trajectory into segments according to the error distribution while collecting the point clouds. Secondly, the features in each overlapped area are extracted and a kind of Locally Aggregated Descriptors are built for the matching. Thirdly, a coarse-to-fine pairwise point clouds alignment is applied on the overlapping areas. Finally, the global alignment of point clouds is fulfilled with minimizing the position deviations between the overlapping areas and the adjacent segments. The proposed method has been used to correct the point clouds from several different MLSs. Experiments show that this method automatically locates and corrects the uneven position deviations in terms of good robustness and efficiencies. Besides, it proves that the proposed method is also an easy-to-use tool for the automatic correction of MLS point clouds position and boresights.

show abstract

“…The point clouds registration has been drawn considerable attention (Pomerleau et al, 2015;Cheng et al, 2018;Dong et al, 2020). Coarse-to-fine is a common strategy employed.…”

Section: Related Workmentioning

confidence: 99%

A Marker-Free Calibration Method for Mobile Laser Scanning Point Clouds Correction

Wang

Xiao-liang

et al. 2020

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Conventional pairwise approaches [8,32] as well as KinectFusion incrementally integrate a set of range data using the ICP algorithm; they suffer from accumulated errors in general. Therefore, the global registration approaches [3,44,29,5,37,18,24,47,1] have been developed to alleviate accumulation errors by optimizing the global poses simultaneously. Bergevin et al [3] proposed a star-shaped network for global registration.…”

Section: Previous Workmentioning

confidence: 99%

“…For the sake of robust global registration, a number of researches [5,37] focused on identifying loop closures which must be acquired for global registration. As long as loop closures are properly identified, it is possible to reduce accumulation errors effectively.…”

Section: Previous Workmentioning

confidence: 99%

Joint Layout Estimation and Global Multi-view Registration for Indoor Reconstruction

Lee

Yea²,

Park

et al. 2017

2017 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

In this paper, we propose a novel method to jointly solve scene layout estimation and global registration problems for accurate indoor 3D reconstruction. Given a sequence of range data, we first build a set of scene fragments using KinectFusion and register them through pose graph optimization. Afterwards, we alternate between layout estimation and layout-based global registration processes in iterative fashion to complement each other. We extract the scene layout through hierarchical agglomerative clustering and energy-based multi-model fitting in consideration of noisy measurements. Having the estimated scene layout in one hand, we register all the range data through the global iterative closest point algorithm where the positions of 3D points that belong to the layout such as walls and a ceiling are constrained to be close to the layout. We experimentally verify the proposed method with the publicly available synthetic and real-world datasets in both quantitative and qualitative ways.

show abstract

“…Article by Shiratori et al [16] describes a method for aligning very large sets of 3D point clouds. From an initial estimate of the sensor paths, a 3D graph is constructed and the alignment problem is decomposed into smaller ones based on the loop closures that exist in this graph.…”

Section: Introduction Reconstruction Of 3d Objects and Scenes Has Varmentioning

confidence: 99%

Proportional Error Back-Propagation (PEB): Real-Time Automatic Loop Closure Correction for Maintaining Global Consistency in 3D Reconstruction with Minimal Computational Cost

Daneshmand

Avots

Anbarjafari

2018

Measurement Science Review

View full text Add to dashboard Cite

This paper introduces a robust, real-time loop closure correction technique for achieving global consistency in 3D reconstruction, whose underlying notion is to back-propagate the cumulative transformation error appearing while merging the pairs of consecutive frames in a sequence of shots taken by an RGB-D or depth camera. The proposed algorithm assumes that the starting frame and the last frame of the sequence roughly overlap. In order to verify the robustness and reliability of the proposed method, namely, Proportional Error Back- Propagation (PEB), it has been applied to numerous case-studies, which encompass a wide range of experimental conditions, including different scanning trajectories with reversely directed motions within them, and the results are presented. The main contribution of the proposed algorithm is its considerably low computational cost which has the possibility of usage in real-time 3D reconstruction applications. Also, neither manual input nor interference is required from the user, which renders the whole process automatic.

show abstract

Efficient Large-Scale Point Cloud Registration Using Loop Closures

Cited by 27 publications

References 26 publications

A Marker-Free Calibration Method for Mobile Laser Scanning Point Clouds Correction

A Marker-Free Calibration Method for Mobile Laser Scanning Point Clouds Correction

Joint Layout Estimation and Global Multi-view Registration for Indoor Reconstruction

Proportional Error Back-Propagation (PEB): Real-Time Automatic Loop Closure Correction for Maintaining Global Consistency in 3D Reconstruction with Minimal Computational Cost

Contact Info

Product

Resources

About