A multi-resolution ICP with heuristic closest point search for fast and robust 3D registration of range images

Jost, Timothée; Hügli, Heinz

doi:10.1109/im.2003.1240278

Cited by 94 publications

(58 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Constraints are the properties that limit the search space for transformation and correspondences. [56], [62] In rigid registration, correspondences assist in further pruning the transformation search space, whilst in the non-rigid case, establishing correspondences is the essential step that drives alignment.…”

Section: Constraints For Rigid and Non-rigid Registrationmentioning

confidence: 99%

Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Nonrigid

Tam

Cheng

Lai

et al. 2013

IEEE Trans. Visual. Comput. Graphics

565

268

View full text Add to dashboard Cite

Abstract-3D surface registration transforms multiple 3D datasets into the same coordinate system so as to align overlapping components of these sets. Recent surveys have covered different aspects of either rigid or non-rigid registration, but seldom discuss them as a whole. Our study serves two purposes: (i) to give a comprehensive survey of both types of registration, focusing on 3D point clouds and meshes, and (ii) to provide a better understanding of registration from the perspective of data fitting. Registration is closely related to data fitting in that it comprises three core interwoven components: model selection, correspondences & constraints and optimization. Study of these components (i) provides a basis for comparison of the novelties of different techniques, (ii) reveals the similarity of rigid and non-rigid registration in terms of problem representations, and (iii) shows how over-fitting arises in non-rigid registration and the reasons for increasing interest in intrinsic techniques. We further summarise some practical issues of registration which include initializations and evaluations, and discuss some of our own observations, insights and foreseeable research trends.

show abstract

Section: Constraints For Rigid and Non-rigid Registrationmentioning

confidence: 99%

Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Nonrigid

Tam

Cheng

Lai

et al. 2013

IEEE Trans. Visual. Comput. Graphics

565

268

View full text Add to dashboard Cite

show abstract

“…Jost and Hugli [2003] compute ICP several times while varying the resolution from coarse to fine. At a coarse resolution (i.e., with a limited number of points) ICP converges faster but with less accuracy than at a fine resolution.…”

Section: Implementation Optimizationmentioning

confidence: 99%

A Review of Point Cloud Registration Algorithms for Mobile Robotics

Pomerleau

Colas²,

Siegwart³

2015

FNT in Robotics

552

241

View full text Add to dashboard Cite

“…They used the ICP algorithm to match the freeform with 6 degrees of freedom (6DOF). To raise the speed of the representative registration ICP algorithm, the number of repetition n as well as the data points Np and Nx were reduced [7]. Another study on the registration algorithm used the Kernel correlation, which expanded the concept of point sets correlation [8].…”

Section: Related Workmentioning

confidence: 99%

Development of Optimized Point Clouds Merging Method for Rapid Processing to Generate Earthwork Site Model

Kwon¹,

Lee²,

Lee³

et al. 2011

28th International Symposium on Automation and Robotics in Construction (ISARC 2011)

View full text Add to dashboard Cite

ABSTRACT:As a continuation of the authors' research presented in previous years (ISARC), these authors focus on the processing aspect of the 3D terrain models acquired from heterogeneous 3D scan sources. This includes a revision of the authors' ICP-based merging algorithm to achieve better accuracy in the ever-changing shape of an earthwork site with acceptable penalty in speed, and the introduction of a new side-scanning fast laser to obtain accurate local shapes at a reasonably fast time. In conjunction with these issues, the data format for holding the terrain data was also taken into account, for faster processing.

show abstract

A multi-resolution ICP with heuristic closest point search for fast and robust 3D registration of range images

Abstract: The iterative closest point (ICP)

Cited by 94 publications

References 17 publications

Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Nonrigid

Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Nonrigid

A Review of Point Cloud Registration Algorithms for Mobile Robotics

Development of Optimized Point Clouds Merging Method for Rapid Processing to Generate Earthwork Site Model

Contact Info

Product

Resources

About