Multi-relation octomap based Heuristic ICP for air/surface robots cooperation

Peng Yin; Yuqing He; Feng Gu; Jianda Han

doi:10.1109/ROBIO.2015.7418987

Multi-relation octomap based Heuristic ICP for air/surface robots cooperation

Peng Yin
, Yuqing He
, Feng Gu
, Jianda Han

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

1 Citation (Scopus)

Abstract

In this paper, we focus on the problem of fast and accurate featureless registration of outdoor large scale 3D point-clouds which possess great differences in the aspects of both resolution and view of point. There are two main methods generally used to solve this problem: feature based algorithm and point based one. However, feature based method can only be used in very special environments with clear geometric structure, while traditional point based method can only obtain a relative coarse estimation and is sensitive to initial alignment. Thus, in this paper, a registration algorithm, called Octree Based Multiresolution Heuristic ICP, is proposed. Without relying on the good initial registration and marked features, hybrid-ICP combines different ICP algorithms, and improve the alignments using finer levels of representation. In our outdoor riverside environments experiments, our method outperform the classical point based registration algorithm with an accuracy of 7 times better than classical Generalized-ICP and a speedup 1.6 times. © 2015 IEEE.

Original language	English
Title of host publication	2015 IEEE International Conference on Robotics and Biomimetics, IEEE-ROBIO 2015
Publisher	IEEE
Pages	1524-1529
ISBN (Print)	9781467396745
DOIs	https://doi.org/10.1109/ROBIO.2015.7418987
Publication status	Published - 2015
Externally published	Yes
Event	IEEE International Conference on Robotics and Biomimetics, IEEE-ROBIO 2015 - Zhuhai, China Duration: 6 Dec 2015 → 9 Dec 2015 https://ieeexplore.ieee.org/xpl/conhome/7397291/proceeding

Publication series

Name	2015 IEEE International Conference on Robotics and Biomimetics, IEEE-ROBIO 2015

Conference

Conference	IEEE International Conference on Robotics and Biomimetics, IEEE-ROBIO 2015
Place	China
City	Zhuhai
Period	6/12/15 → 9/12/15
Internet address	https://ieeexplore.ieee.org/xpl/conhome/7397291/proceeding

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Funding

Research supported by the State Key Program of National Natural Science of China (Grant No. 61473282, 61203340).

Access Output

10.1109/ROBIO.2015.7418987

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{0825a14f929944b19c9cf6124125ff33,

title = "Multi-relation octomap based Heuristic ICP for air/surface robots cooperation",

abstract = "In this paper, we focus on the problem of fast and accurate featureless registration of outdoor large scale 3D point-clouds which possess great differences in the aspects of both resolution and view of point. There are two main methods generally used to solve this problem: feature based algorithm and point based one. However, feature based method can only be used in very special environments with clear geometric structure, while traditional point based method can only obtain a relative coarse estimation and is sensitive to initial alignment. Thus, in this paper, a registration algorithm, called Octree Based Multiresolution Heuristic ICP, is proposed. Without relying on the good initial registration and marked features, hybrid-ICP combines different ICP algorithms, and improve the alignments using finer levels of representation. In our outdoor riverside environments experiments, our method outperform the classical point based registration algorithm with an accuracy of 7 times better than classical Generalized-ICP and a speedup 1.6 times. {\textcopyright} 2015 IEEE.",

author = "Peng Yin and Yuqing He and Feng Gu and Jianda Han",

note = "Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected]. ; IEEE International Conference on Robotics and Biomimetics, IEEE-ROBIO 2015 ; Conference date: 06-12-2015 Through 09-12-2015",

year = "2015",

doi = "10.1109/ROBIO.2015.7418987",

language = "English",

isbn = "9781467396745",

series = "2015 IEEE International Conference on Robotics and Biomimetics, IEEE-ROBIO 2015",

publisher = "IEEE",

pages = "1524--1529",

booktitle = "2015 IEEE International Conference on Robotics and Biomimetics, IEEE-ROBIO 2015",

address = "United States",

url = "https://ieeexplore.ieee.org/xpl/conhome/7397291/proceeding",

}

Yin, P, He, Y, Gu, F & Han, J 2015, Multi-relation octomap based Heuristic ICP for air/surface robots cooperation. in 2015 IEEE International Conference on Robotics and Biomimetics, IEEE-ROBIO 2015., 7418987, 2015 IEEE International Conference on Robotics and Biomimetics, IEEE-ROBIO 2015, IEEE, pp. 1524-1529, IEEE International Conference on Robotics and Biomimetics, IEEE-ROBIO 2015, Zhuhai, China, 6/12/15. https://doi.org/10.1109/ROBIO.2015.7418987

Multi-relation octomap based Heuristic ICP for air/surface robots cooperation. / Yin, Peng; He, Yuqing; Gu, Feng et al.
2015 IEEE International Conference on Robotics and Biomimetics, IEEE-ROBIO 2015. IEEE, 2015. p. 1524-1529 7418987 (2015 IEEE International Conference on Robotics and Biomimetics, IEEE-ROBIO 2015).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Multi-relation octomap based Heuristic ICP for air/surface robots cooperation

AU - Yin, Peng

AU - He, Yuqing

AU - Gu, Feng

AU - Han, Jianda

N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

PY - 2015

Y1 - 2015

N2 - In this paper, we focus on the problem of fast and accurate featureless registration of outdoor large scale 3D point-clouds which possess great differences in the aspects of both resolution and view of point. There are two main methods generally used to solve this problem: feature based algorithm and point based one. However, feature based method can only be used in very special environments with clear geometric structure, while traditional point based method can only obtain a relative coarse estimation and is sensitive to initial alignment. Thus, in this paper, a registration algorithm, called Octree Based Multiresolution Heuristic ICP, is proposed. Without relying on the good initial registration and marked features, hybrid-ICP combines different ICP algorithms, and improve the alignments using finer levels of representation. In our outdoor riverside environments experiments, our method outperform the classical point based registration algorithm with an accuracy of 7 times better than classical Generalized-ICP and a speedup 1.6 times. © 2015 IEEE.

AB - In this paper, we focus on the problem of fast and accurate featureless registration of outdoor large scale 3D point-clouds which possess great differences in the aspects of both resolution and view of point. There are two main methods generally used to solve this problem: feature based algorithm and point based one. However, feature based method can only be used in very special environments with clear geometric structure, while traditional point based method can only obtain a relative coarse estimation and is sensitive to initial alignment. Thus, in this paper, a registration algorithm, called Octree Based Multiresolution Heuristic ICP, is proposed. Without relying on the good initial registration and marked features, hybrid-ICP combines different ICP algorithms, and improve the alignments using finer levels of representation. In our outdoor riverside environments experiments, our method outperform the classical point based registration algorithm with an accuracy of 7 times better than classical Generalized-ICP and a speedup 1.6 times. © 2015 IEEE.

UR - https://www.scopus.com/pages/publications/84964506145

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84964506145&origin=recordpage

U2 - 10.1109/ROBIO.2015.7418987

DO - 10.1109/ROBIO.2015.7418987

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781467396745

T3 - 2015 IEEE International Conference on Robotics and Biomimetics, IEEE-ROBIO 2015

SP - 1524

EP - 1529

BT - 2015 IEEE International Conference on Robotics and Biomimetics, IEEE-ROBIO 2015

PB - IEEE

T2 - IEEE International Conference on Robotics and Biomimetics, IEEE-ROBIO 2015

Y2 - 6 December 2015 through 9 December 2015

ER -

Multi-relation octomap based Heuristic ICP for air/surface robots cooperation

Abstract

Publication series

Conference

Bibliographical note

Funding

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this