Point feature-based outdoor SLAM for rural environments with geometric analysis

Dong Il Kim, Heewon Chae, Jae-Bok Song, Jihong Min

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

This paper proposes a point feature-based outdoor SLAM method using only omnidirectional LIDAR. 3D local occupancy grid mapping and ground plane classification are conducted as a pre-process to refine the point cloud. Then uncertain objects are clustered with Euclidean distance. For applications in rural environments, point features are utilized because clusters are extracted from unclear and overlapped objects. To improve matching performance, the similarity of clusters is calculated with a Hausdorff distance and correspondence filtering with the point histogram is implemented. With the correspondence filtering, we can reduce false matches that cannot be removed from the initial matcher and thus improve the SLAM accuracy. The remaining point features are used as landmarks in SLAM, and the effectiveness of the scheme is verified through simulations with the real-world dataset.

Original languageEnglish
Title of host publication2015 12th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages218-223
Number of pages6
ISBN (Print)9781467379700
DOIs
Publication statusPublished - 2015 Dec 16
Event12th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2015 - Goyang City, Korea, Republic of
Duration: 2015 Oct 282015 Oct 30

Other

Other12th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2015
CountryKorea, Republic of
CityGoyang City
Period15/10/2815/10/30

Keywords

  • 3D Harris corner
  • Hausdorff distance
  • point clouds
  • SLAM
  • Velodyne

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction

Cite this

Kim, D. I., Chae, H., Song, J-B., & Min, J. (2015). Point feature-based outdoor SLAM for rural environments with geometric analysis. In 2015 12th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2015 (pp. 218-223). [7358940] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/URAI.2015.7358940

Point feature-based outdoor SLAM for rural environments with geometric analysis. / Kim, Dong Il; Chae, Heewon; Song, Jae-Bok; Min, Jihong.

2015 12th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 218-223 7358940.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kim, DI, Chae, H, Song, J-B & Min, J 2015, Point feature-based outdoor SLAM for rural environments with geometric analysis. in 2015 12th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2015., 7358940, Institute of Electrical and Electronics Engineers Inc., pp. 218-223, 12th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2015, Goyang City, Korea, Republic of, 15/10/28. https://doi.org/10.1109/URAI.2015.7358940
Kim DI, Chae H, Song J-B, Min J. Point feature-based outdoor SLAM for rural environments with geometric analysis. In 2015 12th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 218-223. 7358940 https://doi.org/10.1109/URAI.2015.7358940
Kim, Dong Il ; Chae, Heewon ; Song, Jae-Bok ; Min, Jihong. / Point feature-based outdoor SLAM for rural environments with geometric analysis. 2015 12th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 218-223
@inproceedings{c5109869f43447e6a08213d5f30323cf,
title = "Point feature-based outdoor SLAM for rural environments with geometric analysis",
abstract = "This paper proposes a point feature-based outdoor SLAM method using only omnidirectional LIDAR. 3D local occupancy grid mapping and ground plane classification are conducted as a pre-process to refine the point cloud. Then uncertain objects are clustered with Euclidean distance. For applications in rural environments, point features are utilized because clusters are extracted from unclear and overlapped objects. To improve matching performance, the similarity of clusters is calculated with a Hausdorff distance and correspondence filtering with the point histogram is implemented. With the correspondence filtering, we can reduce false matches that cannot be removed from the initial matcher and thus improve the SLAM accuracy. The remaining point features are used as landmarks in SLAM, and the effectiveness of the scheme is verified through simulations with the real-world dataset.",
keywords = "3D Harris corner, Hausdorff distance, point clouds, SLAM, Velodyne",
author = "Kim, {Dong Il} and Heewon Chae and Jae-Bok Song and Jihong Min",
year = "2015",
month = "12",
day = "16",
doi = "10.1109/URAI.2015.7358940",
language = "English",
isbn = "9781467379700",
pages = "218--223",
booktitle = "2015 12th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Point feature-based outdoor SLAM for rural environments with geometric analysis

AU - Kim, Dong Il

AU - Chae, Heewon

AU - Song, Jae-Bok

AU - Min, Jihong

PY - 2015/12/16

Y1 - 2015/12/16

N2 - This paper proposes a point feature-based outdoor SLAM method using only omnidirectional LIDAR. 3D local occupancy grid mapping and ground plane classification are conducted as a pre-process to refine the point cloud. Then uncertain objects are clustered with Euclidean distance. For applications in rural environments, point features are utilized because clusters are extracted from unclear and overlapped objects. To improve matching performance, the similarity of clusters is calculated with a Hausdorff distance and correspondence filtering with the point histogram is implemented. With the correspondence filtering, we can reduce false matches that cannot be removed from the initial matcher and thus improve the SLAM accuracy. The remaining point features are used as landmarks in SLAM, and the effectiveness of the scheme is verified through simulations with the real-world dataset.

AB - This paper proposes a point feature-based outdoor SLAM method using only omnidirectional LIDAR. 3D local occupancy grid mapping and ground plane classification are conducted as a pre-process to refine the point cloud. Then uncertain objects are clustered with Euclidean distance. For applications in rural environments, point features are utilized because clusters are extracted from unclear and overlapped objects. To improve matching performance, the similarity of clusters is calculated with a Hausdorff distance and correspondence filtering with the point histogram is implemented. With the correspondence filtering, we can reduce false matches that cannot be removed from the initial matcher and thus improve the SLAM accuracy. The remaining point features are used as landmarks in SLAM, and the effectiveness of the scheme is verified through simulations with the real-world dataset.

KW - 3D Harris corner

KW - Hausdorff distance

KW - point clouds

KW - SLAM

KW - Velodyne

UR - http://www.scopus.com/inward/record.url?scp=84962689657&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962689657&partnerID=8YFLogxK

U2 - 10.1109/URAI.2015.7358940

DO - 10.1109/URAI.2015.7358940

M3 - Conference contribution

SN - 9781467379700

SP - 218

EP - 223

BT - 2015 12th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -