ICP stereo visual odometry for wheeled vehicles based on a 1DOF motion prior
In this paper, we propose a novel, efficient stereo visual-odometry algorithm for ground vehicles moving in outdoor environments. To avoid the drawbacks of computationally-expensive outlier-removal steps based on random-sample schemes, we use a single-degree-of-freedom kinematic model of the vehicle...
Main Authors: | , , , |
---|---|
Format: | Conference Object |
Language: | English |
Published: |
Institute of Electrical and Electronics Engineers
2014
|
Subjects: | |
Online Access: | https://www.zora.uzh.ch/id/eprint/125456/ https://www.zora.uzh.ch/id/eprint/125456/1/ICRA14_Jiang.pdf https://doi.org/10.5167/uzh-125456 https://doi.org/10.1109/ICRA.2014.6906914 |
id |
ftunivzuerich:oai:www.zora.uzh.ch:125456 |
---|---|
record_format |
openpolar |
spelling |
ftunivzuerich:oai:www.zora.uzh.ch:125456 2023-05-15T16:00:47+02:00 ICP stereo visual odometry for wheeled vehicles based on a 1DOF motion prior Jiang, Yanhua Chen, Huiyan Xiong, Guangming Scaramuzza, Davide 2014-06-07 application/pdf https://www.zora.uzh.ch/id/eprint/125456/ https://www.zora.uzh.ch/id/eprint/125456/1/ICRA14_Jiang.pdf https://doi.org/10.5167/uzh-125456 https://doi.org/10.1109/ICRA.2014.6906914 eng eng Institute of Electrical and Electronics Engineers https://www.zora.uzh.ch/id/eprint/125456/1/ICRA14_Jiang.pdf doi:10.5167/uzh-125456 doi:10.1109/ICRA.2014.6906914 urn:issn:1050-4729 info:eu-repo/semantics/openAccess Jiang, Yanhua; Chen, Huiyan; Xiong, Guangming; Scaramuzza, Davide (2014). ICP stereo visual odometry for wheeled vehicles based on a 1DOF motion prior. In: IEEE International Conference on Robotics and Automation (ICRA), Hong Kong, 31 May 2014 - 7 June 2014, Institute of Electrical and Electronics Engineers. Department of Informatics 000 Computer science knowledge & systems Conference or Workshop Item PeerReviewed info:eu-repo/semantics/conferenceObject info:eu-repo/semantics/acceptedVersion 2014 ftunivzuerich https://doi.org/10.5167/uzh-125456 https://doi.org/10.1109/ICRA.2014.6906914 2022-11-29T21:35:53Z In this paper, we propose a novel, efficient stereo visual-odometry algorithm for ground vehicles moving in outdoor environments. To avoid the drawbacks of computationally-expensive outlier-removal steps based on random-sample schemes, we use a single-degree-of-freedom kinematic model of the vehicle to initialize an Iterative Closest Point (ICP) algorithm that is utilized to select high-quality inliers. The motion is then computed incrementally from the inliers using a standard linear 3D-to-2D pose-estimation method without any additional batch optimization. The performance of the approach is evaluated against state-of-the-art methods on both synthetic data and publicly-available datasets (e.g., KITTI and Devon Island) collected over several kilometers in both urban environments and challenging off-road terrains. Experiments show that the our algorithm outperforms state-of-the-art approaches in accuracy, runtime, and ease of implementation. Conference Object Devon Island University of Zurich (UZH): ZORA (Zurich Open Repository and Archive Devon Island ENVELOPE(-88.000,-88.000,75.252,75.252) |
institution |
Open Polar |
collection |
University of Zurich (UZH): ZORA (Zurich Open Repository and Archive |
op_collection_id |
ftunivzuerich |
language |
English |
topic |
Department of Informatics 000 Computer science knowledge & systems |
spellingShingle |
Department of Informatics 000 Computer science knowledge & systems Jiang, Yanhua Chen, Huiyan Xiong, Guangming Scaramuzza, Davide ICP stereo visual odometry for wheeled vehicles based on a 1DOF motion prior |
topic_facet |
Department of Informatics 000 Computer science knowledge & systems |
description |
In this paper, we propose a novel, efficient stereo visual-odometry algorithm for ground vehicles moving in outdoor environments. To avoid the drawbacks of computationally-expensive outlier-removal steps based on random-sample schemes, we use a single-degree-of-freedom kinematic model of the vehicle to initialize an Iterative Closest Point (ICP) algorithm that is utilized to select high-quality inliers. The motion is then computed incrementally from the inliers using a standard linear 3D-to-2D pose-estimation method without any additional batch optimization. The performance of the approach is evaluated against state-of-the-art methods on both synthetic data and publicly-available datasets (e.g., KITTI and Devon Island) collected over several kilometers in both urban environments and challenging off-road terrains. Experiments show that the our algorithm outperforms state-of-the-art approaches in accuracy, runtime, and ease of implementation. |
format |
Conference Object |
author |
Jiang, Yanhua Chen, Huiyan Xiong, Guangming Scaramuzza, Davide |
author_facet |
Jiang, Yanhua Chen, Huiyan Xiong, Guangming Scaramuzza, Davide |
author_sort |
Jiang, Yanhua |
title |
ICP stereo visual odometry for wheeled vehicles based on a 1DOF motion prior |
title_short |
ICP stereo visual odometry for wheeled vehicles based on a 1DOF motion prior |
title_full |
ICP stereo visual odometry for wheeled vehicles based on a 1DOF motion prior |
title_fullStr |
ICP stereo visual odometry for wheeled vehicles based on a 1DOF motion prior |
title_full_unstemmed |
ICP stereo visual odometry for wheeled vehicles based on a 1DOF motion prior |
title_sort |
icp stereo visual odometry for wheeled vehicles based on a 1dof motion prior |
publisher |
Institute of Electrical and Electronics Engineers |
publishDate |
2014 |
url |
https://www.zora.uzh.ch/id/eprint/125456/ https://www.zora.uzh.ch/id/eprint/125456/1/ICRA14_Jiang.pdf https://doi.org/10.5167/uzh-125456 https://doi.org/10.1109/ICRA.2014.6906914 |
long_lat |
ENVELOPE(-88.000,-88.000,75.252,75.252) |
geographic |
Devon Island |
geographic_facet |
Devon Island |
genre |
Devon Island |
genre_facet |
Devon Island |
op_source |
Jiang, Yanhua; Chen, Huiyan; Xiong, Guangming; Scaramuzza, Davide (2014). ICP stereo visual odometry for wheeled vehicles based on a 1DOF motion prior. In: IEEE International Conference on Robotics and Automation (ICRA), Hong Kong, 31 May 2014 - 7 June 2014, Institute of Electrical and Electronics Engineers. |
op_relation |
https://www.zora.uzh.ch/id/eprint/125456/1/ICRA14_Jiang.pdf doi:10.5167/uzh-125456 doi:10.1109/ICRA.2014.6906914 urn:issn:1050-4729 |
op_rights |
info:eu-repo/semantics/openAccess |
op_doi |
https://doi.org/10.5167/uzh-125456 https://doi.org/10.1109/ICRA.2014.6906914 |
_version_ |
1766396797225271296 |