Vision-based terrain analysis for planetary rover utilizing Dynamic Texture

Koki Fujita

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

Abstract

This work proposes a novel vision-based approach for classifying terrain types around a planetary rover in order to improve autonomous mobility in unknown planetary environment. The key technique of the classification scheme is an identification algorithm for a spatio-temporal texture appearing in motion image sequence, called a Dynamic Texture. It is applied to video sequences which are acquired from the rover's on-board camera. In order to decrease the computational load for estimating Dynamic Texture models with the original method called PCAID algorithm, this work proposes a method combining a system identification method called N4SID with an image compression technique called 2-Dimensional Cosine Transform (2-D DCT). Different types of terrain image sequences are recognized with measurement metrics for the estimated dynamical models. In this paper, some representative metrics are applied to synthetic image sequences, and it is discussed which one is appropriate to distinguish different terrain textures as well as the vehicle's motion paramters such as a taranslational velocity.

Original languageEnglish
Title of host publicationApplications of Space Technology for Humanity - Advances in the Astronautical Sciences: Proceedings of the 12th International Conference of Pacific-Basin Societies, ISCOPS
Pages701-712
Number of pages12
Volume138
Publication statusPublished - 2010
Event12th International Conference of Pacific-Basin Societies, ISCOPS - Montreal, QC, Canada
Duration: Jul 27 2010Jul 30 2010

Other

Other12th International Conference of Pacific-Basin Societies, ISCOPS
CountryCanada
CityMontreal, QC
Period7/27/107/30/10

Fingerprint

terrain analysis
textures
Textures
texture
planetary environments
Cosine transforms
identification method
discrete cosine transform
system identification
Image compression
classifying
Identification (control systems)
vehicles
estimating
transform
Cameras
cameras
compression
analysis

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering
  • Space and Planetary Science

Cite this

Fujita, K. (2010). Vision-based terrain analysis for planetary rover utilizing Dynamic Texture. In Applications of Space Technology for Humanity - Advances in the Astronautical Sciences: Proceedings of the 12th International Conference of Pacific-Basin Societies, ISCOPS (Vol. 138, pp. 701-712)

Vision-based terrain analysis for planetary rover utilizing Dynamic Texture. / Fujita, Koki.

Applications of Space Technology for Humanity - Advances in the Astronautical Sciences: Proceedings of the 12th International Conference of Pacific-Basin Societies, ISCOPS. Vol. 138 2010. p. 701-712.

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

Fujita, K 2010, Vision-based terrain analysis for planetary rover utilizing Dynamic Texture. in Applications of Space Technology for Humanity - Advances in the Astronautical Sciences: Proceedings of the 12th International Conference of Pacific-Basin Societies, ISCOPS. vol. 138, pp. 701-712, 12th International Conference of Pacific-Basin Societies, ISCOPS, Montreal, QC, Canada, 7/27/10.
Fujita K. Vision-based terrain analysis for planetary rover utilizing Dynamic Texture. In Applications of Space Technology for Humanity - Advances in the Astronautical Sciences: Proceedings of the 12th International Conference of Pacific-Basin Societies, ISCOPS. Vol. 138. 2010. p. 701-712
Fujita, Koki. / Vision-based terrain analysis for planetary rover utilizing Dynamic Texture. Applications of Space Technology for Humanity - Advances in the Astronautical Sciences: Proceedings of the 12th International Conference of Pacific-Basin Societies, ISCOPS. Vol. 138 2010. pp. 701-712
@inproceedings{cd6a169ccdf543f0a0f1ebc82c462022,
title = "Vision-based terrain analysis for planetary rover utilizing Dynamic Texture",
abstract = "This work proposes a novel vision-based approach for classifying terrain types around a planetary rover in order to improve autonomous mobility in unknown planetary environment. The key technique of the classification scheme is an identification algorithm for a spatio-temporal texture appearing in motion image sequence, called a Dynamic Texture. It is applied to video sequences which are acquired from the rover's on-board camera. In order to decrease the computational load for estimating Dynamic Texture models with the original method called PCAID algorithm, this work proposes a method combining a system identification method called N4SID with an image compression technique called 2-Dimensional Cosine Transform (2-D DCT). Different types of terrain image sequences are recognized with measurement metrics for the estimated dynamical models. In this paper, some representative metrics are applied to synthetic image sequences, and it is discussed which one is appropriate to distinguish different terrain textures as well as the vehicle's motion paramters such as a taranslational velocity.",
author = "Koki Fujita",
year = "2010",
language = "English",
isbn = "9780877035626",
volume = "138",
pages = "701--712",
booktitle = "Applications of Space Technology for Humanity - Advances in the Astronautical Sciences: Proceedings of the 12th International Conference of Pacific-Basin Societies, ISCOPS",

}

TY - GEN

T1 - Vision-based terrain analysis for planetary rover utilizing Dynamic Texture

AU - Fujita, Koki

PY - 2010

Y1 - 2010

N2 - This work proposes a novel vision-based approach for classifying terrain types around a planetary rover in order to improve autonomous mobility in unknown planetary environment. The key technique of the classification scheme is an identification algorithm for a spatio-temporal texture appearing in motion image sequence, called a Dynamic Texture. It is applied to video sequences which are acquired from the rover's on-board camera. In order to decrease the computational load for estimating Dynamic Texture models with the original method called PCAID algorithm, this work proposes a method combining a system identification method called N4SID with an image compression technique called 2-Dimensional Cosine Transform (2-D DCT). Different types of terrain image sequences are recognized with measurement metrics for the estimated dynamical models. In this paper, some representative metrics are applied to synthetic image sequences, and it is discussed which one is appropriate to distinguish different terrain textures as well as the vehicle's motion paramters such as a taranslational velocity.

AB - This work proposes a novel vision-based approach for classifying terrain types around a planetary rover in order to improve autonomous mobility in unknown planetary environment. The key technique of the classification scheme is an identification algorithm for a spatio-temporal texture appearing in motion image sequence, called a Dynamic Texture. It is applied to video sequences which are acquired from the rover's on-board camera. In order to decrease the computational load for estimating Dynamic Texture models with the original method called PCAID algorithm, this work proposes a method combining a system identification method called N4SID with an image compression technique called 2-Dimensional Cosine Transform (2-D DCT). Different types of terrain image sequences are recognized with measurement metrics for the estimated dynamical models. In this paper, some representative metrics are applied to synthetic image sequences, and it is discussed which one is appropriate to distinguish different terrain textures as well as the vehicle's motion paramters such as a taranslational velocity.

UR - http://www.scopus.com/inward/record.url?scp=80053395119&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053395119&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:80053395119

SN - 9780877035626

VL - 138

SP - 701

EP - 712

BT - Applications of Space Technology for Humanity - Advances in the Astronautical Sciences: Proceedings of the 12th International Conference of Pacific-Basin Societies, ISCOPS

ER -