Vision-based approach to obstacle avoidance

Yoko Watanabe, Eric Johnson, Anthony J. Calise

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

17 Citations (Scopus)

Abstract

This paper describes a 3D obstacle modeling system which uses a 2D vision sensor. Prior work tracks feature points in a sequence of images and estimates their positions. However, in this paper we use obstacle edges instead. Using an image segmentation technique, edges are detected as line segments. Subsequently, these edges are modeled in a 3D space from the measured line segments using known camera motions. The z-test method is used for corresponding estimated line data with measurements. Line addition and deletion algorithms are also explained. Simulation results show that simple structures are accurately modeled by the suggested line-based estimator. Finally, this method is applied to a 3D terrain mapping problem.

Original languageEnglish (US)
Title of host publicationCollection of Technical Papers - AIAA Guidance, Navigation, and Control Conference 2005
Pages2600-2609
Number of pages10
Volume4
StatePublished - Dec 1 2005
EventAIAA Guidance, Navigation, and Control Conference 2005 - San Francisco, CA, United States
Duration: Aug 15 2005Aug 18 2005

Other

OtherAIAA Guidance, Navigation, and Control Conference 2005
CountryUnited States
CitySan Francisco, CA
Period8/15/058/18/05

Fingerprint

Collision avoidance
Image segmentation
Cameras
Sensors

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Watanabe, Y., Johnson, E., & Calise, A. J. (2005). Vision-based approach to obstacle avoidance. In Collection of Technical Papers - AIAA Guidance, Navigation, and Control Conference 2005 (Vol. 4, pp. 2600-2609)
Watanabe, Yoko ; Johnson, Eric ; Calise, Anthony J. / Vision-based approach to obstacle avoidance. Collection of Technical Papers - AIAA Guidance, Navigation, and Control Conference 2005. Vol. 4 2005. pp. 2600-2609
@inproceedings{b4a5e5d3e70143bf8d1583d3520ab297,
title = "Vision-based approach to obstacle avoidance",
abstract = "This paper describes a 3D obstacle modeling system which uses a 2D vision sensor. Prior work tracks feature points in a sequence of images and estimates their positions. However, in this paper we use obstacle edges instead. Using an image segmentation technique, edges are detected as line segments. Subsequently, these edges are modeled in a 3D space from the measured line segments using known camera motions. The z-test method is used for corresponding estimated line data with measurements. Line addition and deletion algorithms are also explained. Simulation results show that simple structures are accurately modeled by the suggested line-based estimator. Finally, this method is applied to a 3D terrain mapping problem.",
author = "Yoko Watanabe and Eric Johnson and Calise, {Anthony J.}",
year = "2005",
month = "12",
day = "1",
language = "English (US)",
isbn = "1563477378",
volume = "4",
pages = "2600--2609",
booktitle = "Collection of Technical Papers - AIAA Guidance, Navigation, and Control Conference 2005",

}

Watanabe, Y, Johnson, E & Calise, AJ 2005, Vision-based approach to obstacle avoidance. in Collection of Technical Papers - AIAA Guidance, Navigation, and Control Conference 2005. vol. 4, pp. 2600-2609, AIAA Guidance, Navigation, and Control Conference 2005, San Francisco, CA, United States, 8/15/05.

Vision-based approach to obstacle avoidance. / Watanabe, Yoko; Johnson, Eric; Calise, Anthony J.

Collection of Technical Papers - AIAA Guidance, Navigation, and Control Conference 2005. Vol. 4 2005. p. 2600-2609.

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

TY - GEN

T1 - Vision-based approach to obstacle avoidance

AU - Watanabe, Yoko

AU - Johnson, Eric

AU - Calise, Anthony J.

PY - 2005/12/1

Y1 - 2005/12/1

N2 - This paper describes a 3D obstacle modeling system which uses a 2D vision sensor. Prior work tracks feature points in a sequence of images and estimates their positions. However, in this paper we use obstacle edges instead. Using an image segmentation technique, edges are detected as line segments. Subsequently, these edges are modeled in a 3D space from the measured line segments using known camera motions. The z-test method is used for corresponding estimated line data with measurements. Line addition and deletion algorithms are also explained. Simulation results show that simple structures are accurately modeled by the suggested line-based estimator. Finally, this method is applied to a 3D terrain mapping problem.

AB - This paper describes a 3D obstacle modeling system which uses a 2D vision sensor. Prior work tracks feature points in a sequence of images and estimates their positions. However, in this paper we use obstacle edges instead. Using an image segmentation technique, edges are detected as line segments. Subsequently, these edges are modeled in a 3D space from the measured line segments using known camera motions. The z-test method is used for corresponding estimated line data with measurements. Line addition and deletion algorithms are also explained. Simulation results show that simple structures are accurately modeled by the suggested line-based estimator. Finally, this method is applied to a 3D terrain mapping problem.

UR - http://www.scopus.com/inward/record.url?scp=29744437776&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=29744437776&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:29744437776

SN - 1563477378

SN - 9781563477379

VL - 4

SP - 2600

EP - 2609

BT - Collection of Technical Papers - AIAA Guidance, Navigation, and Control Conference 2005

ER -

Watanabe Y, Johnson E, Calise AJ. Vision-based approach to obstacle avoidance. In Collection of Technical Papers - AIAA Guidance, Navigation, and Control Conference 2005. Vol. 4. 2005. p. 2600-2609