Efficient multiple independent motion segmentation from an active platform by utilizing modified RANSAC

Yingdi Xie; Jun Ohya

Efficient multiple independent motion segmentation from an active platform by utilizing modified RANSAC

Yingdi Xie^*, Jun Ohya

^*Corresponding author for this work

School of Creative Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

In this paper, an efficient approach to segmentation of different independent motion areas from a moving platform is described. This approach is implemented on a stereo vision system, depth information could be computed by matching feature points between stereo images. For two consecutive frames, ego-motion is estimated from the optical flows, including depth information belonging to the background, which has a larger space distribution comparing to those of independent moving objects. In order to distinguish different motion areas, we proposed a modified version of RANSAC mechanism, which could handle the problem of multiple model extraction in a noisy environment.

Original language	English
Title of host publication	Proceedings of the IASTED International Conference on Graphics and Visualization in Engineering, GVE 2007
Pages	31-36
Number of pages	6
Publication status	Published - 2007 Dec 1
Event	2007 IASTED International Conference on Graphics and Visualization in Engineering, GVE 2008 - Clearwater, FL, United States Duration: 2007 Jan 3 → 2007 Jan 5

Publication series

Name	Proceedings of the IASTED International Conference on Graphics and Visualization in Engineering, GVE 2007

Conference

Conference	2007 IASTED International Conference on Graphics and Visualization in Engineering, GVE 2008
Country/Territory	United States
City	Clearwater, FL
Period	07/1/3 → 07/1/5

Keywords

Modified RANSAC
Motion segmentation

ASJC Scopus subject areas

Computer Graphics and Computer-Aided Design
Computer Vision and Pattern Recognition

Cite this

Efficient multiple independent motion segmentation from an active platform by utilizing modified RANSAC. / Xie, Yingdi; Ohya, Jun.
Proceedings of the IASTED International Conference on Graphics and Visualization in Engineering, GVE 2007. 2007. p. 31-36 (Proceedings of the IASTED International Conference on Graphics and Visualization in Engineering, GVE 2007).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Xie, Y & Ohya, J 2007, Efficient multiple independent motion segmentation from an active platform by utilizing modified RANSAC. in Proceedings of the IASTED International Conference on Graphics and Visualization in Engineering, GVE 2007. Proceedings of the IASTED International Conference on Graphics and Visualization in Engineering, GVE 2007, pp. 31-36, 2007 IASTED International Conference on Graphics and Visualization in Engineering, GVE 2008, Clearwater, FL, United States, 07/1/3.

@inproceedings{0cae3ce5ad3049f485f715dd5820392a,

title = "Efficient multiple independent motion segmentation from an active platform by utilizing modified RANSAC",

abstract = "In this paper, an efficient approach to segmentation of different independent motion areas from a moving platform is described. This approach is implemented on a stereo vision system, depth information could be computed by matching feature points between stereo images. For two consecutive frames, ego-motion is estimated from the optical flows, including depth information belonging to the background, which has a larger space distribution comparing to those of independent moving objects. In order to distinguish different motion areas, we proposed a modified version of RANSAC mechanism, which could handle the problem of multiple model extraction in a noisy environment.",

keywords = "Modified RANSAC, Motion segmentation",

author = "Yingdi Xie and Jun Ohya",

year = "2007",

month = dec,

day = "1",

language = "English",

isbn = "9780889866256",

series = "Proceedings of the IASTED International Conference on Graphics and Visualization in Engineering, GVE 2007",

pages = "31--36",

booktitle = "Proceedings of the IASTED International Conference on Graphics and Visualization in Engineering, GVE 2007",

note = "2007 IASTED International Conference on Graphics and Visualization in Engineering, GVE 2008 ; Conference date: 03-01-2007 Through 05-01-2007",

}

TY - GEN

T1 - Efficient multiple independent motion segmentation from an active platform by utilizing modified RANSAC

AU - Xie, Yingdi

AU - Ohya, Jun

PY - 2007/12/1

Y1 - 2007/12/1

N2 - In this paper, an efficient approach to segmentation of different independent motion areas from a moving platform is described. This approach is implemented on a stereo vision system, depth information could be computed by matching feature points between stereo images. For two consecutive frames, ego-motion is estimated from the optical flows, including depth information belonging to the background, which has a larger space distribution comparing to those of independent moving objects. In order to distinguish different motion areas, we proposed a modified version of RANSAC mechanism, which could handle the problem of multiple model extraction in a noisy environment.

AB - In this paper, an efficient approach to segmentation of different independent motion areas from a moving platform is described. This approach is implemented on a stereo vision system, depth information could be computed by matching feature points between stereo images. For two consecutive frames, ego-motion is estimated from the optical flows, including depth information belonging to the background, which has a larger space distribution comparing to those of independent moving objects. In order to distinguish different motion areas, we proposed a modified version of RANSAC mechanism, which could handle the problem of multiple model extraction in a noisy environment.

KW - Modified RANSAC

KW - Motion segmentation

UR - http://www.scopus.com/inward/record.url?scp=54949119126&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=54949119126&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:54949119126

SN - 9780889866256

T3 - Proceedings of the IASTED International Conference on Graphics and Visualization in Engineering, GVE 2007

SP - 31

EP - 36

BT - Proceedings of the IASTED International Conference on Graphics and Visualization in Engineering, GVE 2007

T2 - 2007 IASTED International Conference on Graphics and Visualization in Engineering, GVE 2008

Y2 - 3 January 2007 through 5 January 2007

ER -

Efficient multiple independent motion segmentation from an active platform by utilizing modified RANSAC

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this