Depth map from the combination of matched points with active contours

Elisa Martinez, Carme Torras

Research output: A Conference proceeding or a Chapter in BookConference contribution

1 Citation (Scopus)

Abstract

This paper describes the analysis of an active contour fitted to a target in a sequence of images recorded by a freely moving uncalibrated camera. The motivating application is the visual guidance of a robot towards a target. Contour deformations are analysed to extract the scaled depth of the target, and to explore the feasibility of 3D egomotion recovery. The scaled depth is used to compute the time to contact, which provides a measure of distance to the target, and also to improve the common depth maps obtained from point matches, which are a valuable input for the robot to avoid obstacles.

Original languageEnglish
Title of host publicationIEEE Intelligent Vehicles Symposium, Proceedings
PublisherIEEE
Pages332-337
Number of pages6
ISBN (Print)9780780363639
DOIs
Publication statusPublished - 2000
Externally publishedYes
Event2000 IEEE Intelligent Vehicles Symposium - The Ritz-Carlton Hotel, Dearborn, United States
Duration: 5 Oct 20005 Oct 2000

Conference

Conference2000 IEEE Intelligent Vehicles Symposium
Abbreviated titleIV 2000
CountryUnited States
CityDearborn
Period5/10/005/10/00

Fingerprint

Robots
Cameras
Recovery

Cite this

Martinez, E., & Torras, C. (2000). Depth map from the combination of matched points with active contours. In IEEE Intelligent Vehicles Symposium, Proceedings (pp. 332-337). IEEE. https://doi.org/10.1109/IVS.2000.898364
Martinez, Elisa ; Torras, Carme. / Depth map from the combination of matched points with active contours. IEEE Intelligent Vehicles Symposium, Proceedings. IEEE, 2000. pp. 332-337
@inproceedings{615c410c14284c169e97ee74f46a9b6c,
title = "Depth map from the combination of matched points with active contours",
abstract = "This paper describes the analysis of an active contour fitted to a target in a sequence of images recorded by a freely moving uncalibrated camera. The motivating application is the visual guidance of a robot towards a target. Contour deformations are analysed to extract the scaled depth of the target, and to explore the feasibility of 3D egomotion recovery. The scaled depth is used to compute the time to contact, which provides a measure of distance to the target, and also to improve the common depth maps obtained from point matches, which are a valuable input for the robot to avoid obstacles.",
keywords = "depth map, Active contours",
author = "Elisa Martinez and Carme Torras",
year = "2000",
doi = "10.1109/IVS.2000.898364",
language = "English",
isbn = "9780780363639",
pages = "332--337",
booktitle = "IEEE Intelligent Vehicles Symposium, Proceedings",
publisher = "IEEE",

}

Martinez, E & Torras, C 2000, Depth map from the combination of matched points with active contours. in IEEE Intelligent Vehicles Symposium, Proceedings. IEEE, pp. 332-337, 2000 IEEE Intelligent Vehicles Symposium, Dearborn, United States, 5/10/00. https://doi.org/10.1109/IVS.2000.898364

Depth map from the combination of matched points with active contours. / Martinez, Elisa; Torras, Carme.

IEEE Intelligent Vehicles Symposium, Proceedings. IEEE, 2000. p. 332-337.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Depth map from the combination of matched points with active contours

AU - Martinez, Elisa

AU - Torras, Carme

PY - 2000

Y1 - 2000

N2 - This paper describes the analysis of an active contour fitted to a target in a sequence of images recorded by a freely moving uncalibrated camera. The motivating application is the visual guidance of a robot towards a target. Contour deformations are analysed to extract the scaled depth of the target, and to explore the feasibility of 3D egomotion recovery. The scaled depth is used to compute the time to contact, which provides a measure of distance to the target, and also to improve the common depth maps obtained from point matches, which are a valuable input for the robot to avoid obstacles.

AB - This paper describes the analysis of an active contour fitted to a target in a sequence of images recorded by a freely moving uncalibrated camera. The motivating application is the visual guidance of a robot towards a target. Contour deformations are analysed to extract the scaled depth of the target, and to explore the feasibility of 3D egomotion recovery. The scaled depth is used to compute the time to contact, which provides a measure of distance to the target, and also to improve the common depth maps obtained from point matches, which are a valuable input for the robot to avoid obstacles.

KW - depth map

KW - Active contours

UR - http://www.scopus.com/inward/record.url?scp=0034476489&partnerID=8YFLogxK

U2 - 10.1109/IVS.2000.898364

DO - 10.1109/IVS.2000.898364

M3 - Conference contribution

SN - 9780780363639

SP - 332

EP - 337

BT - IEEE Intelligent Vehicles Symposium, Proceedings

PB - IEEE

ER -

Martinez E, Torras C. Depth map from the combination of matched points with active contours. In IEEE Intelligent Vehicles Symposium, Proceedings. IEEE. 2000. p. 332-337 https://doi.org/10.1109/IVS.2000.898364