Pose estimation of human body part using multiple cameras

Kuntal Sengupta, Jun Ohya

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

Abstract

In this paper, we present a method of obtaining the approximate transformation parameter values as a starting point in estimating the pose of rigid 3D free form objects using multiple 2D images. We back project the edge silhouettes in the images, and obtain the approximate volume in the 3D space containing the object. Next, for a point selected in the volume, we hypothesize a set of points within the 3D CAD model of the object it can possibly correspond to, using the spatial extent function introduced in this paper. This is repeated for three arbitrarily chosen point in the volume. The hypothesized (match point) lists of these three points are next used to derive the pose parameter by enforcing the conditions of rigidity. Our initial experiments demonstrate the potential of this idea, and the pose parameters estimated using this method can be refined using the standard methods available in the literature.

Original languageEnglish
Title of host publicationRobot and Human Communication - Proceedings of the IEEE International Workshop
Editors Anon
Place of PublicationPiscataway, NJ, United States
PublisherIEEE
Pages146-151
Number of pages6
Publication statusPublished - 1996
Externally publishedYes
EventProceedings of the 1996 5th IEEE International Workshop on Robot and Human Communication, RO-MAN - Tsukuba, Jpn
Duration: 1996 Nov 111996 Nov 14

Other

OtherProceedings of the 1996 5th IEEE International Workshop on Robot and Human Communication, RO-MAN
CityTsukuba, Jpn
Period96/11/1196/11/14

Fingerprint

Rigidity
Computer aided design
Cameras
Experiments

ASJC Scopus subject areas

  • Hardware and Architecture
  • Software

Cite this

Sengupta, K., & Ohya, J. (1996). Pose estimation of human body part using multiple cameras. In Anon (Ed.), Robot and Human Communication - Proceedings of the IEEE International Workshop (pp. 146-151). Piscataway, NJ, United States: IEEE.

Pose estimation of human body part using multiple cameras. / Sengupta, Kuntal; Ohya, Jun.

Robot and Human Communication - Proceedings of the IEEE International Workshop. ed. / Anon. Piscataway, NJ, United States : IEEE, 1996. p. 146-151.

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

Sengupta, K & Ohya, J 1996, Pose estimation of human body part using multiple cameras. in Anon (ed.), Robot and Human Communication - Proceedings of the IEEE International Workshop. IEEE, Piscataway, NJ, United States, pp. 146-151, Proceedings of the 1996 5th IEEE International Workshop on Robot and Human Communication, RO-MAN, Tsukuba, Jpn, 96/11/11.
Sengupta K, Ohya J. Pose estimation of human body part using multiple cameras. In Anon, editor, Robot and Human Communication - Proceedings of the IEEE International Workshop. Piscataway, NJ, United States: IEEE. 1996. p. 146-151
Sengupta, Kuntal ; Ohya, Jun. / Pose estimation of human body part using multiple cameras. Robot and Human Communication - Proceedings of the IEEE International Workshop. editor / Anon. Piscataway, NJ, United States : IEEE, 1996. pp. 146-151
@inproceedings{28a146b7af0245fd8e4b49af1e117439,
title = "Pose estimation of human body part using multiple cameras",
abstract = "In this paper, we present a method of obtaining the approximate transformation parameter values as a starting point in estimating the pose of rigid 3D free form objects using multiple 2D images. We back project the edge silhouettes in the images, and obtain the approximate volume in the 3D space containing the object. Next, for a point selected in the volume, we hypothesize a set of points within the 3D CAD model of the object it can possibly correspond to, using the spatial extent function introduced in this paper. This is repeated for three arbitrarily chosen point in the volume. The hypothesized (match point) lists of these three points are next used to derive the pose parameter by enforcing the conditions of rigidity. Our initial experiments demonstrate the potential of this idea, and the pose parameters estimated using this method can be refined using the standard methods available in the literature.",
author = "Kuntal Sengupta and Jun Ohya",
year = "1996",
language = "English",
pages = "146--151",
editor = "Anon",
booktitle = "Robot and Human Communication - Proceedings of the IEEE International Workshop",
publisher = "IEEE",

}

TY - GEN

T1 - Pose estimation of human body part using multiple cameras

AU - Sengupta, Kuntal

AU - Ohya, Jun

PY - 1996

Y1 - 1996

N2 - In this paper, we present a method of obtaining the approximate transformation parameter values as a starting point in estimating the pose of rigid 3D free form objects using multiple 2D images. We back project the edge silhouettes in the images, and obtain the approximate volume in the 3D space containing the object. Next, for a point selected in the volume, we hypothesize a set of points within the 3D CAD model of the object it can possibly correspond to, using the spatial extent function introduced in this paper. This is repeated for three arbitrarily chosen point in the volume. The hypothesized (match point) lists of these three points are next used to derive the pose parameter by enforcing the conditions of rigidity. Our initial experiments demonstrate the potential of this idea, and the pose parameters estimated using this method can be refined using the standard methods available in the literature.

AB - In this paper, we present a method of obtaining the approximate transformation parameter values as a starting point in estimating the pose of rigid 3D free form objects using multiple 2D images. We back project the edge silhouettes in the images, and obtain the approximate volume in the 3D space containing the object. Next, for a point selected in the volume, we hypothesize a set of points within the 3D CAD model of the object it can possibly correspond to, using the spatial extent function introduced in this paper. This is repeated for three arbitrarily chosen point in the volume. The hypothesized (match point) lists of these three points are next used to derive the pose parameter by enforcing the conditions of rigidity. Our initial experiments demonstrate the potential of this idea, and the pose parameters estimated using this method can be refined using the standard methods available in the literature.

UR - http://www.scopus.com/inward/record.url?scp=0030396323&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030396323&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0030396323

SP - 146

EP - 151

BT - Robot and Human Communication - Proceedings of the IEEE International Workshop

A2 - Anon, null

PB - IEEE

CY - Piscataway, NJ, United States

ER -