Active shape-from-shadows with controlled illuminant trajectories

James J. Clark; Lei Wang

doi:10.1023/A:1011131412869

Active shape-from-shadows with controlled illuminant trajectories

James J. Clark^*, Lei Wang

^*Corresponding author for this work

Psychiatry and Behavioral Sciences

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

We present an active vision algorithm for computing the orientation and position of a locally planar object, onto which is cast a shadow of the edge of a half-plane at an unknown location. This algorithm utilises active position control of a point light source, and employs a Kalman filter to perform temporal integration of measurements. The light source position is adjusted after each measurement so as to reduce the trace of the expected state estimate error covariance matrix for the next measurement. We demonstrate the active shape-from-shadows algorithm using a real robotic system.

Original language	English (US)
Pages (from-to)	141-166
Number of pages	26
Journal	International Journal of Computer Vision
Volume	43
Issue number	3
DOIs	https://doi.org/10.1023/A:1011131412869
State	Published - Jul 2001

Funding

This research was supported in part by the U.S. National Science Foundation through grants IRI-92-23676 and CDR-85-00108, and by the Canadian Natural Sciences and Engineering Research Council.

Keywords

Active vision
Kalman filter
Shape-from-shadows

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Artificial Intelligence

Access to Document

10.1023/A:1011131412869

Cite this

@article{21d95ee74cbd4793ba1f497cc5fe8c2b,

title = "Active shape-from-shadows with controlled illuminant trajectories",

abstract = "We present an active vision algorithm for computing the orientation and position of a locally planar object, onto which is cast a shadow of the edge of a half-plane at an unknown location. This algorithm utilises active position control of a point light source, and employs a Kalman filter to perform temporal integration of measurements. The light source position is adjusted after each measurement so as to reduce the trace of the expected state estimate error covariance matrix for the next measurement. We demonstrate the active shape-from-shadows algorithm using a real robotic system.",

keywords = "Active vision, Kalman filter, Shape-from-shadows",

author = "Clark, {James J.} and Lei Wang",

note = "Funding Information: This research was supported in part by the U.S. National Science Foundation through grants IRI-92-23676 and CDR-85-00108, and by the Canadian Natural Sciences and Engineering Research Council.",

year = "2001",

month = jul,

doi = "10.1023/A:1011131412869",

language = "English (US)",

volume = "43",

pages = "141--166",

journal = "International Journal of Computer Vision",

issn = "0920-5691",

publisher = "Springer Netherlands",

number = "3",

}

TY - JOUR

T1 - Active shape-from-shadows with controlled illuminant trajectories

AU - Clark, James J.

AU - Wang, Lei

N1 - Funding Information: This research was supported in part by the U.S. National Science Foundation through grants IRI-92-23676 and CDR-85-00108, and by the Canadian Natural Sciences and Engineering Research Council.

PY - 2001/7

Y1 - 2001/7

N2 - We present an active vision algorithm for computing the orientation and position of a locally planar object, onto which is cast a shadow of the edge of a half-plane at an unknown location. This algorithm utilises active position control of a point light source, and employs a Kalman filter to perform temporal integration of measurements. The light source position is adjusted after each measurement so as to reduce the trace of the expected state estimate error covariance matrix for the next measurement. We demonstrate the active shape-from-shadows algorithm using a real robotic system.

AB - We present an active vision algorithm for computing the orientation and position of a locally planar object, onto which is cast a shadow of the edge of a half-plane at an unknown location. This algorithm utilises active position control of a point light source, and employs a Kalman filter to perform temporal integration of measurements. The light source position is adjusted after each measurement so as to reduce the trace of the expected state estimate error covariance matrix for the next measurement. We demonstrate the active shape-from-shadows algorithm using a real robotic system.

KW - Active vision

KW - Kalman filter

KW - Shape-from-shadows

UR - http://www.scopus.com/inward/record.url?scp=0035386470&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035386470&partnerID=8YFLogxK

U2 - 10.1023/A:1011131412869

DO - 10.1023/A:1011131412869

M3 - Article

AN - SCOPUS:0035386470

SN - 0920-5691

VL - 43

SP - 141

EP - 166

JO - International Journal of Computer Vision

JF - International Journal of Computer Vision

IS - 3

ER -

Active shape-from-shadows with controlled illuminant trajectories

Abstract

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this