Active Shape-from-Shadows with Controlled Illuminant Trajectories

Authors:
James J. Clark;Lei Wang
Affiliations:
Centre for Intelligent Machines, McGill University, Montreal, Quebec, Canada H3A 2A7. clark@cim.mcgill.ca;Department of Psychiatry, Washington University School of Medicine, St. Louis, MO, 63110
Venue:
International Journal of Computer Vision - Special issue: Research at McGill University
Year:
2001

Citing 5
Cited 0

Tracking with Kalman snakes

Active vision
Tracking with rigid models

Active vision
Integration, Coordination and Control of Multi-Sensor Robot Systems

Integration, Coordination and Control of Multi-Sensor Robot Systems
Data Fusion for Sensory Information Processing Systems

Data Fusion for Sensory Information Processing Systems
Recursive filtering with non-Gaussian noises

IEEE Transactions on Signal Processing

Quantified Score

Hi-index	0.01

Visualization

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.