Reiection detection via two view consensus

Srimal Jayawardena (RSISE)

COMPUTER VISION AND ROBOTICS SERIES PhD monitoring

DATE: 2011-10-13
TIME: 14:45:00 - 15:15:00
LOCATION: RSISE Seminar Room, ground floor, building 115, cnr. North and Daley Roads, ANU
CONTACT: JavaScript must be enabled to display this email address.

ABSTRACT:
Detecting diierent reiections on an object is useful in image analysis where reiections confuse algorithms and are treated as noise. Existing methods to detect reiections focus on spec- ular highlight removal but are not known to work well in complex scenarios like inter object reiection. The proposed method aims to detect complex reiections in images of known ob- jects. We propose to use a Markov Random Field based on a logistic classiier which uses images from two views of the object to achieve this end.

BIO: