2D/3D Registration of 3D Models using a Single 2D Image
Srimal Jayawardena (SoCS CECS)
CS HDR MONITORING AI Research GroupDATE: 2010-04-16
TIME: 14:00:00 - 14:30:00
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:
The problem of identifying the 3D pose of a known object from a given 2D image has important applications in Computer Vision.
These range from robotic vision to image analysis. A detailed pose estimate is particularly necessary for assessing vehicle damage using a photograph of the damaged vehicle. The proposed method uses a 3D model of the known object to estimate a very accurate pose from a 2D image. It requires only a single 2D image and does not use any explicit point correspondences. Very accurate pose estimates have been generated for artificial and semi-artificial images.
BIO:
PhD student in Computer Science.
