Visualization and Intelligent Systems Laboratory
VISLab

 

 

Contact Information

VISLab
Winston Chung Hall Room 216
University of California, Riverside
900 University Avenue
Riverside, CA 92521-0425


Tel: (951)-827-3954

CRIS
Bourns College of Engineering
UCR
NSF IGERT on Video Bioinformatics

UCR Collaborators:
CSE
ECE
ME
STAT
PSYC
ENTM
BIOL
BPSC
ECON
MATH
BIOENG
MGNT

Other Collaborators:
Keio University

Other Activities:
IEEE Biometrics Workshop 2014
IEEE Biometrics Workshop 2013
Worshop on DVSN 2009
Multibiometrics Book

Webmaster Contact Information:
Alex Shin
wshin@ece.ucr.edu

Last updated: July 1, 2017

 

 

Performance Prediction for Model-based Object Recognition

Presented by: Xiaobing Qian

ABSTRACT: In this presentation, I will introduce the approach to predict the probability of correct recognition for model-based, point-based object recognition. The method considers data distortion factors such as perturbation, occlusion, and clutter. Performance is predicted in two stages. In the first stage, the PDF of the vote between each pair of views in the database is computed out. In the second stage, the PDF is used to predict the lower/upper bound of PCR or itself. The validity of our predictions is demonstrated by the experiment on synthetic SAR data.