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

 

 

Video Object Segmentation and Tracking Based on Feature Localization

Presented by: Xaotao Zou

ABSTRACT: The essential part is the introduction of a new concept "Locales" in segmenting and tracking objects in videos. A Video Locale is a sequence of image(frame) feature locales that share similar features (e.g. Color, Texture, shape and motion etc) in the spatio-temporal domain. Image feature locales are grown from tiles (blocks of pixels) which can be non-disjoint and non-conected, and is followed by unforced probabilitic pyramid-linking methods for locale-growing. After intra-frame locales generation, the similar but simplified inter-frame locales generation and motion estimation would be executed for following frames. Instead of the regions and tracked regions in classical object segmentation, the frame(image) locales and video locales are detected for object tracking in videos.