Sciweavers

486 search results - page 84 / 98
» Object Based Segmentation of Video Using Color, Motion and S...
Sort
View
CRV
2006
IEEE
176views Robotics» more  CRV 2006»
13 years 9 months ago
Stereo Retinex
The retinex algorithm for lightness and color constancy is extended to include 3-dimensional spatial information reconstructed from a stereo image. A key aspect of traditional ret...
Weihua Xiong, Brian V. Funt
ICMCS
2005
IEEE
152views Multimedia» more  ICMCS 2005»
14 years 1 months ago
Pre-Attentional Filtering in Compressed Video
We propose the use of attentional cascades based on the DCT and motion information contained in an MPEG coded stream. An attentional cascade is a sequence of very efficient class...
Juan María Sánchez, Ramon Lluis Feli...
ICMCS
2006
IEEE
189views Multimedia» more  ICMCS 2006»
14 years 1 months ago
Multiscale Edge-Based Text Extraction from Complex Images
Text that appears in images contains important and useful information. Detection and extraction of text in images have been used in many applications. In this paper, we propose a ...
Xiaoqing Liu, Jagath Samarabandu
CVPR
2008
IEEE
14 years 2 months ago
A Loopy Belief Propagation approach for robust background estimation
Background estimation, i.e. automatic recovery of the background image from a sequence of images containing moving foreground objects, is an important module in many applications,...
Xun Xu, Thomas S. Huang
ECCV
2010
Springer
14 years 24 days ago
Detecting People Using Mutually Consistent Poselet Activations
Bourdev and Malik (ICCV 09) introduced a new notion of parts, poselets, constructed to be tightly clustered both in the configuration space of keypoints, as well as in the appeara...