Sciweavers

2269 search results - page 122 / 454
» Fragmentation in the Vision of Scenes
Sort
View
ECCV
2000
Springer
16 years 8 months ago
Euclidean Group Invariant Computation of Stochastic Completion Fields Using Shiftable-Twistable Functions
We describe a method for computing the likelihood that a completion joining two contour fragments passes through any given position and orientation in the image plane, that is, a m...
John W. Zweck, Lance R. Williams
ICPR
2004
IEEE
16 years 7 months ago
Robust Detection of People in Thermal Imagery
We present a new contour analysis technique to detect people in thermal imagery. Background-subtraction is first used to identify local regions-of-interest. Gradient information w...
James W. Davis, Vinay Sharma
SIGGRAPH
1998
ACM
15 years 10 months ago
Recovering Photometric Properties of Architectural Scenes from Photographs
In this paper, we present a new approach to producing photorealistic computer renderings of real architectural scenes under novel lighting conditions, such as at different times o...
Yizhou Yu, Jitendra Malik

Publication
234views
13 years 9 months ago
Road Scene Understanding from a Single Image
Road scene segmentation is important in computer vision for different applications such as autonomous driving and pedestrian detection. Recovering the 3D structure of road scenes ...
Jose M. Alvarez, Theo Gevers, Yann LeCun, Antonio ...
CVPR
2008
IEEE
16 years 8 months ago
Kernel-based learning of cast shadows from a physical model of light sources and surfaces for low-level segmentation
In background subtraction, cast shadows induce silhouette distortions and object fusions hindering performance of high level algorithms in scene monitoring. We introduce a nonpara...
André Zaccarin, Nicolas Martel-Brisson