Sciweavers

9 search results - page 1 / 2
» D - Clutter: Building object model library from unsupervised...
Sort
View
CVPR
2008
IEEE
14 years 6 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
BMVC
2010
13 years 2 months ago
Active 3D Segmentation through Fixation of Previously Unseen Objects
We present an approach for active segmentation based on integration of several cues. It serves as a framework for generation of object hypotheses of previously unseen objects in n...
Mårten Björkman, Danica Kragic
3DIM
2007
IEEE
13 years 10 months ago
Range Image Segmentation for Modeling and Object Detection in Urban Scenes
We present fast and accurate segmentation algorithms of range images of urban scenes. The utilization of these algorithms is essential as a pre-processing step for a variety of ta...
Cecilia Chao Chen, Ioannis Stamos
ICCV
2003
IEEE
14 years 6 months ago
Using Temporal Coherence to Build Models of Animals
This paper describes a system that can build appearance models of animals automatically from a video sequence of the relevant animal with no explicit supervisory information. The ...
Deva Ramanan, David A. Forsyth
ECCV
2006
Springer
13 years 8 months ago
Learning Semantic Scene Models by Trajectory Analysis
Abstract. In this paper, we describe an unsupervised learning framework to segment a scene into semantic regions and to build semantic scene models from longterm observations of mo...
Xiaogang Wang, Kinh Tieu, Eric Grimson