Sciweavers

357 search results - page 33 / 72
» 3D Recognition and Segmentation of Objects in Cluttered Scen...
Sort
View
CVPR
2008
IEEE
14 years 9 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
CORR
2011
Springer
222views Education» more  CORR 2011»
12 years 11 months ago
Weakly Supervised Learning of Foreground-Background Segmentation using Masked RBMs
Abstract. We propose an extension of the Restricted Boltzmann Machine (RBM) that allows the joint shape and appearance of foreground objects in cluttered images to be modeled indep...
Nicolas Heess, Nicolas Le Roux, John M. Winn
ICPR
2008
IEEE
14 years 2 months ago
Recognition of box-like objects by fusing cues of shape and edges
Boxes are the universal choice for packing, storage, and transportation. In this paper we propose a template-based algorithm for recognition of box-like objects, which is invarian...
Chia-Chih Chen, Jake K. Aggarwal
ICCV
2005
IEEE
14 years 1 months ago
Learning Hierarchical Models of Scenes, Objects, and Parts
We describe a hierarchical probabilistic model for the detection and recognition of objects in cluttered, natural scenes. The model is based on a set of parts which describe the e...
Erik B. Sudderth, Antonio B. Torralba, William T. ...
ICPR
2000
IEEE
13 years 11 months ago
Recognition of Indoor Images Employing Qualitative Model Fitting and Supporting Relation between Objects
In this paper, we describe a new design of a recognition system for a single image of indoor scene including complex occlusions. In our system, rst, the system estimates 3D struc...
Keiji Yanai, Koichiro Deguchi