Sciweavers

170 search results - page 3 / 34
» Identifying Foreground from Multiple Images
Sort
View
MVA
2002
186views Computer Vision» more  MVA 2002»
13 years 8 months ago
Identifying Body Parts of Multiple People in Multi-Camera Images
In order to track and recognize the movements of multiple people using multiple cameras, each person needs to be segmented and identified in the image of each camera. We propose a...
Masafumi Tominaga, Hitoshi Hongo, Hiroyasu Koshimi...
CVPR
2012
IEEE
11 years 11 months ago
Adaptive figure-ground classification
We propose an adaptive figure-ground classification algorithm to automatically extract a foreground region using a user-provided bounding-box. The image is first over-segmented wi...
Yisong Chen, Antoni B. Chan, Guoping Wang
ICCV
2001
IEEE
14 years 10 months ago
BraMBLe: A Bayesian Multiple-Blob Tracker
Blob trackers have become increasingly powerful in recent years largely due to the adoption of statistical appearance models which allow effective background subtraction and robus...
Michael Isard, John MacCormick
PAMI
2012
11 years 11 months ago
Fast Joint Estimation of Silhouettes and Dense 3D Geometry from Multiple Images
—We propose a probabilistic formulation of joint silhouette extraction and 3D reconstruction given a series of calibrated 2D images. Instead of segmenting each image separately i...
Kalin Kolev, Thomas Brox, Daniel Cremers
HUC
2010
Springer
13 years 8 months ago
Tasking networked CCTV cameras and mobile phones to identify and localize multiple people
We present a method to identify and localize people by leveraging existing CCTV camera infrastructure along with inertial sensors (accelerometer and magnetometer) within each pers...
Thiago Teixeira, Deokwoo Jung, Andreas Savvides