Sciweavers

568 search results - page 56 / 114
» Saccadic Object Recognition with an Active Vision System
Sort
View
CVPR
2012
IEEE
13 years 5 days ago
Teaching 3D geometry to deformable part models
Current object class recognition systems typically target 2D bounding box localization, encouraged by benchmark data sets, such as Pascal VOC. While this seems suitable for the de...
Bojan Pepik, Michael Stark, Peter V. Gehler, Bernt...
HUMO
2007
Springer
15 years 3 months ago
Recognizing Activities with Multiple Cues
In this paper, we introduce a first-order probabilistic model that combines multiple cues to classify human activities from video data accurately and robustly. Our system works in...
Rahul Biswas, Sebastian Thrun, Kikuo Fujimura
ECCV
2008
Springer
15 years 11 months ago
Scale Invariant Action Recognition Using Compound Features Mined from Dense Spatio-temporal Corners
Abstract. The use of sparse invariant features to recognise classes of actions or objects has become common in the literature. However, features are often "engineered" to...
Andrew Gilbert, John Illingworth, Richard Bowden
CVPR
1998
IEEE
15 years 11 months ago
Using Adaptive Tracking to Classify and Monitor Activities in a Site
We describe a vision system that monitors activity in a site over extended periods of time. The system uses a distributed set of sensors to cover the site, and an adaptive tracker...
W. Eric L. Grimson, Chris Stauffer, R. Romano, L. ...
IROS
2009
IEEE
304views Robotics» more  IROS 2009»
15 years 4 months ago
Real time tracking using an active pan-tilt-zoom network camera
— We present here a real time active vision system on a PTZ network camera to track an object of interest. We address two critical issues in this paper. One is the control of the...
Thang Ba Dinh, Qian Yu, Gérard G. Medioni