Sciweavers

56 search results - page 8 / 12
» Learning Object Intrinsic Structure for Robust Visual Tracki...
Sort
View
ECCV
2006
Springer
13 years 10 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
CVPR
2009
IEEE
1413views Computer Vision» more  CVPR 2009»
15 years 2 months ago
Learning Semantic Scene Models by Object Classification and Trajectory Clustering
The visual surveillance task is to monitor the activity of objects in a scene. In far-field settings (i.e., wide outdoor areas), the majority of visible activities are objects movi...
Hanqing Lu, Stan Z. Li, Tianzhu Zhang
IJSR
2010
169views more  IJSR 2010»
13 years 5 months ago
A Component-Based Approach to Visual Person Tracking from a Mobile Platform
Abstract In this article, we present a component-based visual tracker for mobile platforms with an application to person tracking. The core of the technique is a componentbased des...
Simone Frintrop, Achim Königs, Frank Hoeller,...
ECCV
2008
Springer
14 years 9 months ago
Online Tracking and Reacquisition Using Co-trained Generative and Discriminative Trackers
Visual tracking is a challenging problem, as an object may change its appearance due to viewpoint variations, illumination changes, and occlusion. Also, an object may leave the fie...
Gérard G. Medioni, Qian Yu, Thang Ba Dinh
IROS
2009
IEEE
195views Robotics» more  IROS 2009»
14 years 1 months ago
Appearance contrast for fast, robust trail-following
— We describe a framework for finding and tracking “trails” for autonomous outdoor robot navigation. Through a combination of visual cues and ladar-derived structural inform...
Christopher Rasmussen, Yan Lu, Mehmet Kocamaz