Sciweavers

Share
WACV
2005
IEEE
9 years 5 months ago
Persistent Objects Tracking Across Multiple Non Overlapping Cameras
We present an approach for persistent tracking of moving objects observed by non-overlapping and moving cameras. Our approach robustly recovers the geometry of non-overlapping vie...
Jinman Kang, Isaac Cohen, Gérard G. Medioni
WACV
2005
IEEE
9 years 5 months ago
Requirements for Camera Calibration: Must Accuracy Come with a High Price?
While a large number of vision applications rely on the mapping between 3D scenes and their corresponding 2D camera images, the question that occurs to most researchers is what, i...
Wei Sun, Jeremy R. Cooperstock
WACV
2005
IEEE
9 years 5 months ago
Image Segmentation by Unsupervised Sparse Clustering
In this paper, we present a novel solution of image segmentation based on positiveness by regarding the segmentation as one of the graph-theoretic clustering problems. On the cont...
Byoung-Ki Jeon, Yun-Beom Jung, Ki-Sang Hong
WACV
2005
IEEE
9 years 5 months ago
Using Co-Occurrence and Segmentation to Learn Feature-Based Object Models from Video
A number of recent systems for unsupervised featurebased learning of object models take advantage of cooccurrence: broadly, they search for clusters of discriminative features tha...
Thomas S. Stepleton, Tai Sing Lee
WACV
2005
IEEE
9 years 5 months ago
Incorporating Background Invariance into Feature-Based Object Recognition
Current feature-based object recognition methods use information derived from local image patches. For robustness, features are engineered for invariance to various transformation...
Andrew N. Stein, Martial Hebert
WACV
2005
IEEE
9 years 5 months ago
Learning to Track Objects Through Unobserved Regions
As tracking systems become more effective at reliably tracking multiple objects over extended periods of time within single camera views and across overlapping camera views, incre...
Chris Stauffer
WACV
2005
IEEE
9 years 5 months ago
Incorporating Object Tracking Feedback into Background Maintenance Framework
Adaptive background modeling/subtraction techniques are popular, in particular, because they are able to cope with background variations that are due to lighting variations. Unfor...
Leonid Taycher, John W. Fisher III, Trevor Darrell
WACV
2005
IEEE
9 years 5 months ago
Isomap and Nonparametric Models of Image Deformation
Isomap is an exemplar of a set of data driven nonlinear dimensionality reduction techniques that have shown promise for the analysis of images and video. These methods parameteriz...
Richard Souvenir, Robert Pless
WACV
2005
IEEE
9 years 5 months ago
Joint Key-Frame Extraction and Object-Based Video Segmentation
In this paper, we propose a coherent framework for joint key-frame extraction and object-based video segmentation. Conventional key-frame extraction and object segmentation are us...
Xiaomu Song, Guoliang Fan
books