Sciweavers

69 search results - page 5 / 14
» Building Detection and Description from a Single Intensity I...
Sort
View
DAGM
2008
Springer
14 years 11 months ago
Learning Visual Compound Models from Parallel Image-Text Datasets
Abstract. In this paper, we propose a new approach to learn structured visual compound models from shape-based feature descriptions. We use captioned text in order to drive the pro...
Jan Moringen, Sven Wachsmuth, Sven J. Dickinson, S...
ICIP
2008
IEEE
15 years 3 months ago
Recaptured photo detection using specularity distribution
Detection of planar surfaces in a generic scene is difficult when the illumination is complex and less intense, and the surfaces have non-uniform colors (e.g., a movie poster). A...
Hang Yu, Tian-Tsong Ng, Qibin Sun
MVA
1996
118views Computer Vision» more  MVA 1996»
14 years 10 months ago
Correlation-Based Visual Tracking Enhanced by Affine Motion Description
Since conventional correlation-based visual tracking algorithms are based on a single reference block, they often fail to track a target in the following situations: 1) a view of ...
Yoshihisa Adachi, Minoru Asada, Takayuki Nakamura
ISVC
2009
Springer
15 years 3 months ago
Real-Time Articulated Hand Detection and Pose Estimation
We propose a novel method for planar hand detection from a single uncalibrated image, with the purpose of estimating the articulated pose of a generic model, roughly adapted to the...
Giorgio Panin, Sebastian Klose, Alois Knoll
CVIU
2010
267views more  CVIU 2010»
14 years 6 months ago
Accelerated hardware video object segmentation: From foreground detection to connected components labelling
This paper demonstrates the use of a single-chip FPGA for the segmentation of moving objects in a video sequence. The system maintains highly accurate background models, and integ...
Kofi Appiah, Andrew Hunter, Patrick Dickinson, Hon...