Sciweavers

20 search results - page 3 / 4
» A pixel-wise local information-based background subtraction ...
Sort
View
CVPR
2008
IEEE
14 years 1 months ago
Pose primitive based human action recognition in videos or still images
This paper presents a method for recognizing human actions based on pose primitives. In learning mode, the parameters representing poses and activities are estimated from videos. ...
Christian Thurau, Václav Hlavác
MVA
2007
211views Computer Vision» more  MVA 2007»
13 years 8 months ago
Shadow Elimination in Traffic Video Segmentation
Shadow detection is critical for robust and reliable vision-based systems for traffic vision analysis. Shadow points are often misclassified as object points causing errors in loc...
Hong Liu, Jintao Li, Qun Liu, Yueliang Qian
BMCBI
2010
156views more  BMCBI 2010»
13 years 7 months ago
Extended morphological processing: a practical method for automatic spot detection of biological markers from microscopic images
Background: A reliable extraction technique for resolving multiple spots in light or electron microscopic images is essential in investigations of the spatial distribution and dyn...
Yoshitaka Kimori, Norio Baba, Nobuhiro Morone
ICCV
2007
IEEE
14 years 9 months ago
Hierarchical Part-Template Matching for Human Detection and Segmentation
Local part-based human detectors are capable of handling partial occlusions efficiently and modeling shape articulations flexibly, while global shape template-based human detector...
Zhe Lin, Larry S. Davis, David S. Doermann, Daniel...
ACIVS
2007
Springer
13 years 11 months ago
Joint Domain-Range Modeling of Dynamic Scenes with Adaptive Kernel Bandwidth
Abstract. The first step in various computer vision applications is a detection of moving objects. The prevalent pixel-wise models regard image pixels as independent random process...
Borislav Antic, Vladimir S. Crnojevic