Sciweavers

844 search results - page 19 / 169
» From Motion Observation to Qualitative Motion Representation
Sort
View
ICPR
2008
IEEE
14 years 3 months ago
Human activity recognition from frame's spatiotemporal representation
This paper presents an approach for human activity recognition by representing the frames of the video sequence with the distribution of local motion features and their spatiotemp...
Zhipeng Zhao, Ahmed M. Elgammal
ICPR
2008
IEEE
14 years 10 months ago
Detecting global motion patterns in complex videos
Learning dominant motion patterns or activities from a video is an important surveillance problem, especially in crowded environments like markets, subways etc., where tracking of...
Min Hu, Mubarak Shah, Saad Ali
CIVR
2007
Springer
231views Image Analysis» more  CIVR 2007»
14 years 3 months ago
Classification of video events using 4-dimensional time-compressed motion features
Among the various types of semantic concepts modeled, events pose the greatest challenge in terms of computational power needed to represent the event and accuracy that can be ach...
Alexander Haubold, Milind R. Naphade
CVPR
2007
IEEE
14 years 11 months ago
A Topic-Motion Model for Unsupervised Video Object Discovery
The bag-of-words representation has attracted a lot of attention recently in the field of object recognition. Based on the bag-of-words representation, topic models such as Probab...
David Liu, Tsuhan Chen
IVC
2008
145views more  IVC 2008»
13 years 9 months ago
Camera calibration from human motion
This paper presents a method for the self-calibration of non-rigid affine structure to a Euclidean co-ordinate frame from only two views by enforcing constraints derived from the ...
Philip A. Tresadern, Ian D. Reid