Sciweavers

970 search results - page 135 / 194
» Generation of Semantic Regions from Image Sequences
Sort
View
CVPR
2005
IEEE
16 years 8 months ago
Dynamosaics: Video Mosaics with Non-Chronological Time
With the limited field of view of human vision, our perception of most scenes is built over time while our eyes are scanning the scene. In the case of static scenes this process c...
Alex Rav-Acha, Yael Pritch, Dani Lischinski, Shmue...
MVA
2002
186views Computer Vision» more  MVA 2002»
15 years 6 months ago
Identifying Body Parts of Multiple People in Multi-Camera Images
In order to track and recognize the movements of multiple people using multiple cameras, each person needs to be segmented and identified in the image of each camera. We propose a...
Masafumi Tominaga, Hitoshi Hongo, Hiroyasu Koshimi...
CIVR
2004
Springer
166views Image Analysis» more  CIVR 2004»
15 years 11 months ago
Object Segmentation and Ontologies for MPEG-2 Video Indexing and Retrieval
Abstract. A novel approach to object-based video indexing and retrieval is presented, employing an object segmentation algorithm for the real-time, unsupervised segmentation of com...
Vasileios Mezaris, Michael G. Strintzis
MM
2000
ACM
515views Multimedia» more  MM 2000»
15 years 10 months ago
Efficient use of local edge histogram descriptor
The purpose of this paper is to show how the edge histogram descriptor for MPEG-7 can be efficiently utilized for image matching. Since the edge histogram descriptor recommended f...
Dong Kwon Park, Yoon Seok Jeon, Chee Sun Won
WSCG
2004
232views more  WSCG 2004»
15 years 7 months ago
Robust Tracking of Athletes Using Multiple Features of Multiple Views
This paper presents a robust and reconfigurable object tracker that integrates multiple visual features from multiple views. The tandem modular architecture stepwise refines the e...
Toshihiko Misu, Seiichi Gohshi, Yoshinori Izumi, Y...