Sciweavers

6 search results - page 1 / 2
» Energy transfer features combined with DCT for object detect...
Sort
View
TCSV
2010
12 years 11 months ago
Compressed Domain Video Object Segmentation
We propose a compressed domain video object segmentation method for MPEG or MPEG-like encoded videos. Computational superiority is the main advantage of the compressed domain proc...
Fatih Murat Porikli, Faisal I. Bashir, Huifang Sun
CVPR
2004
IEEE
13 years 8 months ago
Scale-Invariant Shape Features for Recognition of Object Categories
We introduce a new class of distinguished regions based on detecting the most salient convex local arrangements of contours in the image. The regions are used in a similar way to ...
Frédéric Jurie, Cordelia Schmid
IJNS
2007
133views more  IJNS 2007»
13 years 4 months ago
Online Learning of Objects in a Biologically Motivated Visual Architecture
We present a biologically motivated architecture for object recognition that is capable of online learning of several objects based on interaction with a human teacher. The system...
Heiko Wersing, Stephan Kirstein, Michael Gött...
ICIP
2006
IEEE
14 years 6 months ago
Multispectral Object Segmentation and Retrieval in Surveillance Video
This paper describes a system for object segmentation and feature extraction for surveillance video. Segmentation is performed by a dynamic vision system that fuses information fr...
Ciarán O. Conaire, Noel E. O'Connor, Eddie ...
IROS
2007
IEEE
162views Robotics» more  IROS 2007»
13 years 10 months ago
Where is your dive buddy: tracking humans underwater using spatio-temporal features
— We present an algorithm for underwater robots to track mobile targets, and specifically human divers, by detecting periodic motion. Periodic motion is typically associated wit...
Junaed Sattar, Gregory Dudek