Detection of moving objects in video sequences by the computation of optical flow based on region growing

Authors:
A. Kravchonok
Affiliations:
United Institute of Informatics Problems, National Academy of Sciences of Belarus, Minsk, Belarus
Venue:
Pattern Recognition and Image Analysis
Year:
2011

Citing 5
Cited 0

Performance of optical flow techniques

International Journal of Computer Vision
Development of a video-rate stereo machine

IROS '95 Proceedings of the International Conference on Intelligent Robots and Systems-Volume 3 - Volume 3
Robust Salient Motion Detection with Complex Background for Real-Time Video Surveillance

WACV-MOTION '05 Proceedings of the IEEE Workshop on Motion and Video Computing (WACV/MOTION'05) - Volume 2 - Volume 02
Fuzzy pushdown automata

Fuzzy Sets and Systems
A Contour-Based Moving Object Detection and Tracking

ICCCN '05 Proceedings of the 14th International Conference on Computer Communications and Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

An algorithm of fast detection of optical flow on the basis of region growing is offered computing the optical flow only for moving objects and not affecting fixed image areas. The algorithm uses a marquee and SSE2/SSE3 instructions to make the computations considerably faster, has linear complexity depending on the size of the optical flow window, and can be applied in real-time mode to detect and track moving objects in video sequences while partially filling the frames with moving objects.