A multiresolution spatiotemporal motion segmentation technique for video sequences based on pyramidal structures

Authors:
J. A. Rodríguez;C. Urdiales;A. Bandera;F. Sandoval
Affiliations:
Dpto. Tecnología Electrónica, ETSI Telecomunicación, Universidad de Málaga, Campus de Teatinos, 29071 Málaga, Spain;Dpto. Tecnología Electrónica, ETSI Telecomunicación, Universidad de Málaga, Campus de Teatinos, 29071 Málaga, Spain;Dpto. Tecnología Electrónica, ETSI Telecomunicación, Universidad de Málaga, Campus de Teatinos, 29071 Málaga, Spain;Dpto. Tecnología Electrónica, ETSI Telecomunicación, Universidad de Málaga, Campus de Teatinos, 29071 Málaga, Spain
Venue:
Pattern Recognition Letters
Year:
2002

Citing 5
Cited 2

An analysis of a disturbed multiresolution vision system

Pattern Recognition
A critical view of pyramid segmentation algorithms

Pattern Recognition Letters
Figure/ground separation using stochastic pyramid relinking

Pattern Recognition
Performance of optical flow techniques

International Journal of Computer Vision
Spatiotemporal MRF approach to video segmentation: application to motion detection and lip segmentation

Signal Processing

Using resolution pyramids for watershed image segmentation

Image and Vision Computing
A review of log-polar imaging for visual perception in robotics

Robotics and Autonomous Systems

Quantified Score

Hi-index	0.10

Visualization

Abstract

This paper presents a new spatiotemporal segmentation technique for video sequences. It relies on building adaptively interlinked pyramids over consecutive frames. Pyramids are interlinked to keep a relationship between the regions in the frames. Its performance is good in real-world conditions because it does not depend on image constraints.