Color video segmentation by dissimilarity based on edges

Authors:
Lucía Ramos;Jorge Novo;José Rouco;Antonio Mosquera;Manuel G. Penedo
Affiliations:
VARPA Group, Department of Computer Science, University of A Coruña, Spain;VARPA Group, Department of Computer Science, University of A Coruña, Spain;VARPA Group, Department of Computer Science, University of A Coruña, Spain;Artificial Vision Group, Department of Electronics and Computer Science, University of Santiago de Compostela, Spain;VARPA Group, Department of Computer Science, University of A Coruña, Spain
Venue:
HAIS'10 Proceedings of the 5th international conference on Hybrid Artificial Intelligence Systems - Volume Part II
Year:
2010

Citing 3
Cited 0

A Computational Approach to Edge Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic Video Indexing and Full-Video Search for Object Appearances

Proceedings of the IFIP TC2/WG 2.6 Second Working Conference on Visual Database Systems II
A feature-based algorithm for detecting and classifying production effects

Multimedia Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this work new approaches are proposed to the extension to color-space of different shot change detection methods These techniques are those ones that use the dissimilarity based on edges, in particular on space and frequency domains They were previously defined to deal with grayscale videos, so the methods are redesigned to provide the best possible results in color-space videos Moreover, some improvements are performed to obtain better results, as the use of an adaptative threshold instead of the fixed one previously used Some experiments are presented to show the better behaviour of the new developed approaches.