Video Segmentation Descriptors for Event Recognition

This paper presents a new video motion descriptor based on a multi-scale video segmentation to provide a multi-layered output as well as connections with the rich interactions that occur between objects at the semantic level. We also put the emphasis on relationships between motion clusters by provi...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Trichet,Remi, Nevatia,Ramakant
Format:	Report
Sprache:	eng
Schlagworte:	character recognition Color computer vision Context modeling Cybernetics Feature extraction histograms Motion segmentation multiple scales pattern recognition Robustness Statistics and Probability Tracking video descriptor video segmentation
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	This paper presents a new video motion descriptor based on a multi-scale video segmentation to provide a multi-layered output as well as connections with the rich interactions that occur between objects at the semantic level. We also put the emphasis on relationships between motion clusters by providing a new relative motion descriptor encapsulating relative motion patterns within a local spatio-temporal neighborhood. Experimental results on the challenging TRECVID MED11 event recognition dataset validate the approach. 2014 22nd International Conference on Pattern Recognition (ICPR) , 24 Aug 2014, 28 Aug 2014,