Summarisation of short-term and long-term videos using texture and colour


Autoria(s): Carvajal, Johanna; McCool, Chris; Sanderson, Conrad
Data(s)

24/03/2014

Resumo

We present a novel approach to video summarisation that makes use of a Bag-of-visual-Textures (BoT) approach. Two systems are proposed, one based solely on the BoT approach and another which exploits both colour information and BoT features. On 50 short-term videos from the Open Video Project we show that our BoT and fusion systems both achieve state-of-the-art performance, obtaining an average F-measure of 0.83 and 0.86 respectively, a relative improvement of 9% and 13% when compared to the previous state-of-the-art. When applied to a new underwater surveillance dataset containing 33 long-term videos, the proposed system reduces the amount of footage by a factor of 27, with only minor degradation in the information content. This order of magnitude reduction in video data represents significant savings in terms of time and potential labour cost when manually reviewing such footage.

Formato

application/pdf

Identificador

http://eprints.qut.edu.au/71630/

Relação

http://eprints.qut.edu.au/71630/1/carvajal_video_summarisation_wacv_2014.pdf

http://www.wacv14.org/

Carvajal, Johanna, McCool, Chris, & Sanderson, Conrad (2014) Summarisation of short-term and long-term videos using texture and colour. In WACV 2014 : IEEE Winter Conference on Applications of Computer Vision, 24-26 March 2014, Sheraton Steamboat Resort, Steamboat Springs, Colorado. (Unpublished)

Direitos

Copyright 2014 please consult author(s)

Fonte

Science & Engineering Faculty

Palavras-Chave #010200 APPLIED MATHEMATICS #080104 Computer Vision #080106 Image Processing #080109 Pattern Recognition and Data Mining #090609 Signal Processing
Tipo

Conference Paper