Salient Motion Detection in Compressed Domain
Authors:
- 8 August 2013
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 20 (10) , 996-999
Abstract
We propose a novel motion saliency framework using DCT coefficients and motion vectors as features from MPEG-2 videos. The DCT coefficients of the luma and chroma components are used to calculate the spatial saliency of a frame while the motion vectors are utilized to refine it. Spatio-temporal similarity maps are calculated separately in order to cater to tracking shots. Results show that the proposed motion saliency framework is computationally nearly an 8-fold improvement over the best performing state-of-the-art method while nearly equalling its performance in identifying salient regions.Keywords
This publication has 18 references indexed in Scilit:
- Video saliency detection in the compressed domain2012
- Visual media retargeting2009
- Object Tracking in Structured Environments for Video Surveillance ApplicationsIEEE Transactions on Circuits and Systems for Video Technology, 2009
- Frequency-tuned salient region detection2009
- Attention-from-motion: A factorization approach for detecting attention objects in motionComputer Vision and Image Understanding, 2009
- Saliency Detection: A Spectral Residual Approach2007
- Compressed domain object tracking for automatic indexing of objects in MPEG home video2003
- Background and foreground modeling using nonparametric kernel density estimation for visual surveillanceProceedings of the IEEE, 2002
- A simple saliency model predicts a number of motion popout phenomenaVision Research, 1999
- A model of saliency-based visual attention for rapid scene analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998