Exploring Visual and Motion Saliency for Automatic Video Object Extraction
- 20 March 2013
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 22 (7), 2600-2610
- https://doi.org/10.1109/tip.2013.2253483
Abstract
This paper presents a saliency-based video object extraction (VOE) framework. The proposed framework aims to automatically extract foreground objects of interest without any user interaction or the use of any training data (i.e., not limited to any particular type of object). To separate foreground and background regions within and across video frames, the proposed method utilizes visual and motion saliency information extracted from the input video. A conditional random field is applied to effectively combine the saliency induced features, which allows us to deal with unknown pose and scale variations of the foreground object (and its articulated parts). Based on the ability to preserve both spatial continuity and temporal consistency in the proposed VOE framework, experiments on a variety of videos verify that our method is able to produce quantitatively and qualitatively satisfactory VOE results.Keywords
This publication has 30 references indexed in Scilit:
- Visual Saliency from Image Features with Application to CompressionCognitive Computation, 2012
- Key-segments for video object segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Advanced background subtraction approach using Laplacian distribution modelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Efficient hierarchical graph-based video segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Motion Coherent Tracking with Multi-label MRF optimizationPublished by British Machine Vision Association and Society for Pattern Recognition ,2010
- Saliency-based video segmentation with graph cuts and sequentially updated priorsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Image Denoising Via Sparse and Redundant Representations Over Learned DictionariesIEEE Transactions on Image Processing, 2006
- Unsupervised Learning of Object Features from Video SequencesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Segmenting foreground objects from a dynamic textured background via a robust Kalman filterPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- A model of saliency-based visual attention for rapid scene analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998