Global self-similarity and saliency measures based on sparse representations for classification of objects and spatio-temporal sequences
2012-12
Loading...
View/Download File
Persistent link to this item
Statistics
View StatisticsJournal Title
Journal ISSN
Volume Title
Title
Global self-similarity and saliency measures based on sparse representations for classification of objects and spatio-temporal sequences
Authors
Published Date
2012-12
Publisher
Type
Thesis or Dissertation
Abstract
Extracting the truly salient regions in images is critical for many computer vision applications. Salient regions are considered the most informative regions of an image. Traditionally these salient regions have always been considered as local phenomena in which the salient regions stand out as local extrema with respect to their immediate neighbors. We introduce a novel global saliency metric based on sparse representation in which the regions that are most dissimilar with respect to the entire image are deemed salient. We examine our definition of saliency from the theoretical stand point of sparse representation and minimum description length. Encouraged by the efficacy of our method in modeling foreground objects, we propose two classification methods for recognizing objects in images. First, we introduce two novel global self-similarity descriptors for object representation which can directly be used in any classification framework. Next, we use our salient feature detection approach with conventional region descriptors in a bag-of-features framework. Experimentally we show that our feature detection method enhances the bag-of-features framework. Finally, we extend our salient bag-of-features approach to the spatio-temporal domain for use with three-dimensional dense descriptors. We apply this method successfully to video sequences involving human actions. We obtain state-of-the-art recognition rates in three distinct datasets involving sports and movie actions.
Description
University of Minnesota Ph.D. dissertation. December 2012. Major: Computer Science. Advisor: Nikolaos Papanikolopoulos. 1 computer file (PDF); x, 127 pages.
Related to
Replaces
License
Collections
Series/Report Number
Funding information
Isbn identifier
Doi identifier
Previously Published Citation
Suggested citation
Somasundaram, Guruprasad. (2012). Global self-similarity and saliency measures based on sparse representations for classification of objects and spatio-temporal sequences. Retrieved from the University Digital Conservancy, https://hdl.handle.net/11299/144326.
Content distributed via the University Digital Conservancy may be subject to additional license and use restrictions applied by the depositor. By using these files, users agree to the Terms of Use. Materials in the UDC may contain content that is disturbing and/or harmful. For more information, please see our statement on harmful content in digital repositories.