ABSTRACT
In this paper we introduce a 3-dimensional (3D) SIFT descriptor for video or 3D imagery such as MRI data. We also show how this new descriptor is able to better represent the 3D nature of video data in the application of action recognition. This paper will show how 3D SIFT is able to outperform previously used description methods in an elegant and efficient manner. We use a bag of words approach to represent videos, and present a method to discover relationships between spatio-temporal words in order to better describe the video data.
- M. Blank et al., "Actions as Space-Time Shapes," ICCV, 2005. Google ScholarDigital Library
- M. Brown et al., "Recognising Panoramas," ICCV, 2003. Google ScholarDigital Library
- G. Csurka et al., "Visual Categorization with Bags of Keypoints", ECCV, 2004.Google Scholar
- A. Efros et al., "Recognizing Action at a Distance," ICCV, 2003. Google ScholarDigital Library
- Y. Ke et al., "Efficient Visual Event Detection using Volumetric Features", ICCV, 2005. Google ScholarDigital Library
- M. Lalonde et al., "Real-Time eye blink detection with GPU-based SIFT tracking," Fourth Canadian Conference on Computer and Robot Vision, 2007. Google ScholarDigital Library
- S. Lazebnik et al., "Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories," CVPR, 2005. Google ScholarDigital Library
- D. G. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints," IJCV, 2004. Google ScholarDigital Library
- D. G. Lowe, "Object recognition from local scale-invariant features," ICCV, 1999. Google ScholarDigital Library
- J. C. Niebles et al., "Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words," BMVC, 2006.Google Scholar
- S. Se et al., "Vision-based Mobile Robot Localization And Mapping using Scale-Invariant Features," International Journal of Robotics Research, 2002.Google Scholar
- A. Yilmaz et al., "Actions Sketch: A Novel Action Representation," CVPR, 2005. Google ScholarDigital Library
Index Terms
- A 3-dimensional sift descriptor and its application to action recognition
Recommendations
Improvements to the Descriptor of SIFT by BOF Approaches
ACPR '13: Proceedings of the 2013 2nd IAPR Asian Conference on Pattern RecognitionThe efficacy and efficiency of SIFT have made it a state-of-art feature descriptor. It has been widely used in many computer vision applications such as image classification. A large number of methods, e.g. PCA-SIFT, have been contributed to further ...
Action recognition using 3D DAISY descriptor
In this paper we propose a novel spatial-temporal descriptor for action recognition. We extend a recent image local descriptor, DAISY, to three dimensions to deal with the information in the additional temporal domain in videos. The new 3D DAISY ...
A new framework for feature descriptor based on SIFT
The description of interest points is a critical aspect of point correspondence which is vital in some computer vision and pattern recognition tasks. SIFT descriptor has been proven to perform better on the distinctiveness and robustness than other ...
Comments