Loading...
Sparse representation of local spatial-temporal features with dimensionality reduction for motion recognition
Wang, Jin Sun, Xiangping Liu, Ping She, Mary F. H. Kong, Lingxue
Wang, Jin
Sun, Xiangping
Liu, Ping
She, Mary F. H.
Kong, Lingxue
Abstract
Sparse representation and compressive sensing have attracted substantial interests in computer vision. In this paper, by introducing two new classification criteria, we extended the sparse representation classification method (SRC) for individual images to classify a video that contains a group of local spatial-temporal features. A dictionary is constructed by concatenating all class-specific dictionaries, each of which is learned from a motion class. A test video is assigned to a class label based on the minimum of reconstruction errors of individual local features or overall reconstruction error. Moreover, we compared the effectiveness of the traditional Principal Component Analysis (PCA) and two compressive sensing based dimensionality reduction methods, i.e., Random Matrix projection and Hash Matrix projection in the framework of sparse representation for motion recognition. Experimental results on four public datasets including hand gesture, human facial, human action and mouse behavior demonstrate that the proposed method achieves comparable or higher recognition accuracies compared to other state-of-the-art methods in the literatures. Although the traditional PCA requires more computation to get the transformation matrix, it performs better than the Random Matrix and Hash Matrix projections using gradient features. However, when raw features (i.e., pixel values) are used, the performance of the Random Matrix and Hash Matrix projections is significantly improved.
Keywords
motion analysis, sparse coding, compressive sensing, interest points
Date
2013
Type
Journal article
Journal
Neurocomputing
Book
Volume
115
Issue
Page Range
150-160
Article Number
ACU Department
Non-faculty
Collections
Relation URI
Source URL
Event URL
Open Access Status
License
File Access
Controlled