Consistent Sparse Representation for Abnormal Event Detection

Zhong ZHANG  Shuang LIU  Zhiwei ZHANG  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E98-D   No.10   pp.1866-1870
Publication Date: 2015/10/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2015EDL8113
Type of Manuscript: LETTER
Category: Pattern Recognition
Keyword: 
consistent regularization,  sparse representation,  abnormal event detection,  

Full Text: PDF(239.2KB)>>
Buy this Article




Summary: 
Sparsity-based methods have been recently applied to abnormal event detection and have achieved impressive results. However, most such methods suffer from the problem of dimensionality curse; furthermore, they also take no consideration of the relationship among coefficient vectors. In this paper, we propose a novel method called consistent sparse representation (CSR) to overcome the drawbacks. We first reconstruct each feature in the space spanned by the clustering centers of training features so as to reduce the dimensionality of features and preserve the neighboring structure. Then, the consistent regularization is added to the sparse representation model, which explicitly considers the relationship of coefficient vectors. Our method is verified on two challenging databases (UCSD Ped1 database and Subway batabase), and the experimental results demonstrate that our method obtains better results than previous methods in abnormal event detection.