An in-depth study of sparse codes on abnormality detection
- 10 November 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 66-72
Abstract
Sparse representation has been applied successfully in abnormal event detection, in which the baseline is to learn a dictionary accompanied by sparse codes. While much emphasis is put on discriminative dictionary construction, there are no comparative studies of sparse codes regarding abnormality detection. We present an in-depth study of two types of sparse codes solutions - greedy algorithms and convex L1-norm solutions - and their impact on abnormality detection performance. We also propose our framework of combining sparse codes with different detection methods. Our comparative experiments are carried out from various angles to better understand the applicability of sparse codes, including computation time, reconstruction error, sparsity, detection accuracy, and their performance combining various detection methods. The experiment results show that combining OMP codes with maximum coordinate detection could achieve state-of-the-art performance on the UCSD dataset [14].Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Unsupervised Behavior-Specific Dictionary Learning for Abnormal Event Detection2015
- Abnormal Event Detection at 150 FPS in MATLAB2013
- Label Consistent K-SVD: Learning a Discriminative Dictionary for RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Sparse Solution of Underdetermined Systems of Linear Equations by Stagewise Orthogonal Matching PursuitIEEE Transactions on Information Theory, 2012
- Sparse reconstruction cost for abnormal event detection2011
- Anomaly detection in crowded scenes2010
- Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models2009
- Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition2002
- An improved FOCUSS-based learning algorithm for solving sparse linear inverse problems2001
- Matching pursuits with time-frequency dictionariesIEEE Transactions on Signal Processing, 1993