Sparse representation for robust abnormality detection in crowded scenes

作者：

Highlights：

• A non-negative sparse coding based approach for abnormality event detection in crowded scenes is proposed.

• Dictionary learning is formulated as a non-negative matrix factorization problem.

• EMD is selected as distance metric to cope with feature noisy and uncertainty.

• Wavelet EMD is introduced to reduce computation and guarantee the convexity of optimization.

摘要

Highlights•A non-negative sparse coding based approach for abnormality event detection in crowded scenes is proposed.•Dictionary learning is formulated as a non-negative matrix factorization problem.•EMD is selected as distance metric to cope with feature noisy and uncertainty.•Wavelet EMD is introduced to reduce computation and guarantee the convexity of optimization.

论文关键词：Nonnegative matrix factorization,Crowded scene,Abnormality detection,Sparse coding,Earth mover's distance,Wavelet EMD

论文评审过程：Received 5 June 2013, Revised 9 November 2013, Accepted 20 November 2013, Available online 1 December 2013.

论文官网地址：https://doi.org/10.1016/j.patcog.2013.11.018