An Efficient Learning with Sparse Regularized Kernel for One-Class Classification

Abstract: Speedy abnormal event detection meets the growing demand to process an enormous number of surveillance videos. Although real-time processing is a key criterion to a practically employable system given continuously captured videos, most sparse code methods cannot be performed fast enough. A novel anomaly detection framework with transferred deep Convolutional Neural Network (CNN) is propose. The presents an online learning with sparse regularized kernel based one-class Extreme Learning Machine (ELM) classifier and is referred as �sparse-OC-ELM�. The baseline kernel hyperplane model considers whole data in a single chunk with regularized ELM approach for offline learning in case of One-Class Classification (OCC). The regularized kernel ELM based online learning and consistency-based model selection has been employed to select learning algorithm parameters. The online RK-OC-ELM has been evaluated on standard benchmark datasets as well as on artificial datasets and the results are compared with existing state-of-the art one class classifiers. The proposed method achieves high detection rates on benchmark datasets at a speed of 140-150 frames per second on average when computing on an ordinary desktop PC using MATLAB. The experimental results evaluate the proposed method on two publicly available video surveillance datasets, showing competitive performance with respect to state of the art approaches.

Keywords: Abnormal Event Detection, Outlier Detection, Video Data Stream, Sparse Learning, Dynamic Detection.