Detection of Abnormal Visual Events via Global Optical Flow Orientation Histogram

• Published in: IEEE transactions on information forensics and security Vol. 9; no. 6; pp. 988 - 998
• Main Authors: Tian Wang, Snoussi, Hichem
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.06.2014; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithmics. Computability. Computer arithmetics; Algorithms; Applied sciences; Artificial intelligence; Classification; Computer science; control theory; systems; Data processing. List processing. Character string processing; Encoding; Engineering Sciences; Exact sciences and technology; Feature extraction; Forensic engineering; Frames; Histograms; Memory organisation. Data processing; Nonlinear optics; Nonlinearity; Optical imaging; Orientation; Pattern recognition. Digital image processing. Computational geometry; Signal and Image processing; Software; Support vector machines; Theoretical computing; Training; Vectors; HOFO; optical flow; Abnormal detection; one-class SVM; Image subtraction; Streaming; Computer vision; Histogram; Descriptor system; Image processing; Image content; Video signal; Image segmentation; Surveillance; ABackground; Scene analysis; Vector support machine; Anomaly; Learning algorithm; Artificial intelligence; Optical flow; Binary classification
• ISSN: 1556-6013; 1556-6021
• DOI: 10.1109/TIFS.2014.2315971

The aim of this paper is to detect abnormal events in video streams, a challenging but important subject in video surveillance. We propose a novel algorithm to address this problem. The algorithm is based on an image descriptor and a nonlinear classification method. We introduce a histogram of optical flow orientation as a descriptor encoding the moving information of each video frame. The nonlinear one-class support vector machine classification algorithm, following a learning period characterizing the normal behavior of training frames, detects abnormal events in the current frame. Further, a fast version of the detection algorithm is designed by fusing the optical flow computation with a background subtraction step. We finally apply the method to detect abnormal events on several benchmark data sets, and show promising results.