Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/TIFS.2014.2315971 | IEEE Transactions on Information Forensics and Security |
Keywords | Field | DocType |
video streams,nonlinear one-class support vector machine classification algorithm,abnormal detection,abnormal visual event detection,one-class svm,global optical flow orientation histogram,background subtraction step,learning (artificial intelligence),hofo,training frames normal behavior,image classification,image sequences,learning period,object detection,optical flow,optical flow computation fusion,support vector machines,video frame,image descriptor,video surveillance,vectors,optical imaging,histograms,learning artificial intelligence,nonlinear optics,feature extraction | Background subtraction,Object detection,Computer vision,Histogram,Pattern recognition,Computer science,Support vector machine,Video tracking,Artificial intelligence,Contextual image classification,Optical flow,Encoding (memory) | Journal |
Volume | Issue | ISSN |
9 | 6 | 1556-6013 |
Citations | PageRank | References |
34 | 0.96 | 25 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tian Wang | 1 | 45 | 1.77 |
Hichem Snoussi | 2 | 509 | 62.19 |