DocumentCode :
3630123
Title :
Detecting Suspicious Behavior in Surveillance Images
Author :
Daniel Barbará;Carlotta Domeniconi;Zoran Duric;Maurizio Filippone;Richard Mansfield;Edgard Lawson
Author_Institution :
Comput. Sci. Dept., George Mason Univ., Fairfax, VA
fYear :
2008
Firstpage :
891
Lastpage :
900
Abstract :
We introduce a novel technique to detect anomalies in images. The notion of normalcy is given by a baseline of images, under the assumption that the majority of such images is normal. The key of our approach is a featureless probabilistic representation of images, based on the length of the codeword necessary to represent each image. Such codeword´s lengths are then used for anomaly detection based on statistical testing. Our techniques were tested on synthetic and real data sets. The results show that our approach can achieve high true positive and low false positive rates.
Keywords :
"Surveillance","Object detection","Computer science","Statistical analysis","Data mining","Conferences","Electronic mail","Testing","Information theory","Probability"
Publisher :
ieee
Conference_Titel :
Data Mining Workshops, 2008. ICDMW ´08. IEEE International Conference on
ISSN :
2375-9232
Electronic_ISBN :
2375-9259
Type :
conf
DOI :
10.1109/ICDMW.2008.36
Filename :
4734020
Link To Document :
بازگشت