Detecting Suspicious Behavior in Surveillance Images

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.

• Type: Conference
• Year: 2008
• Where: ICDM
• Authors: Daniel Barbará, Carlotta Domeniconi, Zoran Duric, Maurizio Filippone, Richard Mansfield, Edgard Lawson
• Keywords: Data Mining, False Positive Rates, Featureless Probabilistic Representation, ICDM 2008, Such Codeword Lengths