Anomalous human behavior detection

Anomalous human behavior detection: An Adaptive approach

van Leeuwen, C.
Halma, A.
Schutte, K.

Kadar, I. (editor)

2013

Detection of anomalies (outliers or abnormal instances) is an important element in a range of applications such as fault, fraud, suspicious behavior detection and knowledge discovery. In this article we propose a new method for anomaly detection and performed tested its ability to detect anomalous behavior in videos from DARPA's Mind's Eye program, containing a variety of human activities. In this semi-unsupervised task a set of normal instances is provided for training, after which unknown abnormal behavior has to be detected in a test set. The features extracted from the video data have high dimensionality, are sparse and inhomogeneously distributed in the feature space making it a challenging task. Given these characteristics a distance-based method is preferred, but choosing a threshold to classify instances as (AD)normal is non-trivial. Our novel aproach, the Adaptive Outlier Distance (AOD) is able to detect outliers in these conditions based on local distance ratios. The underlying assumption is that the local maximum distance between labeled examples is a good indicator of the variation in that neighborhood, and therefore a local threshold will result in more robust outlier detection. We compare our method to existing state-of-art methods such as the Local Outlier Factor (LOF) and the Local Distance-based Outlier Factor (LDOF). The results of the experiments show that our novel approach improves the quality of the anomaly detection. © 2013 SPIE.

Anomaly detection
One-class classification
Outlier detection
Pattern recognition
Video analysis
Safety and Security
Defence, Safety and Security
Physics & Electronics
II - Intelligent Imaging
TS - Technical Sciences

http://resolver.tudelft.nl/uuid:b1985daa-b2a6-4aba-b5fd-01ed55a4bb16

https://doi.org/10.1117/12.2015678

477635

SPIE, Bellingham, WA

Signal Processing, Sensor Fusion, and Target Recognition XXII, 29 April - 2 May 2013, Baltimore, MD, USA

Proceedings of SPIE

conference paper