Anomaly detection for internet surveillance

Bouma, Henri; Raaijmakers, Stephan; Halma, Arvid; Wedemeijer, Harry

doi:10.1117/12.918573

Cited by 3 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dedicated classifiers attempt to recognize these actions in certain parts of a scene at every moment. [1][2][3] The results of these classifiers on all verbs are represented as verb probabilities, and form the input for the anomaly detection system.…”

Section: Task Descriptionmentioning

confidence: 99%

See 1 more Smart Citation

Anomalous human behavior detection: an adaptive approach

Leeuwen

Halma²,

Schutte

2013

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

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 (ab)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.

show abstract

Section: Task Descriptionmentioning

confidence: 99%

“…The actual action recognition is not in the scope of this paper, instead we used a data set which had already been classified. 2 In this data set of over 3500 clips, each clip was given a set of 48 probabilities corresponding to 48 verbs. We also had access to human annotated ground truth of the majority of these clips.…”

Section: Behavioral Anomaliesmentioning

confidence: 99%