Increasing the security at vital infrastructures: automated detection of deviant behaviors

Burghouts, Gertjan J.; Hollander, Richard den; Schutte, Klamer; Marck, Jan Willem; Landsmeer, Sander H.; Breejen, E. den

doi:10.1117/12.884579

Cited by 6 publications

(5 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Choosing the threshold is not part of the responsibilities of the algorithm, and may be difficult to choose in practice, since most real world data is unlikely to be distributed homogeneously. 5 A difference in local densities may suggest different thresholds, as is depicted in Figure 2.…”

Section: Fixed or Dynamic Thresholdmentioning

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: Fixed or Dynamic Thresholdmentioning

confidence: 99%

“…In section 4 we will first show results of a synthetic experiment, after which we evaluate behavior detected from video data in order to find anomalous actions. Finally in section 5 we will discuss what we can learn from this, and consider future work. …”

Section: Introductionmentioning

confidence: 99%

Anomalous human behavior detection: an adaptive approach

Leeuwen

Halma²,

Schutte

2013

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

show abstract

“…It consists of five building blocks (see figure 2): visual processing, fusion engine, event description, action classifier, and the description generator. The visual processing [14] incorporates three steps. First the extraction of meaningful objects and their properties from video by (1) detection of moving objects [15], (2) a trained object detector for specific classes like persons and cars [16,17], and (3) computation of other features (e.g.…”

Section: System Overviewmentioning

confidence: 99%

Automated Textual Descriptions for a Wide Range of Video Events with 48 Human Actions

Hanckmann

Schutte

Burghouts

2012

Computer Vision – ECCV 2012. Workshops and Demonstrations

Self Cite

View full text Add to dashboard Cite

Abstract. Presented is a hybrid method to generate textual descriptions of video based on actions. The method includes an action classifier and a description generator. The aim for the action classifier is to detect and classify the actions in the video, such that they can be used as verbs for the description generator. The aim of the description generator is (1) to find the actors (objects or persons) in the video and connect these correctly to the verbs, such that these represent the subject, and direct and indirect objects, and (2) to generate a sentence based on the verb, subject, and direct and indirect objects. The novelty of our method is that we exploit the discriminative power of a bag-of-features action detector with the generative power of a rule-based action descriptor. Shown is that this approach outperforms a homogeneous setup with the rulebased action detector and action descriptor.

show abstract

“…The visual processing [7] of a scene starts with the detection of meaningful objects and their properties. The detection of objects is performed in two ways.…”

Section: Visual Processingmentioning

confidence: 99%

Automatic human action recognition in a scene from visual inputs

Bouma

Hanckmann

Marck

et al. 2012

Unattended Ground, Sea, and Air Sensor Technologies and Applications XIV

Self Cite

View full text Add to dashboard Cite

Surveillance is normally performed by humans, since it requires visual intelligence. However, this can be dull and dangerous, especially for military operations. Therefore, unmanned autonomous visual-intelligence systems are desired. In this paper, we present a novel system that can recognize human actions, which are relevant to detect operationally significant activity. Central to the system is a break-down of high-level perceptual concepts (verbs) in simpler observable events. The system is trained on 3482 videos and evaluated on 2589 videos from the DARPA Mind's Eye program, with for each video human annotations indicating the presence or absence of 48 different actions. The results show that our system reaches good performance approaching the human average response.

show abstract

Increasing the security at vital infrastructures: automated detection of deviant behaviors

Cited by 6 publications

References 3 publications

Anomalous human behavior detection: an adaptive approach

Anomalous human behavior detection: an adaptive approach

Automated Textual Descriptions for a Wide Range of Video Events with 48 Human Actions

Automatic human action recognition in a scene from visual inputs

Contact Info

Product

Resources

About