Bayesian Nonparametric Approaches to Abnormality Detection in Video Surveillance
Ann. Data. Sci. (
Bayesian Nonparametric Approaches to Abnormality Detection in Video Surveillance
Vu Nguyen 0 1
Dinh Phung 0 1
Duc-Son Pham 0 1
Svetha Venkatesh 0 1
0 Department of Computing, Curtin University , Bentley , Australia
1 Centre for Pattern Recognition and Data Analytics (PRaDA), Deakin University , Geelong , Australia
In data science, anomaly detection is the process of identifying the items, events or observations which do not conform to expected patterns in a dataset. As widely acknowledged in the computer vision community and security management, discovering suspicious events is the key issue for abnormal detection in video surveillance. The important steps in identifying such events include stream data segmentation and hidden patterns discovery. However, the crucial challenge in stream data segmentation and hidden patterns discovery are the number of coherent segments in surveillance stream and the number of traffic patterns are unknown and hard to specify. Therefore, in this paper we revisit the abnormality detection problem through the lens of Bayesian nonparametric (BNP) and develop a novel usage of BNP methods for this problem. In particular, we employ the Infinite Hidden Markov Model and Bayesian Nonparametric Factor Analysis for stream data segmentation and pattern discovery. In addition, we introduce an interactive system allowing users to inspect and browse suspicious events.
1 Introduction
In data science, anomaly detection is the process of identifying items, events or
observations which do not conform to expected patterns or other items in a dataset. Typically
the anomalous items are existing in some kind of specific problem such as bank frauds,
medical problems or finding errors in text. There are two major categories of abnormal
detection namely unsupervised abnormal detection and supervised abnormal
detection. The former detects anomalies in an unlabeled test data set under the assumption
that the majority of the instances in the data set are normal by looking for instances
that seem to fit least to the remainder of the data set. The latter requires a data set that
has been labeled as ‘normal’ and ‘abnormal’ and involves training a classifier (e.g.
Support Vector Machine [
1
], Logistic Regression [
2
]).
In this paper, we consider specifically the problem of unsupervised abnormality
detection in video surveillance. As widely acknowledged in the computer vision
community and security management, discovering suspicions and irregularities of events
in a video sequence is the key issue for abnormal detection in video surveillance [
3–7
].
The important steps in identifying such events include stream data segmentation and
hidden patterns discovery. However, the crucial challenge in stream data segmentation
and hidden patterns discovery are the number of coherent segments in surveillance
stream and the number of traffic patterns are unknown and hard to specify.
The theory of Bayesian nonparametric (BNP) [
8–13
] holds a promise to address
these challenges. As such, BNP can automatically identify the suitable number of
cluster from the data. Therefore, in this paper we revisit the abnormality detection
problem through the lens of BNP and develop a novel usage of BNP methods for this
problem. In particular, we employ the infinite hidden Markov model [14] and Bayesian
nonparametric factor analysis [
15
].
The first advantage of our methods is that identifying the unknown number of
coherent sections of the video stream would result in better detection performance.
Each coherent section of motion (e.g. traffic movements at night time and day time)
would contain different types of abnormality. Unlike traditional abnormality detection
methods which typically build upon a unified model across data stream. The second
benefit of our system is an interface allowing users to interactively examine rare events
in an intuitive manner. Because the abnormal events detected by algorithms and what
is considered anomalous by users may be inconsistent, the proposed interface would
greatly be beneficial.
To this end, we make two major contributions to abnormal detection in video
surveillance: (1) proposing to use the Infinite Hidden Markov Model for stream
data segmentation, and (2) introducing the Bayesian nonparametric Factor
Analysisbased interactive system allowing users to inspect and browse suspiciously abnormal
events.
This paper is organized as follows. We present an overview on abnormality detection
in video surveillance and the need of segmenting the data and interaction in Sect. 2.
In Sect. 3, we describes our contribution on Bayesian nonparametric data stream
segmentation for abnormal detection. Section 4 illustrates our introduced browsing
system for abnormal detection. The experiment is provided in Sect. 5. Finally, we
present a summary of the paper with some concluding remarks in Sect. 6.
2 Video Surveillance
Ideally, abnormality detection algorithms should report o (...truncated)