TY - JOUR
T1 - Video anomaly detection with compact feature sets for online performance
AU - Leyva, Roberto
AU - Sanchez, Victor
AU - Li, Chang Tsun
N1 - Includes bibliographical references.
PY - 2017/7
Y1 - 2017/7
N2 - Over the past decade, video anomaly detection has been explored with remarkable results. However, research on methodologies suitable for online performance is still very limited. In this paper, we present an online framework for video anomaly detection. The key aspect of our framework is a compact set of highly descriptive features, which is extracted from a novel cell structure that helps to define support regions in a coarse-to-fine fashion. Based on the scene's activity, only a limited number of support regions are processed, thus limiting the size of the feature set. Specifically, we use foreground occupancy and optical flow features. The framework uses an inference mechanism that evaluates the compact feature set via Gaussian Mixture Models, Markov Chains, and Bag-of-Words in order to detect abnormal events. Our framework also considers the joint response of the models in the local spatio-temporal neighborhood to increase detection accuracy. We test our framework on popular existing data sets and on a new data set comprising a wide variety of realistic videos captured by surveillance cameras. This particular data set includes surveillance videos depicting criminal activities, car accidents, and other dangerous situations. Evaluation results show that our framework outperforms other online methods and attains a very competitive detection performance compared with state-of-the-art non-online methods.
AB - Over the past decade, video anomaly detection has been explored with remarkable results. However, research on methodologies suitable for online performance is still very limited. In this paper, we present an online framework for video anomaly detection. The key aspect of our framework is a compact set of highly descriptive features, which is extracted from a novel cell structure that helps to define support regions in a coarse-to-fine fashion. Based on the scene's activity, only a limited number of support regions are processed, thus limiting the size of the feature set. Specifically, we use foreground occupancy and optical flow features. The framework uses an inference mechanism that evaluates the compact feature set via Gaussian Mixture Models, Markov Chains, and Bag-of-Words in order to detect abnormal events. Our framework also considers the joint response of the models in the local spatio-temporal neighborhood to increase detection accuracy. We test our framework on popular existing data sets and on a new data set comprising a wide variety of realistic videos captured by surveillance cameras. This particular data set includes surveillance videos depicting criminal activities, car accidents, and other dangerous situations. Evaluation results show that our framework outperforms other online methods and attains a very competitive detection performance compared with state-of-the-art non-online methods.
KW - Online processing
KW - Video anomaly detection
KW - Video surveillance
UR - http://www.scopus.com/inward/record.url?scp=85021710375&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85021710375&partnerID=8YFLogxK
U2 - 10.1109/TIP.2017.2695105
DO - 10.1109/TIP.2017.2695105
M3 - Article
C2 - 28436865
AN - SCOPUS:85021710375
VL - 26
SP - 3463
EP - 3478
JO - IEEE Transactions on Image Processing
JF - IEEE Transactions on Image Processing
SN - 1057-7149
IS - 7
M1 - 7903693
ER -