Cyclostationary Statistical Models and Algorithms for Anomaly Detection Using Multi-Modal Data
This work addresses anomaly detection for surveillance and event monitoring using multi-modal data, but it appears incremental as it builds on existing deep learning and statistical methods.
The authors tackled anomaly detection in multi-modal data by proposing a cyclostationary model to capture regular patterns in object counts, and developed sequential algorithms that are asymptotically efficient, applying them to detect a 5K run in New York City using CCTV and social media data.
A framework is proposed to detect anomalies in multi-modal data. A deep neural network-based object detector is employed to extract counts of objects and sub-events from the data. A cyclostationary model is proposed to model regular patterns of behavior in the count sequences. The anomaly detection problem is formulated as a problem of detecting deviations from learned cyclostationary behavior. Sequential algorithms are proposed to detect anomalies using the proposed model. The proposed algorithms are shown to be asymptotically efficient in a well-defined sense. The developed algorithms are applied to a multi-modal data consisting of CCTV imagery and social media posts to detect a 5K run in New York City.