ADOC
A Day on Campus Dataset. An Anomaly Detection Dataset for Events in a Single Camera.
Anomaly Event Examples
Visual examples from the ADOC dataset showing diverse events under varying conditions.
Golf Cart on Walkway
Person on Grass
Person on Skateboard
Having a Conversation
Riding Bike (Day)
Person with Umbrella
Mobility Scooter
Riding Bike (Night)
The ADOC dataset is a foundational resource for anomaly detection in single-camera surveillance. We acquired 24 continuous hours of 1080p, H.264 video from a live university campus. The data encapsulates extreme variations in illumination, background clutter, and crowd density.
We define anomalies as statistically “rare” events (low-frequency occurrences). Our data is meticulously annotated with 875 events, including high-frequency actions and specific rare activities like “golf cart on walkway” or “person with a mobility scooter.”
Selected Anomaly Events
| Event Name | Frequency |
|---|---|
| Person riding a bike | 238 |
| Person on grass | 132 |
| Golf cart on walkway | 105 |
| Having a conversation | 58 |
| Person on skateboard | 48 |