Harborfront Anomaly Detection

Creating high-quality datasets for the task of video anomaly detection is challeng-
ing due to a subjective anomaly definition and the rarity of anomalies, which oust
the possibility of obtaining statistically significant data. This results in datasets
where anomalies are placed in a single category, and are often considered less rel-
evant from a security standpoint. Instead, we propose to create video anomaly
datasets based on a framework utilizing object annotations to ease the annotation
process and allow users to decide on the anomaly definition. Furthermore, this
allows for a fine-grained evaluation w.r.t. anomaly types, which represents a nov-
elty in the area of video anomaly detection. The framework is demonstrated using
the existing thermal long-term drift (LTD) dataset, identifying and evaluating
five different types of anomalies (appearance, motion, localization, density, and
tampering) on six test sets. State-of-the-art anomaly detection methods are evalu-
ated and found to underperform on the thermal anomaly detection dataset, which
emphasizes a need for an adjustable anomaly definition in order to produce bet-
ter anomaly datasets and models that generalize towards practical use. We share
the code of the proposed framework to extract anomaly types along with object
annotations for the LTD dataset at https://github.com/jagob/harborfront-vad.