Context-Dependent Anomaly Detection for Low Altitude Traffic Surveillance

TL;DR

This paper presents CADNet, a novel deep neural network that detects contextual anomalies in UAV surveillance by integrating environmental context through GPS and time data, outperforming existing methods.

Contribution

The work introduces the first UAV-specific contextual anomaly detection method using a variational autoencoder with a context sub-network, enhancing anomaly detection accuracy.

Findings

CADNet outperforms baseline methods in anomaly detection accuracy.

The approach effectively incorporates environmental context via GPS and time data.

Quantitative results demonstrate superior performance on the AU-AIR dataset.

Abstract

The detection of contextual anomalies is a challenging task for surveillance since an observation can be considered anomalous or normal in a specific environmental context. An unmanned aerial vehicle (UAV) can utilize its aerial monitoring capability and employ multiple sensors to gather contextual information about the environment and perform contextual anomaly detection. In this work, we introduce a deep neural network-based method (CADNet) to find point anomalies (i.e., single instance anomalous data) and contextual anomalies (i.e., context-specific abnormality) in an environment using a UAV. The method is based on a variational autoencoder (VAE) with a context sub-network. The context sub-network extracts contextual information regarding the environment using GPS and time data, then feeds it to the VAE to predict anomalies conditioned on the context. To the best of our knowledge, our method is the first contextual anomaly detection method for UAV-assisted aerial surveillance. We evaluate our method on the AU-AIR dataset in a traffic surveillance scenario. Quantitative comparisons against several baselines demonstrate the superiority of our approach in the anomaly detection tasks. The codes and data will be available at https://bozcani.github.io/cadnet.