UAV-AdNet: Unsupervised Anomaly Detection using Deep Neural Networks for Aerial Surveillance

TL;DR

UAV-AdNet is an unsupervised deep learning system that detects anomalies in aerial surveillance by combining spatial object layouts and GPS data, improving detection accuracy for critical infrastructure monitoring.

Contribution

The paper introduces UAV-AdNet, a novel unsupervised neural network architecture that integrates GPS and image data for enhanced anomaly detection in UAV-based aerial surveillance.

Findings

Outperforms baseline models in scene reconstruction

Achieves higher accuracy in anomaly detection tasks

Demonstrates effective use of combined spatial and GPS data

Abstract

Anomaly detection is a key goal of autonomous surveillance systems that should be able to alert unusual observations. In this paper, we propose a holistic anomaly detection system using deep neural networks for surveillance of critical infrastructures (e.g., airports, harbors, warehouses) using an unmanned aerial vehicle (UAV). First, we present a heuristic method for the explicit representation of spatial layouts of objects in bird-view images. Then, we propose a deep neural network architecture for unsupervised anomaly detection (UAV-AdNet), which is trained on environment representations and GPS labels of bird-view images jointly. Unlike studies in the literature, we combine GPS and image data to predict abnormal observations. We evaluate our model against several baselines on our aerial surveillance dataset and show that it performs better in scene reconstruction and several anomaly detection tasks. The codes, trained models, dataset, and video will be available at https://bozcani.github.io/uavadnet.