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

arXiv: https://arxiv.org/abs/2011.02853 · HTML: https://mlsanity.com/paper/2011.02853/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2020.

## Built on by (most cited first, 6 of 6)

- [Context-Dependent Anomaly Detection for Low Altitude Traffic Surveillance](https://mlsanity.com/paper/2104.06781/) (2021)
- [Prompt-Driven Temporal Domain Adaptation for Nighttime UAV Tracking](https://mlsanity.com/paper/2409.18533/) (2024)
- [Margin-Aware Intra-Class Novelty Identification for Medical Images](https://mlsanity.com/paper/2108.00117/) (2021)
- [Safe Vessel Navigation Visually Aided by Autonomous Unmanned Aerial Vehicles in Congested Harbors and Waterways](https://mlsanity.com/paper/2108.03862/) (2021)
- [Contextual Information Based Anomaly Detection for a Multi-Scene UAV Aerial Videos](https://mlsanity.com/paper/2203.15437/) (2022)
- [Decision-making of Emergent Incident based on P-MADDPG](https://mlsanity.com/paper/2203.12673/) (2022)

## Abstract (arXiv)

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.