# AirTrack: Onboard Deep Learning Framework for Long-Range Aircraft Detection and Tracking

arXiv: https://arxiv.org/abs/2209.12849 · HTML: https://mlsanity.com/paper/2209.12849/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 41 references that are in the map.
- First posted on arXiv 26 Sep 2022.

## Builds on (most cited first, 12 of 12)

- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Simple Online and Realtime Tracking](https://mlsanity.com/paper/1602.00763/) (2016)
- [CenterNet: Keypoint Triplets for Object Detection](https://mlsanity.com/paper/1904.08189/) (2019)
- [Tracking Objects as Points](https://mlsanity.com/paper/2004.01177/) (2020)
- [Feature Selective Anchor-Free Module for Single-Shot Object Detection](https://mlsanity.com/paper/1903.00621/) (2019)
- [Finding Tiny Faces](https://mlsanity.com/paper/1612.04402/) (2016)
- [SiamMOT: Siamese Multi-Object Tracking](https://mlsanity.com/paper/2105.11595/) (2021)
- [Adaptivity without Compromise: A Momentumized, Adaptive, Dual Averaged Gradient Method for Stochastic Optimization](https://mlsanity.com/paper/2101.11075/) (2021)
- [Flying Objects Detection from a Single Moving Camera](https://mlsanity.com/paper/1411.7715/) (2014)
- [Learning Calibrated-Guidance for Object Detection in Aerial Images](https://mlsanity.com/paper/2103.11399/) (2021)
- [Below Horizon Aircraft Detection Using Deep Learning for Vision-Based Sense and Avoid](https://mlsanity.com/paper/1903.03275/) (2019)

## Built on by (most cited first, 9 of 9)

- [MMAUD: A Comprehensive Multi-Modal Anti-UAV Dataset for Modern Miniature Drone Threats](https://mlsanity.com/paper/2402.03706/) (2024)
- [Ensuring UAV Safety: A Vision-only and Real-time Framework for Collision Avoidance Through Object Detection, Tracking, and Distance Estimation](https://mlsanity.com/paper/2405.06749/) (2024)
- [TartanAviation: Image, Speech, and ADS-B Trajectory Datasets for Terminal Airspace Operations](https://mlsanity.com/paper/2403.03372/) (2024)
- [AVOIDDS: Aircraft Vision-based Intruder Detection Dataset and Simulator](https://mlsanity.com/paper/2306.11203/) (2023)
- [Long Range Object-Level Monocular Depth Estimation for UAVs](https://mlsanity.com/paper/2302.08943/) (2023)
- [Efficient Determination of Safety Requirements for Perception Systems](https://mlsanity.com/paper/2307.01371/) (2023)
- [Common Corruptions for Enhancing and Evaluating Robustness in Air-to-Air Visual Object Detection](https://mlsanity.com/paper/2405.06765/) (2024)
- [Model-Agnostic Open-Set Air-to-Air Visual Object Detection for Reliable UAV Perception](https://mlsanity.com/paper/2509.09297/) (2025)
- [AutoODD: Agentic Audits via Bayesian Red Teaming in Black-Box Models](https://mlsanity.com/paper/2509.08638/) (2025)

## Abstract (arXiv)

Detect-and-Avoid (DAA) capabilities are critical for safe operations of unmanned aircraft systems (UAS). This paper introduces, AirTrack, a real-time vision-only detect and tracking framework that respects the size, weight, and power (SWaP) constraints of sUAS systems. Given the low Signal-to-Noise ratios (SNR) of far away aircraft, we propose using full resolution images in a deep learning framework that aligns successive images to remove ego-motion. The aligned images are then used downstream in cascaded primary and secondary classifiers to improve detection and tracking performance on multiple metrics. We show that AirTrack outperforms state-of-the art baselines on the Amazon Airborne Object Tracking (AOT) Dataset. Multiple real world flight tests with a Cessna 182 interacting with general aviation traffic and additional near-collision flight tests with a Bell helicopter flying towards a UAS in a controlled setting showcase that the proposed approach satisfies the newly introduced ASTM F3442/F3442M standard for DAA. Empirical evaluations show that our system has a probability of track of more than 95% up to a range of 700m. Video available at https://youtu.be/H3lL_Wjxjpw .