Research Article

AutoML-Based Fusion of Radar and Image Data for Aerial Target Classification

Number: 6 June 20, 2026

AutoML-Based Fusion of Radar and Image Data for Aerial Target Classification

Abstract

This study aims to detect and classify aerial targets by integrating radar data with image processing techniques. While radar systems provide essential physical parameters such as target position and velocity, image processing methods including grayscale conversion and feature extraction enable the analysis of visual characteristics. This multimodal integration significantly enhances classification performance, particularly in distinguishing between various aerial platforms such as unmanned aerial vehicles (UAVs), fighter jets, and helicopters. Rather than acting as a stand alone classifier, FLAML (Fast and Lightweight AutoML) an automated machine learning (AutoML) framework that automatically evaluates and optimizes a range of candidate machine learning models was employed to identify the most suitable classifier for the task. Among these, ensemble based models namely XGBoost (Extreme Gradient Boosting), LightGBM (Light Gradient Boosting Machine), and Random Forest demonstrated superior performance compared to other approaches. Results obtained from five fold cross validation indicate that both LightGBM and XGBoost achieved comparable and state of the art generalization performance on the test data, with an accuracy and macro F1-score of approximately 84%. These findings reveal that the combined use of radar and image-based data provides an effective and reliable approach for aerial target detection and classification.

Keywords

Ethical Statement

In this article, the principles of scientific research and publication ethics were followed. This study did not involve human or animal subjects and did not require additional ethics committee approval.

References

  1. Adel, A., Alani, N. H. S., Whiteside, S. T., & Jan, T. (2024). Who is watching whom? Military and civilian drone: Vision intelligence investigation and recommendations. IEEE Access, 12, 177236–177276. https://doi.org/10.1109/ACCESS.2024.3505034
  2. Akbıyık, B. (2020). 5G işaretleri kullanılarak bilişsel pasif radar ile dron tespiti [Yüksek lisans tezi, Başkent Üniversitesi]. YÖK Tez Merkezi.
  3. Chen, S., Tai, N., Fan, C., Liu, J., & Hong, S. (2018). Sequence-component-based current differential protection for transmission lines connected with IIGs. IET Generation, Transmission & Distribution, 12(12), 3086–3096. https://doi.org/10.1049/iet-gtd.2017.1507
  4. Chen, V. C., Li, F., Ho,S.S., Wechsler, H. (2006). Micro-Doppler effect in radar: Phenomenon, model, and simulation study. IEEE Transactions on Aerospace and Electronic Systems, 42(1), 2–21. https://doi.org/10.1109/TAES.2006.1603402
  5. Czerkawski, M., Clemente, C., Michie, C., Andonovic, I., & Tachtatzis, C. (2022). Robustness of Deep Neural Networks for Micro-Doppler Radar Classification. 2022 23rd International Radar Symposium (IRS) içinde (ss. 480-485). IEEE. https://doi.org/10.23919/IRS54158.2022.9905017
  6. Das, M. (2019). Drone dataset (UAV) [Data set]. Kaggle. https://www.kaggle.com/datasets/dasmehdixtr/drone-dataset-uav
  7. Erdoğan, M., & Yıldız, O. (2024). Evrişimli Sinir Ağı Kullanarak Dengesiz Doppler Radar Verisinde Hedef Tespiti. Politeknik Dergisi, 27(4), 1317-1326. https://doi.org/10.2339/politeknik.1180081
  8. Famili, A., Stavrou, A., Wang, H., Park, J.-M., & Gerdes, R. (2024). Securing Your Airspace: Detection of Drones Trespassing Protected Areas. Sensors, 24(7), 2028. https://doi.org/10.3390/s24072028

Details

Primary Language

English

Subjects

Adversarial Machine Learning, Machine Learning Algorithms

Journal Section

Research Article

Publication Date

June 20, 2026

Submission Date

March 25, 2026

Acceptance Date

June 9, 2026

Published in Issue

Year 2026 Number: 6

APA
Harman, G., & Soylu, Y. (2026). AutoML-Based Fusion of Radar and Image Data for Aerial Target Classification. Journal of Emerging Computer Technologies, 6, 29-43. https://izlik.org/JA26NP23KF
AMA
1.Harman G, Soylu Y. AutoML-Based Fusion of Radar and Image Data for Aerial Target Classification. JECT. 2026;(6):29-43. https://izlik.org/JA26NP23KF
Chicago
Harman, Güneş, and Yağmur Soylu. 2026. “AutoML-Based Fusion of Radar and Image Data for Aerial Target Classification”. Journal of Emerging Computer Technologies, nos. 6: 29-43. https://izlik.org/JA26NP23KF.
EndNote
Harman G, Soylu Y (June 1, 2026) AutoML-Based Fusion of Radar and Image Data for Aerial Target Classification. Journal of Emerging Computer Technologies 6 29–43.
IEEE
[1]G. Harman and Y. Soylu, “AutoML-Based Fusion of Radar and Image Data for Aerial Target Classification”, JECT, no. 6, pp. 29–43, June 2026, [Online]. Available: https://izlik.org/JA26NP23KF
ISNAD
Harman, Güneş - Soylu, Yağmur. “AutoML-Based Fusion of Radar and Image Data for Aerial Target Classification”. Journal of Emerging Computer Technologies. 6 (June 1, 2026): 29-43. https://izlik.org/JA26NP23KF.
JAMA
1.Harman G, Soylu Y. AutoML-Based Fusion of Radar and Image Data for Aerial Target Classification. JECT. 2026;:29–43.
MLA
Harman, Güneş, and Yağmur Soylu. “AutoML-Based Fusion of Radar and Image Data for Aerial Target Classification”. Journal of Emerging Computer Technologies, no. 6, June 2026, pp. 29-43, https://izlik.org/JA26NP23KF.
Vancouver
1.Güneş Harman, Yağmur Soylu. AutoML-Based Fusion of Radar and Image Data for Aerial Target Classification. JECT [Internet]. 2026 Jun. 1;(6):29-43. Available from: https://izlik.org/JA26NP23KF
Journal of Emerging Computer Technologies
is indexed and abstracted by
Harvard Hollis, Scilit, ROAD, Google Scholar, OpenAIRE

Publisher
Izmir Academy Association

88x31.png