MULTI-TARGET TRACKING WITH FEDERATED EXTENDED KALMAN FILTERS

Nurbanu Güzey

doi:10.17780/ksujes.1661941

EN TR

MULTI-TARGET TRACKING WITH FEDERATED EXTENDED KALMAN FILTERS

Abstract

This paper presents a novel federated signal processing framework for multi-target tracking in distributed radar/sonar systems. Each sensor node independently tracks targets using an Extended Kalman Filter (EKF) that processes nonlinear range–bearing measurements, thereby generating refined state estimates and uncertainty covariances without transmitting raw sensor data. Instead, only these processed outputs—augmented by dynamically updated trust factors—are communicated to a central fusion center. The fusion center aggregates the local estimates via an inverse-covariance weighting scheme augmented by adaptive trust weights, yielding globally consistent target tracks with improved accuracy and robustness. Simulation results demonstrate that the proposed federated EKF approach significantly reduces communication overhead while maintaining high tracking performance under heterogeneous sensor conditions.

Keywords

FEDERATİF GENİŞLETİLMİŞ KALMAN FİLTRELERİ İLE ÇOKLU HEDEF TAKİBİ

Öz

Bu çalışma, dağıtık radar/sonar sistemlerinde çoklu hedef takibi için yeni bir federatif sinyal işleme çerçevesi sunmaktadır. Her bir sensör düğümü, ham sensör verilerini iletmeden, doğrusal olmayan menzil–yön ölçümlerini işleyen Genişletilmiş Kalman Filtresi (EKF) kullanarak hedefleri bağımsız olarak takip eder; böylece daha hassas durum tahminleri ve belirsizlik kovaryansları elde edilir. Ham sensör verileri yerine, yalnızca dinamik olarak güncellenen güven faktörleriyle zenginleştirilmiş işlenmiş çıktılar merkezi bir füzyon merkezine iletilir. Füzyon merkezi, yerel tahminleri adaptif güven ağırlıklarıyla desteklenen ters-kovaryans ağırlıklandırma şeması aracılığıyla birleştirerek, daha yüksek doğruluk ve dayanıklılığa sahip küresel olarak tutarlı hedef izleri elde eder. Simülasyon sonuçları, önerilen federatif EKF yaklaşımının heterojen sensör koşulları altında yüksek takip performansını sürdürürken iletişim yükünü önemli ölçüde azalttığını göstermektedir.

Anahtar Kelimeler

References

Boiteau, S., Vanegas, F., & Gonzalez, F. (2024). Framework for autonomous UAV navigation and target detection in global‐navigation‐satellite‐system‐denied and visually degraded environments. Remote Sensing, 16, 471. https://doi.org/10.3390/rs16030471
Chen, B., Pei, X., & Chen, Z. (2019). Research on target detection based on distributed track fusion for intelligent vehicles. Sensors, 20, 56. https://doi.org/10.3390/s20010056
Grigorescu, S., Trăsnea, B., Cocias, T., & Măceşanu, G. (2019). A survey of deep learning techniques for autonomous driving. Journal of Field Robotics, 37, 362–386. https://doi.org/10.1002/rob.21918
Goodin, C., Doude, M., Hudson, C. R., & Carruth, D. W. (2018). Enabling off‐road autonomous navigation—simulation of lidar in dense vegetation. Electronics, 7, 154. https://doi.org/10.3390/electronics7090154
Helgesen, K., Brekke, E., Helgesen, H. H., & Engelhardtsen. (2019). Sensor combinations in heterogeneous multi‐sensor fusion for maritime target tracking. In 2019 22nd International Conference on Information Fusion (FUSION) (pp. 1–9). https://doi.org/10.23919/fusion43075.2019.9011297
Lee, S., Yuan, Z., Petrunin, I., & Shin, H. (2024). Impact analysis of time synchronization error in airborne target tracking using a heterogeneous sensor network. Drones, 8, 167. https://doi.org/10.3390/drones8050167
Lee, W., Cho, H., Hyeong, S., & Chung, W. (2019). Practical modeling of GNSS for autonomous vehicles in urban environments. Sensors, 19, 4236. https://doi.org/10.3390/s19194236
Liu, H. (2020). Autonomous navigation for Mars exploration. In Mars Exploration: A Step Forward. https://doi.org/10.5772/intechopen.92093

Omori, M., Yoshitake, H., & Shino, M. (2024). Autonomous navigation for personal mobility vehicles considering passenger tolerance against approaching pedestrians. https://doi.org/10.21203/rs.3.rs-3825758/v1
Reddy, B. N. B., Pardhasaradhi, B., Srinath, G., & Srihari, P. (2022). Distributed fusion of optimally quantized local tracker estimates for underwater wireless sensor networks. IEEE Access, 10, 38982–38998. https://doi.org/10.1109/access.2022.3164515
Suleymanov, S., & Bayramov, A. A. (2023). Artificial intelligence application for unmanned aerial vehicle navigation. Modeling Control and Information Technologies, 21–24. https://doi.org/10.31713/mcit.2023.004
Wang, C., & Yu, H. (2023). Multiple attitude estimation models based on a pressure sensor array. Journal of Physics: Conference Series, 2456, 012001. https://doi.org/10.1088/1742-6596/2456/1/012001
Wei, W., Gao, Z., Gao, S., & Jia, K. (2018). A sins/srs/gns autonomous integrated navigation system based on spectral redshift velocity measurements. Sensors, 18, 1145. https://doi.org/10.3390/s18041145
Wu, Q. (2024). Research on autonomous mobile robot maze navigation problem based on Dijkstra’s algorithm. Applied and Computational Engineering, 39, 10–17. https://doi.org/10.54254/2755-2721/39/20230570
Yue, P., Xin, J., Zhang, Y., Lu, Y., & Shan, M. (2024). Semantic-driven autonomous visual navigation for unmanned aerial vehicles. IEEE Transactions on Industrial Electronics, 71, 14853–14863. https://doi.org/10.1109/tie.2024.3363761
Yu, P., Wei, W., Li, J., Wang, F., Zhang, L., & Chen, Z. (2023). An improved autonomous inertial-based integrated navigation scheme based on vehicle motion recognition. IEEE Access, 11, 104806–104816. https://doi.org/10.1109/access.2023.3318548
Zhang, K., Wang, Z., Guo, L., Peng, Y., & Zheng, Z. (2020). An asynchronous data fusion algorithm for target detection based on multi-sensor networks. IEEE Access, 8, 59511–59523. https://doi.org/10.1109/access.2020.2982682

Details

Primary Language

English

Subjects

Electrical Engineering (Other)

Journal Section

Research Article

Authors

Nurbanu Güzey ^*
0000-0002-6587-2489
Türkiye

Publication Date

December 3, 2025

Submission Date

March 20, 2025

Acceptance Date

August 6, 2025

Published in Issue

Year 2025 Volume: 28 Number: 4

DOI

https://doi.org/10.17780/ksujes.1661941

IZ

https://izlik.org/JA78HR68YF

Cite

RIS / Bibtex

APA

Güzey, N. (2025). MULTI-TARGET TRACKING WITH FEDERATED EXTENDED KALMAN FILTERS. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 28(4), 1703-1711. https://doi.org/10.17780/ksujes.1661941