EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Distinguishing a Drone from Birds Based on Trajectory Movement and Deep Learning

Andrii Nesteruk, Valerii Nikitin, Yosyp Albrekht iD, Łukasz Ścisło iD, Damian Grela iD, Paweł Król iD

Sensors · 2026

DOI: 10.3390/s26030755 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Andrii Nesteruk und 5 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Informatics and Computer Engineering, National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute", 37 Peremohy Ave…. Hauptthemen laut MEDLINE: Birds, Deep Learning, Unmanned Aerial Devices. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Unmanned aerial vehicles (UAVs) increasingly share low-altitude airspace with birds, making early distinguishing between drones and biological targets critical for safety and security. This work addresses long-range scenarios where objects occupy only a few pixels and appearance-based recognition becomes unreliable. We develop a model-driven simulation pipeline that generates synthetic data with a controlled camera model, atmospheric background and realistic motion of three aerial target types: multicopter, fixed-wing UAV and bird. From these sequences, each track is encoded as a time series of image-plane coordinates and apparent size, and a bidirectional long short-term memory (LSTM) network is trained to classify trajectories as drone-like or bird-like. The model learns characteristic differences in smoothness, turning behavior and velocity fluctuations, and to achieve reliable separation between drone and bird motion patterns on synthetic test data. Motion-trajectory cues alone can support early distinguishing of drones from birds when visual details are scarce, providing a complementary signal to conventional image-based detection. The proposed synthetic data and sequence classification pipeline forms a reproducible testbed that can be extended with real trajectories from radar or video tracking systems and used to prototype and benchmark trajectory-based recognizers for integrated surveillance solutions. The proposed method is designed to generalize naturally to real surveillance systems, as it relies on trajectory-level motion patterns rather than appearance-based features that are sensitive to sensor quality, illumination, or weather conditions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

BirdsDeep LearningUnmanned Aerial DevicesAnimalsLong Short Term MemoryAlgorithmsDetection AlgorithmsMovement

Stichwörter der Autor:innen

computer visiondrone detectioninformation technologieslong short-term memory (LSTM) networksmotion trajectory analysissynthetic datasetsunmanned aerial vehicles (UAVs)

Autor:innen und Institutionen

  • Faculty of Informatics and Computer Engineering, National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute", 37 Peremohy Ave., 03056 Kyiv, Ukraine.
  • Faculty of Electrical and Computer Engineering, Cracow University of Technology, Warszawska 24, 31-155 Cracow, Poland.

ORCID-Profile: Yosyp Albrekht, Łukasz Ścisło, Damian Grela, Paweł Król

Zitieren

APA

Nesteruk, A., Nikitin, V., Albrekht, Y., Ścisło, Ł., Grela, D., & Król, P. (2026). Distinguishing a Drone from Birds Based on Trajectory Movement and Deep Learning. Sensors. https://doi.org/10.3390/s26030755

Vancouver

Nesteruk A, Nikitin V, Albrekht Y, Ścisło Ł, Grela D, Król P. Distinguishing a Drone from Birds Based on Trajectory Movement and Deep Learning. Sensors. 2026. doi:10.3390/s26030755

BibTeX
@article{Nesteruk2026,
  author = {Nesteruk, Andrii and Nikitin, Valerii and Albrekht, Yosyp and Ścisło, Łukasz and Grela, Damian and Król, Paweł},
  title = {Distinguishing a Drone from Birds Based on Trajectory Movement and Deep Learning},
  journal = {Sensors},
  year = {2026},
  doi = {10.3390/s26030755}
}
Kostenlos starten →