Visual Drone Detection and Tracking for Autonomous Operation from Maritime Vessel

Timothy Halleux; Tien Thanh Nguyen; Charles Hamesse; Geert De Cubber; Bart Janssens

doi:10.1109/ISMCR56534.2022.9950568

Visual Drone Detection and Tracking for Autonomous Operation from Maritime Vessel

Timothy Halleux, Tien Thanh Nguyen, Charles Hamesse, Geert De Cubber, Bart Janssens

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

To allow incorporation of autonomous Unmanned Aerial Vehicles (UAV's/drones) into maritime military operations, it is critical to be able to accurately localize the UAV with respect to the moving maritime vessel during the take-off and landing phases. This work addresses the study and implementation of a visual detection, tracking and three-dimensional positioning method for a specific drone from a moving maritime vessel. The YOLOv5 detector and the OceanPlus tracker have been trained on a custom dataset with good performance in accuracy and processing time. The drone's position with respect to the vessel is estimated by applying stereo triangulation to the centres of the bounding boxes returned by the object detectors and trackers. The performance of the proposed positioning method was evaluated in a realistic simulated environment in the Unreal Game Engine. The proposed method allows detection, tracking, and positioning of a target drone at ranges exceeding 100m while achieving positioning errors below 10cm during landing phases.

Original language	English
Title of host publication	Proceedings - International Symposium on Measurement and Control in Robotics
Subtitle of host publication	Robotics and Virtual Tools for a New Era, ISMCR 2022
Editors	Zafar Taqvi, Simone Keller Fuchter, Geraldo Gurgel Filho
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665454964
DOIs	https://doi.org/10.1109/ISMCR56534.2022.9950568
Publication status	Published - 2022
Event	25th International Symposium on Measurement and Control in Robotics, ISMCR 2022 - Virtual, Online, United States Duration: 28 Sept 2022 → 30 Sept 2022

Publication series

Name	Proceedings - International Symposium on Measurement and Control in Robotics: Robotics and Virtual Tools for a New Era, ISMCR 2022

Conference

Conference	25th International Symposium on Measurement and Control in Robotics, ISMCR 2022
Country/Territory	United States
City	Virtual, Online
Period	28/09/22 → 30/09/22

Keywords

Object Detection
Tracking
UAV
synthetic data
Robotics

Access to Document

10.1109/ISMCR56534.2022.9950568

Cite this

Halleux, T., Nguyen, T. T., Hamesse, C., De Cubber, G., & Janssens, B. (2022). Visual Drone Detection and Tracking for Autonomous Operation from Maritime Vessel. In Z. Taqvi, S. K. Fuchter, & G. G. Filho (Eds.), Proceedings - International Symposium on Measurement and Control in Robotics: Robotics and Virtual Tools for a New Era, ISMCR 2022 (Proceedings - International Symposium on Measurement and Control in Robotics: Robotics and Virtual Tools for a New Era, ISMCR 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISMCR56534.2022.9950568

Halleux, Timothy ; Nguyen, Tien Thanh ; Hamesse, Charles et al. / Visual Drone Detection and Tracking for Autonomous Operation from Maritime Vessel. Proceedings - International Symposium on Measurement and Control in Robotics: Robotics and Virtual Tools for a New Era, ISMCR 2022. editor / Zafar Taqvi ; Simone Keller Fuchter ; Geraldo Gurgel Filho. Institute of Electrical and Electronics Engineers Inc., 2022. (Proceedings - International Symposium on Measurement and Control in Robotics: Robotics and Virtual Tools for a New Era, ISMCR 2022).

@inproceedings{5becd6e6f684452f9a0fb1e27d0096f3,

title = "Visual Drone Detection and Tracking for Autonomous Operation from Maritime Vessel",

abstract = "To allow incorporation of autonomous Unmanned Aerial Vehicles (UAV's/drones) into maritime military operations, it is critical to be able to accurately localize the UAV with respect to the moving maritime vessel during the take-off and landing phases. This work addresses the study and implementation of a visual detection, tracking and three-dimensional positioning method for a specific drone from a moving maritime vessel. The YOLOv5 detector and the OceanPlus tracker have been trained on a custom dataset with good performance in accuracy and processing time. The drone's position with respect to the vessel is estimated by applying stereo triangulation to the centres of the bounding boxes returned by the object detectors and trackers. The performance of the proposed positioning method was evaluated in a realistic simulated environment in the Unreal Game Engine. The proposed method allows detection, tracking, and positioning of a target drone at ranges exceeding 100m while achieving positioning errors below 10cm during landing phases.",

keywords = "Object Detection, Tracking, UAV, synthetic data, Robotics",

author = "Timothy Halleux and Nguyen, {Tien Thanh} and Charles Hamesse and {De Cubber}, Geert and Bart Janssens",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 25th International Symposium on Measurement and Control in Robotics, ISMCR 2022 ; Conference date: 28-09-2022 Through 30-09-2022",

year = "2022",

doi = "10.1109/ISMCR56534.2022.9950568",

language = "English",

series = "Proceedings - International Symposium on Measurement and Control in Robotics: Robotics and Virtual Tools for a New Era, ISMCR 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Zafar Taqvi and Fuchter, {Simone Keller} and Filho, {Geraldo Gurgel}",

booktitle = "Proceedings - International Symposium on Measurement and Control in Robotics",

}

Halleux, T, Nguyen, TT , Hamesse, C , De Cubber, G & Janssens, B 2022, Visual Drone Detection and Tracking for Autonomous Operation from Maritime Vessel. in Z Taqvi, SK Fuchter & GG Filho (eds), Proceedings - International Symposium on Measurement and Control in Robotics: Robotics and Virtual Tools for a New Era, ISMCR 2022. Proceedings - International Symposium on Measurement and Control in Robotics: Robotics and Virtual Tools for a New Era, ISMCR 2022, Institute of Electrical and Electronics Engineers Inc., 25th International Symposium on Measurement and Control in Robotics, ISMCR 2022, Virtual, Online, United States, 28/09/22. https://doi.org/10.1109/ISMCR56534.2022.9950568

Visual Drone Detection and Tracking for Autonomous Operation from Maritime Vessel. / Halleux, Timothy; Nguyen, Tien Thanh ; Hamesse, Charles et al.
Proceedings - International Symposium on Measurement and Control in Robotics: Robotics and Virtual Tools for a New Era, ISMCR 2022. ed. / Zafar Taqvi; Simone Keller Fuchter; Geraldo Gurgel Filho. Institute of Electrical and Electronics Engineers Inc., 2022. (Proceedings - International Symposium on Measurement and Control in Robotics: Robotics and Virtual Tools for a New Era, ISMCR 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Visual Drone Detection and Tracking for Autonomous Operation from Maritime Vessel

AU - Halleux, Timothy

AU - Nguyen, Tien Thanh

AU - Hamesse, Charles

AU - De Cubber, Geert

AU - Janssens, Bart

PY - 2022

Y1 - 2022

N2 - To allow incorporation of autonomous Unmanned Aerial Vehicles (UAV's/drones) into maritime military operations, it is critical to be able to accurately localize the UAV with respect to the moving maritime vessel during the take-off and landing phases. This work addresses the study and implementation of a visual detection, tracking and three-dimensional positioning method for a specific drone from a moving maritime vessel. The YOLOv5 detector and the OceanPlus tracker have been trained on a custom dataset with good performance in accuracy and processing time. The drone's position with respect to the vessel is estimated by applying stereo triangulation to the centres of the bounding boxes returned by the object detectors and trackers. The performance of the proposed positioning method was evaluated in a realistic simulated environment in the Unreal Game Engine. The proposed method allows detection, tracking, and positioning of a target drone at ranges exceeding 100m while achieving positioning errors below 10cm during landing phases.

AB - To allow incorporation of autonomous Unmanned Aerial Vehicles (UAV's/drones) into maritime military operations, it is critical to be able to accurately localize the UAV with respect to the moving maritime vessel during the take-off and landing phases. This work addresses the study and implementation of a visual detection, tracking and three-dimensional positioning method for a specific drone from a moving maritime vessel. The YOLOv5 detector and the OceanPlus tracker have been trained on a custom dataset with good performance in accuracy and processing time. The drone's position with respect to the vessel is estimated by applying stereo triangulation to the centres of the bounding boxes returned by the object detectors and trackers. The performance of the proposed positioning method was evaluated in a realistic simulated environment in the Unreal Game Engine. The proposed method allows detection, tracking, and positioning of a target drone at ranges exceeding 100m while achieving positioning errors below 10cm during landing phases.

KW - Object Detection

KW - Tracking

KW - UAV

KW - synthetic data

KW - Robotics

UR - http://www.scopus.com/inward/record.url?scp=85143805257&partnerID=8YFLogxK

U2 - 10.1109/ISMCR56534.2022.9950568

DO - 10.1109/ISMCR56534.2022.9950568

M3 - Conference contribution

AN - SCOPUS:85143805257

T3 - Proceedings - International Symposium on Measurement and Control in Robotics: Robotics and Virtual Tools for a New Era, ISMCR 2022

BT - Proceedings - International Symposium on Measurement and Control in Robotics

A2 - Taqvi, Zafar

A2 - Fuchter, Simone Keller

A2 - Filho, Geraldo Gurgel

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 25th International Symposium on Measurement and Control in Robotics, ISMCR 2022

Y2 - 28 September 2022 through 30 September 2022

ER -

Halleux T, Nguyen TT , Hamesse C , De Cubber G , Janssens B. Visual Drone Detection and Tracking for Autonomous Operation from Maritime Vessel. In Taqvi Z, Fuchter SK, Filho GG, editors, Proceedings - International Symposium on Measurement and Control in Robotics: Robotics and Virtual Tools for a New Era, ISMCR 2022. Institute of Electrical and Electronics Engineers Inc. 2022. (Proceedings - International Symposium on Measurement and Control in Robotics: Robotics and Virtual Tools for a New Era, ISMCR 2022). doi: 10.1109/ISMCR56534.2022.9950568

Visual Drone Detection and Tracking for Autonomous Operation from Maritime Vessel

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

MarLand: Automated take-off and landing of unmanned vehicles from Belgian Navy vessels

COURAGEOUS: Building a common understanding of the effectiveness of counter-UAS solutions

Cite this

Visual Drone Detection and Tracking for Autonomous Operation from Maritime Vessel

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Projects

MarLand: Automated take-off and landing of unmanned vehicles from Belgian Navy vessels

COURAGEOUS: Building a common understanding of the effectiveness of counter-UAS solutions

Cite this