Vision-based UAV detection and tracking using motion signatures

Pedro Alexandre Prates, Ricardo Mendonça, André Lourenço, Francisco Marques, J. P. Matos-Carvalho, Jose Barata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

This paper proposes a method for UAV detection and position extraction in video sequences obtained from a camera facing upwards towards the sky. The goal is for the presented model to act as groundwork for the development of a cooperative UAV autonomous landing system. It seeks to overcome most of the downfalls of pattern-based approaches by instead using the UAV's innate motion behaviours to perform detection. Seeing that the sky is a fairly stagnant environment, objects are detected through a Background Subtraction algorithm. As clouds generally present a slow and progressive movement they are to be considered part of the background and all other objects (e.g planes, birds, UAVs) as foreground. The irregular motion patterns of the UAV, especially of its propellers, are used to create a movement signature that distinguishes the UAV from other objects. The signature is classified as an entropy metric obtained from the resulting optical flow over a number of past frames. To further improve the detection rate, a tracking algorithm based on a Kalman filter was developed. Experimental results obtained from a dataset encompassing 12 diverse videos showed the ability of the computer vision algorithm to perform the tracking of the UAV with an average performance of 93.4%.

Original languageEnglish
Title of host publicationProceedings - 2018 IEEE Industrial Cyber-Physical Systems, ICPS 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages482-487
Number of pages6
ISBN (Electronic)9781538665312
DOIs
Publication statusPublished - 15 Jun 2018
Event1st IEEE International Conference on Industrial Cyber-Physical Systems, ICPS 2018 - Saint Petersburg, Russian Federation
Duration: 15 May 201818 May 2018

Conference

Conference1st IEEE International Conference on Industrial Cyber-Physical Systems, ICPS 2018
CountryRussian Federation
CitySaint Petersburg
Period15/05/1818/05/18

Fingerprint

Motion Tracking
Unmanned aerial vehicles (UAV)
Signature
Metric Entropy
Background Subtraction
Cooperative Systems
Motion
Optical Flow
Autonomous Systems
Computer Vision
Kalman Filter
Irregular
Camera
Aircraft landing systems
Experimental Results
Optical flows
Birds
Propellers
Vision
Object

Keywords

  • Autonomous Landing
  • Background Subtraction
  • Computer Vision
  • Kalman Filter
  • Optical Flow
  • Unmanned Aerial Vehicles

Cite this

Prates, P. A., Mendonça, R., Lourenço, A., Marques, F., Matos-Carvalho, J. P., & Barata, J. (2018). Vision-based UAV detection and tracking using motion signatures. In Proceedings - 2018 IEEE Industrial Cyber-Physical Systems, ICPS 2018 (pp. 482-487). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPHYS.2018.8390752
Prates, Pedro Alexandre ; Mendonça, Ricardo ; Lourenço, André ; Marques, Francisco ; Matos-Carvalho, J. P. ; Barata, Jose. / Vision-based UAV detection and tracking using motion signatures. Proceedings - 2018 IEEE Industrial Cyber-Physical Systems, ICPS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 482-487
@inproceedings{36932ff043de4c788bd40e1ed7c96476,
title = "Vision-based UAV detection and tracking using motion signatures",
abstract = "This paper proposes a method for UAV detection and position extraction in video sequences obtained from a camera facing upwards towards the sky. The goal is for the presented model to act as groundwork for the development of a cooperative UAV autonomous landing system. It seeks to overcome most of the downfalls of pattern-based approaches by instead using the UAV's innate motion behaviours to perform detection. Seeing that the sky is a fairly stagnant environment, objects are detected through a Background Subtraction algorithm. As clouds generally present a slow and progressive movement they are to be considered part of the background and all other objects (e.g planes, birds, UAVs) as foreground. The irregular motion patterns of the UAV, especially of its propellers, are used to create a movement signature that distinguishes the UAV from other objects. The signature is classified as an entropy metric obtained from the resulting optical flow over a number of past frames. To further improve the detection rate, a tracking algorithm based on a Kalman filter was developed. Experimental results obtained from a dataset encompassing 12 diverse videos showed the ability of the computer vision algorithm to perform the tracking of the UAV with an average performance of 93.4{\%}.",
keywords = "Autonomous Landing, Background Subtraction, Computer Vision, Kalman Filter, Optical Flow, Unmanned Aerial Vehicles",
author = "Prates, {Pedro Alexandre} and Ricardo Mendon{\cc}a and Andr{\'e} Louren{\cc}o and Francisco Marques and Matos-Carvalho, {J. P.} and Jose Barata",
note = "This work was partially funded by the CTS-UNINOVA multi-annual funding, through the PIDDAC Program funds.",
year = "2018",
month = "6",
day = "15",
doi = "10.1109/ICPHYS.2018.8390752",
language = "English",
pages = "482--487",
booktitle = "Proceedings - 2018 IEEE Industrial Cyber-Physical Systems, ICPS 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Prates, PA, Mendonça, R, Lourenço, A, Marques, F, Matos-Carvalho, JP & Barata, J 2018, Vision-based UAV detection and tracking using motion signatures. in Proceedings - 2018 IEEE Industrial Cyber-Physical Systems, ICPS 2018. Institute of Electrical and Electronics Engineers Inc., pp. 482-487, 1st IEEE International Conference on Industrial Cyber-Physical Systems, ICPS 2018, Saint Petersburg, Russian Federation, 15/05/18. https://doi.org/10.1109/ICPHYS.2018.8390752

Vision-based UAV detection and tracking using motion signatures. / Prates, Pedro Alexandre; Mendonça, Ricardo; Lourenço, André; Marques, Francisco; Matos-Carvalho, J. P.; Barata, Jose.

Proceedings - 2018 IEEE Industrial Cyber-Physical Systems, ICPS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 482-487.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Vision-based UAV detection and tracking using motion signatures

AU - Prates, Pedro Alexandre

AU - Mendonça, Ricardo

AU - Lourenço, André

AU - Marques, Francisco

AU - Matos-Carvalho, J. P.

AU - Barata, Jose

N1 - This work was partially funded by the CTS-UNINOVA multi-annual funding, through the PIDDAC Program funds.

PY - 2018/6/15

Y1 - 2018/6/15

N2 - This paper proposes a method for UAV detection and position extraction in video sequences obtained from a camera facing upwards towards the sky. The goal is for the presented model to act as groundwork for the development of a cooperative UAV autonomous landing system. It seeks to overcome most of the downfalls of pattern-based approaches by instead using the UAV's innate motion behaviours to perform detection. Seeing that the sky is a fairly stagnant environment, objects are detected through a Background Subtraction algorithm. As clouds generally present a slow and progressive movement they are to be considered part of the background and all other objects (e.g planes, birds, UAVs) as foreground. The irregular motion patterns of the UAV, especially of its propellers, are used to create a movement signature that distinguishes the UAV from other objects. The signature is classified as an entropy metric obtained from the resulting optical flow over a number of past frames. To further improve the detection rate, a tracking algorithm based on a Kalman filter was developed. Experimental results obtained from a dataset encompassing 12 diverse videos showed the ability of the computer vision algorithm to perform the tracking of the UAV with an average performance of 93.4%.

AB - This paper proposes a method for UAV detection and position extraction in video sequences obtained from a camera facing upwards towards the sky. The goal is for the presented model to act as groundwork for the development of a cooperative UAV autonomous landing system. It seeks to overcome most of the downfalls of pattern-based approaches by instead using the UAV's innate motion behaviours to perform detection. Seeing that the sky is a fairly stagnant environment, objects are detected through a Background Subtraction algorithm. As clouds generally present a slow and progressive movement they are to be considered part of the background and all other objects (e.g planes, birds, UAVs) as foreground. The irregular motion patterns of the UAV, especially of its propellers, are used to create a movement signature that distinguishes the UAV from other objects. The signature is classified as an entropy metric obtained from the resulting optical flow over a number of past frames. To further improve the detection rate, a tracking algorithm based on a Kalman filter was developed. Experimental results obtained from a dataset encompassing 12 diverse videos showed the ability of the computer vision algorithm to perform the tracking of the UAV with an average performance of 93.4%.

KW - Autonomous Landing

KW - Background Subtraction

KW - Computer Vision

KW - Kalman Filter

KW - Optical Flow

KW - Unmanned Aerial Vehicles

UR - http://www.scopus.com/inward/record.url?scp=85050146388&partnerID=8YFLogxK

U2 - 10.1109/ICPHYS.2018.8390752

DO - 10.1109/ICPHYS.2018.8390752

M3 - Conference contribution

SP - 482

EP - 487

BT - Proceedings - 2018 IEEE Industrial Cyber-Physical Systems, ICPS 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Prates PA, Mendonça R, Lourenço A, Marques F, Matos-Carvalho JP, Barata J. Vision-based UAV detection and tracking using motion signatures. In Proceedings - 2018 IEEE Industrial Cyber-Physical Systems, ICPS 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 482-487 https://doi.org/10.1109/ICPHYS.2018.8390752