Analysis of data from drones for surveillance and threat identification in maritime areas

pdf
Published: Sep 4, 2024
DOI: https://doi.org/10.12681/elrie.7273
Fotios Lampropoulos
Abstract

Introduction


Innovative and functional AI Drones (Artificial Intelligence Unmanned Aircraft) systems, commonly known as 'drones', have revolutionized fields such as civil protection, maritime and land surveillance, natural disaster management and threat monitoring in public spaces. More than ever, drones are coming into our daily lives to improve public safety in search and rescue, to identify important information from digital images, video and other visual inputs to take action and increase efficiency in saving lives. . One of the most important applications of drones is in maritime and land surveillance and threat identification, they are used to monitor vast sea areas, detect criminal and criminal activities and prevent any incident in maritime areas. These drones have the ability to move more efficiently than traditional surveillance methods in a short amount of time. In addition, drones equipped with high-resolution sensors and thermal cameras can detect threats such as illegal fishing, oil spills, drownings, lifeboats and other public hazards.


There are many benefits to drones playing key problem-solving roles in various fields such as maritime security, but there are also some individual limitations. One of the most basic constraints is the regulations surrounding the use of smart UAVs (Unmanned Aerial Vehicles). In some areas, their use is restricted and requires special permission. In fact, smart UAVs are particularly popular that use artificial intelligence (AI) in real time, allowing rapid data analysis, recording of the marine space which thanks to the artificial intelligence software can perceive the incident, identify objects and provide real-time analytical feedback processing. Artificial intelligence UAVs (Unmanned Aerial Vehicles) commonly known as "drones" research their approach, helping with positive results in the coordination of prevention of dangerous situations and the mission of search and rescue.


 


Keywords: Artificial Intelligence, Smart UAV, Real-Time, Object Detection, Deep learning.

Article Details
  • Section
  • Εισηγήσεις
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors retain copyright under a Creative Commons Attribution that allows others to share the work with an acknowledgement of the work's authorship and initial publication in the proceedings.
References
A review on deep learning in UAV remote sensing by: https://www.sciencedirect.com/science/article/pii/S030324342100163X.
Allan, B.M., Ierodiaconou, D., Hoskins, A.J. & Arnould, J.P.Y.(2019) A rapid UAV method for assessing body conditionin fur seals.Drones,3, 24.
Anna Gąszczak , Toby P.Breckona , Jiwan Hana aCranfield University, School of Engineering, United Kingdom
Audebert, N., Le Saux, B., Lefevre, S., 2019. Deep learning for classification ofhyperspectral data: A comparative review. IEEE Geosci. Remote Sens. Mag. 7,159–173. https://doi.org/10.1109/MGRS.2019.2912563 arXiv:1904.10674.
Barbedo, J.G.A., Koenigkan, L.V., Santos, P.M., Ribeiro, A.R.B., 2020. Counting cattle in UAV images-dealing with clustered animals and animal/background contrast changes. Sensors 20. https://doi.org/10.3390/s20072126 & https://www.mdpi.com/1424-8220/20/7/2126.
Barbedo, J.G.A., Koenigkan, L.V., Santos, T.T., Santos, P.M., 2019. A study on the detection of cattle in UAV images using deep learning. Sensors (Switzerland) 19, 1–14. https://doi.org/10.3390/s19245436.
Bithas, P.S., Michailidis, E.T., Nomikos, N., Vouyioukas, D., Kanatas, A.G., 2019. A survey on machine-learning techniques for UAV-based communications. Sensors (Switzerland) 19, 1–39. https://doi.org/10.3390/s19235170.
Bradski, Gary, and Adrian Kaehler. "Learning OpenCV: Computer vision with the OpenCV library." (2008).
Ceif G , (2018), «Deep Learning vs Classical Machine Learning» , available on the website:https://towardsdatascience.com/deeplearning-vs-classicalmachine-learning-9a42c6d48aa.
De Oliveira, D.C., Wehrmeister, M.A., 2018. Using deep learning and low-cost rgb and thermal cameras to detect pedestrians in aerial images captured by multirotor UAV. Sensors (Switzerland) 18. https://doi.org/10.3390/s18072244.
Deep learning-based strategies for the detection and tracking of drones using several cameras από: https://ipsjcva.springeropen.com/articles/10.1186/s41074-019-0059-x?trk=public_post_comment-text.
Detection and tracking of belugas, kayaks and motorized boats in drone video using deep learning από https://cdnsciencepub.com/doi/10.1139/juvs-2021-0024.
Dian Bah, M., Hafiane, A., Canals, R., 2018. Deep learning with unsupervised data labeling for weed detection in line crops in UAV images. Remote Sens. 10, 1–22. https://doi.org/10.3390/rs10111690.
Dinan S (2017) Drones become latest tool drug cartels use to smuggle drugs into u.s. https://www.washingtontimes.com/news/2017/aug/20/mexican-drug-cartels-using-drones-to-smuggle-heroi/.
DroneSAR|Emergency Response specific software for DJI drones. https://www.dronesarpilot.com
Fu, Y., Kinniry, M. & Kloepper, L.N. (2018) The Chirocopter:a UAV for recording sound and video of bats at altitude. Methods in Ecology and Evolution,9, 1531–1535.
Gallagher S (2013) German chancellor’s drone ‘attack’ shows the threat ofweaponized UAVs. Ars Technica.
Gaspar, T., Oliveira, P. & Silvestre, C. (2011) UAV-basedmarine mammals positioning and tracking system. In:Proceedings of the 2011 IEEE International Conference onMechatronics and Automation. Beijing, China, pp.1050–1055.
Girshick, Ross, et al. "Rich feature hierarchies for accurate object detection and semantic segmentation." Proceedings of the IEEE conference on computer vision and pattern recognition. 2014.
Hammer M, Hebel M, Laurenzis M, Arens M (2018) Lidar-based detection and tracking of small uavs. In: Emerging Imaging and Sensing Technologies for Security and Defence III and Unmanned Sensors, Systems, and Countermeasures, vol. 10799. International Society for Optics and Photonics. p 107990
Liu H, Wei Z, Chen Y, Pan J, Lin L, Ren Y (2017) Drone detection based onan audio-assisted camera array. In: Multimedia Big Data (BigMM), 2017 IEEE Third International Conference On. IEEE. pp 402–406.
Müller T (2017) Robust drone detection for day/night counter-UAV with static vis and swir cameras. In: Ground/Air Multisensor Interoperability,Integration, and Networking for Persistent ISR VIII, vol. 10190. International Society for Optics and Photonics. p 1019018.
Nils Tijtgat, Bruno Volckaert, Toon Goedemé, Gent, Belgium, Technologiecampus DE NAYER, Katholieke Universiteit Leuven, Leuven, Flanders, BE
Redmon, Joseph, et al. "You only look once: Unified, real-time object detection." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
Schumann A, Sommer L, Klatte J, Schuchert T, Beyerer J (2017) Deep cross-domain flying object classification for robust UAV detection. In: Advanced Video and Signal Based Surveillance (AVSS), 2017 14th IEEE International Conference On. IEEE. pp 1–6.
Shalev-Shwartz, Shai, and Shai Ben-David. Understanding machine learning: From theory to algorithms. Cambridge university press, 2014.
Thomas Moranduzzo, Farid Melgani, Yakoub Bazi, Naif Alajlan, International Journal of Remote Sensing, 2015
Zhang L, Young S (2018) China busts smugglers using drones to transport smartphones: state media. https://www.reuters.com/article/us-chinacrime-smartphones-smugglers/china-busts-smugglers-using-dronesto-transport-smartphones-state-media-idUSKBN1H60BT.