Tracking Analysis of Drone Detection Systems at Airports: Methodology and Results

Heidger, Ralf; Lambercy, Vincent; Lambers, Douwe

doi:10.23919/irs51887.2021.9466192

Cited by 2 publications

(4 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Coverage aspects are also moderately covered and tend to lean towards strong consideration in some papers. 16,34 The Inspection of measures A_DDS_Entropy, A_DDS_Entropy_Index in subtables of scenario scoring sheets T7-T9 (Figure 7) and scoring sheets T7'-T9'(Figure 8) reveal that artifacts identified by (1), 16 (3), 18 (4), 19 (6), 21 (9), 2 (14), 27 (16), 1 (17), 29 (18), 30 and ( 22), 34 provide significant information covering most aspects. Pyrgies 26 presents a "defense-in-depth" approach organized into five concentric layers: prevention, deterrence, detection, interruption, and destruction.…”

Section: Airport Scenario Survey Summarymentioning

confidence: 99%

“…Therefore, one can easily use this table to find out the level of discussions or treatment of an aspect that one is examining. Again, looking up S7 (Figure 7), one can assess that “system threat” aspects are dealt with in sufficiently great detail in Eriksson, 16 while “processing requirements” are strongly dealt with in Heidger et al 18 . Artifacts may be compared against one another using the following measures:

\begin{eqnarray} && DDS\_Entropy _{(Artifact)} = \sum _{n=1}^{No.\:of Sys.Reqt/Drivers}\nonumber\\ &&\quad {(Computed\:Cell\:Value\:of\:Sys Reqt/Driver_{n}),} \end{eqnarray}

$$\begin{eqnarray...

…”

Section: The Survey and Measures For Analysismentioning

confidence: 99%

“…CNN (convolutional neural network) and AI are promising for video processing. Inspection of measures A_DDS_Entropy, A_DDS_Entropy_Index in subtables of scenario scoring sheets T7–T9 (Figure 7) and scoring sheets T7'–T9'(Figure 8) reveal that artifacts identified by (1), 16 (3), 18 (4), 19 (6), 21 (9), 2 (14), 27 (16), 1 (17), 29 (18), 30 and (22), 34 provide significant information covering most aspects.…”

Section: The Survey and Measures For Analysismentioning

confidence: 99%

“…Again, looking up S7 (Figure 7), one can assess that "system threat" aspects are dealt with in sufficiently great detail in Eriksson, 16 while "processing requirements" are strongly dealt with in Heidger et al 18 Artifacts may be compared against one another using the following measures:…”

mentioning

confidence: 99%

See 3 more Smart Citations

A survey and analysis of drone detection systems using a systems approach superposed on scenarios

Kashi,

Prashanth,

Kashi

et al. 2023

Systems Engineering

View full text Add to dashboard Cite

The proliferation of drones in civil and military applications has brought about new challenges in the context of safety and security considerations of operational aspects. The use of small‐ and medium‐sized drones in civilian airspaces even with regulatory approval may not provide guarantees of safety and security. Detection of drones is the first step towards providing a mitigating mechanism for challenges posed by mal‐intentioned drones. Sensors and their characteristics affecting the detection process are discussed. A figure of merit is proposed to compare systems employing these sensors. The key focus of the paper is the examination of the spectrum of drone detection systems (DDS) using a systems‐based approach applied to scenarios. In order to make an equitable comparison between systems, two scenarios are utilized to discuss system characteristics. Next, a survey of DDS in each of these scenarios is performed. Artifacts are analyzed, culling information using the systems model. An approach is proposed to perform evaluation of these artifacts using a scoring mechanism. Simple yet novel measures to assess the information content pertaining to DDS are presented. This approach enables researchers, system architects, system designers, solution providers, and system integrators to be aware of various challenges at the system and subsystem level. The proposed method helps to provide pointers to the literature where information about challenges and specific solutions can be obtained.

show abstract

Section: Airport Scenario Survey Summarymentioning

confidence: 99%

\begin{eqnarray} && DDS\_Entropy _{(Artifact)} = \sum _{n=1}^{No.\:of Sys.Reqt/Drivers}\nonumber\\ &&\quad {(Computed\:Cell\:Value\:of\:Sys Reqt/Driver_{n}),} \end{eqnarray}

$$\begin{eqnarray...

…”

Section: The Survey and Measures For Analysismentioning

confidence: 99%

Section: The Survey and Measures For Analysismentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

A survey and analysis of drone detection systems using a systems approach superposed on scenarios

Kashi,

Prashanth,

Kashi

et al. 2023

Systems Engineering

View full text Add to dashboard Cite

show abstract

MUSAK: A Multi-Scale Space Kinematic Method for Drone Detection

Liu

Zhan

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Accurate and robust drone detection is an important and challenging task. However, on this issue, previous research, whether based on appearance or motion features, has not yet provided a satisfactory solution, especially under a complex background. To this end, the present work proposes a motion-based method termed the Multi-Scale Space Kinematic detection method (MUSAK). It fully leverages the motion patterns by extracting 3D, pseudo 3D and 2D kinematic parameters at three scale spaces according to the keypoints quality and builds three Gated Recurrent Unit (GRU)-based detection branches for drone recognition. The MUSAK method is evaluated on a hybrid dataset named multiscale UAV dataset (MUD), consisting of public datasets and self-collected data with motion labels. The experimental results show that MUSAK improves the performance by a large margin, a 95% increase in average precision (AP), compared with the previous state-of-the-art (SOTA) motion-based methods, and the hybrid MUSAK method, which integrates with the appearance-based method Faster Region-based Convolutional Neural Network (Faster R-CNN), achieves a new SOTA performance on AP metrics (AP, APM, and APS).

show abstract

Tracking Analysis of Drone Detection Systems at Airports: Methodology and Results

Cited by 2 publications

References 1 publication

A survey and analysis of drone detection systems using a systems approach superposed on scenarios

A survey and analysis of drone detection systems using a systems approach superposed on scenarios

MUSAK: A Multi-Scale Space Kinematic Method for Drone Detection

Contact Info

Product

Resources

About