2022
DOI: 10.1109/access.2022.3162866
|View full text |Cite
|
Sign up to set email alerts
|

DroneSense: The Identification, Segmentation, and Orientation Detection of Drones via Neural Networks

Abstract: The growing ubiquity of drones has raised concerns over the ability of traditional air-space monitoring technologies to accurately characterise such vehicles. Here, we present a CNN using a decision tree and ensemble structure to fully characterise drones in flight. Our system determines the drone type, orientation (in terms of pitch, roll, and yaw), and performs segmentation to classify different body parts (engines, body, and camera). We also provide a computer model for the rapid generation of large quantit… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
5
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6
2
1

Relationship

2
7

Authors

Journals

citations
Cited by 15 publications
(5 citation statements)
references
References 117 publications
0
5
0
Order By: Relevance
“…Optical sensors include cameras, gated lasers, and other visual sensing modalities that perform optical processing. The use of optical sensors provides another approach to detect and classify UAVs [129]. Similar to using radars, there are two approaches for deploying optical sensors: active and passive.…”
Section: Optical Sensorsmentioning
confidence: 99%
“…Optical sensors include cameras, gated lasers, and other visual sensing modalities that perform optical processing. The use of optical sensors provides another approach to detect and classify UAVs [129]. Similar to using radars, there are two approaches for deploying optical sensors: active and passive.…”
Section: Optical Sensorsmentioning
confidence: 99%
“…The ability to measure depth has led to SPADs being used in a wide range of applications, for instance: exploiting the single-photon sensitivity to image underwater 6 , through obscurants 7 , 8 or at long range 9 , 10 ; or, leveraging temporal gating to image ‘through’ nets 11 , 12 or to view the flight of a laser pulse 13 , 14 . More recently, SPAD-based Lidars have been examined for automotive applications 15 – 17 as well as for machine vision tasks including gesture recognition 18 , 19 , identification 20 , drone tracking 21 , and pose detection 22 . The growing number of SPAD based imaging applications highlights the need to develop imaging systems which can resolve fine depth features at high acquisition rates.…”
Section: Introductionmentioning
confidence: 99%
“…The applications of DL are wide and varied. They have seen use in audio denoising [ 7 ], land classification from satellite images [ 8 ], self-driving cars [ 9 ], drone detection [ 10 ], and more. Over the past decade, DL has also been used for plant stress phenotyping, primarily using image data [ 11 , 12 ].…”
Section: Introductionmentioning
confidence: 99%