2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) 2023
DOI: 10.1109/icaiic57133.2023.10067042
|View full text |Cite
|
Sign up to set email alerts
|

Multi-Spectral Fusion using Generative Adversarial Networks for UAV Detection of Wild Fires

Abstract: 1 st Ta n m a y K a c k er S c h. of A er os p a c e Tr a ns p ort M a n uf a ct uri n g Cr a n fi el d U ni v ersit y , B e df or d, U K t a n m a y. k a c k er. 4 6 5 @ cr a n fi el d. a c. u k 2 n d A d olf o P err us q ui a C e ntr e f or A ut o. C y b er p h ysi c al S ys. Cr a n fi el d U ni v ersit y , B e df or d, U K A d olf o. P err us q ui a-G u z m a n @ cr a n fi el d. a c. u k 3 r d Weisi G u o C e ntr e f or A ut o. C y b er p h ysi c al S ys. Cr a n fi el d U ni v ersit y , B e df or d, U K w e… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3

Citation Types

0
2
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
5
1
1

Relationship

2
5

Authors

Journals

citations
Cited by 8 publications
(3 citation statements)
references
References 20 publications
0
2
0
Order By: Relevance
“…However, processing and analyzing such a volume of data requires the use of modern and effective tools. In this context, machine learning techniques such as extreme gradient boosting [4]- [6], logistic regression [7]- [9], and vanilla convolutional neural networks (vanilla CNN) [10]- [12] are emerging as promising tools that offer advanced solutions for wildfire management: prediction and early detection based on multispectral image analysis. The purpose of this study is to comparatively analyze the effectiveness and applicability of these machine learning methods in fire detection tasks.…”
Section: Introductionmentioning
confidence: 99%
“…However, processing and analyzing such a volume of data requires the use of modern and effective tools. In this context, machine learning techniques such as extreme gradient boosting [4]- [6], logistic regression [7]- [9], and vanilla convolutional neural networks (vanilla CNN) [10]- [12] are emerging as promising tools that offer advanced solutions for wildfire management: prediction and early detection based on multispectral image analysis. The purpose of this study is to comparatively analyze the effectiveness and applicability of these machine learning methods in fire detection tasks.…”
Section: Introductionmentioning
confidence: 99%
“…The spectrogram [4]- [8] is used as a feature representation in classification tasks. This generates a visual representation that can be exploited by machine learning or deep learning models, e.g, convolutional neural networks (CNNs) to detect spatial patterns associated to the profile [8]- [10], or recurrent neural networks (RNNs) [11], [12] to model timedependencies from consecutive visual frames. Other visual representations that can be further used includes: the range Doppler matrix [13], the cepstrogram [5], [14], or the Cadence velocity diagram (CVD) [14] which can enhance current drone detection and classification systems.…”
Section: Introductionmentioning
confidence: 99%
“…Here, the approaches are based on classification tasks using image sequences to predict pedestrian trajectories. Deep generative models [21], [22] have been applied to predict the long-term human trajectory conditioned on the long-term objective of the task. In terms of drone intent prediction, genetic algorithms have been adopted to model dangerous drone intents using a support vector regressor (SVR) model of the drone kinematics based on ADS-B flight data [2].…”
Section: Introductionmentioning
confidence: 99%