2015
DOI: 10.1049/el.2015.3038
|View full text |Cite
|
Sign up to set email alerts
|

Classification of loaded/unloaded micro‐drones using multistatic radar

Abstract: This letter presents preliminary results on the use of multistatic radar and micro-Doppler analysis to detect and discriminate between microdrones hovering carrying different payloads. Two suitable features related to the centroid of the micro-Doppler signature have been identified and used to perform classification, investigating also the added benefit of using information from a multistatic radar as opposed to a conventional monostatic system. Very good performance with accuracy above 90% has been demonstrat… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
70
0

Year Published

2016
2016
2021
2021

Publication Types

Select...
4
3
2

Relationship

1
8

Authors

Journals

citations
Cited by 129 publications
(71 citation statements)
references
References 9 publications
(14 reference statements)
1
70
0
Order By: Relevance
“…The centroid features extracted are the weighted centre of gravity and the bandwidth relative to this evaluated for each time sample within a spectrogram. This research presented here is an extension of the preliminary results shown in [15] which also utilized these centroid features. In this publication five different types of payloads rather than the previous limited set of three are successfully classified, and the effect on the classification performance of the duration of the data used for feature extraction is also investigated.…”
Section: Introductionmentioning
confidence: 92%
See 1 more Smart Citation
“…The centroid features extracted are the weighted centre of gravity and the bandwidth relative to this evaluated for each time sample within a spectrogram. This research presented here is an extension of the preliminary results shown in [15] which also utilized these centroid features. In this publication five different types of payloads rather than the previous limited set of three are successfully classified, and the effect on the classification performance of the duration of the data used for feature extraction is also investigated.…”
Section: Introductionmentioning
confidence: 92%
“…These features were briefly discussed and tested in our previous work in [15] where only three classes were considered, namely 0 g, 200 g, and 500 g payloads. The Doppler centroid is an estimation of the centre of gravity of the micro-Doppler signature, whereas the Doppler bandwidth provides an estimate of the signature bandwidth around the centroid.…”
Section: Centroid Featuresmentioning
confidence: 99%
“…In this case four features, namely the mean and standard deviation of both the Doppler centroid and bandwidth were used as input to the classifiers. These features have also been shown to be useful for classification in other domains [31], where it was shown how two features, namely the mean of the Doppler centroid and bandwidth, could be potentially used to discriminate between micro-drones hovering and flying while carrying different types of payloads. The Doppler centroid can be considered to be an estimate of the centre of gravity of the micro-Doppler signature, and the Doppler bandwidth calculates the energy extent of the micro-Doppler signature around the centroid, as described in [32], where these parameters were applied to characterise the signatures of wind turbines.…”
Section: Feature Extractionmentioning
confidence: 99%
“…Unlike camera images or sound concentrating microphones, radar is available in all weather conditions, because it is rarely hindered by rain or fog. In [2] and [3], for the drone detection, the uses of a continuous wave (CW) radar and a narrowband pulse radar have reported, respectively. These studies tried to detect and distinguish a drone from other flying objects such as birds and insects, by analyzing the Doppler signatures of the drone.…”
Section: Introductionmentioning
confidence: 99%