Drone Classification Using Convolutional Neural Networks With Merged Doppler Images

We propose a drone classification method based on convolutional neural network (CNN) and micro-Doppler signature (MDS). The MDS only presents Doppler information in time domain. The frequency domain representation of MDS is called as cadence-velocity diagram (CVD). To analyze the Doppler information...

Full description

Saved in:
Bibliographic Details
Published in:IEEE geoscience and remote sensing letters 2017-01, Vol.14 (1), p.38-42
Main Authors: Kim, Byung Kwan, Kang, Hyun-Seong, Park, Seong-Ook
Format: Article
Language:English
Subjects:
Accuracy
Anechoic chambers
Artificial neural networks
Blades
Classification
Continuous wave radar
Convolutional neural network (CNN)
Doppler effect
Doppler sonar
Drones
Frequency dependence
Frequency domain analysis
Frequency modulation
Image classification
Methods
micro-Doppler signature (MDS)
Neural networks
Radar
Radar imaging
radar signal analysis
radar signal processing
Spectrogram
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose a drone classification method based on convolutional neural network (CNN) and micro-Doppler signature (MDS). The MDS only presents Doppler information in time domain. The frequency domain representation of MDS is called as cadence-velocity diagram (CVD). To analyze the Doppler information of drone in time and frequency domain, we propose a new image by merging MDS and CVD, as merged Doppler image. GoogLeNet, a CNN structure, is utilized for the proposed image data set because of its high performance and optimized computing resources. The image data set is generated by the returned Ku-band frequency modulation continuous wave radar signal. Proposed approach is tested and verified in two different environments, anechoic chamber and outdoor. First, we tested our approach with different numbers of operating motor and aspect angle of a drone. The proposed method improved the accuracy from 89.3% to 94.7%. Second, two types of drone at the 50 and 100 m height are classified and showed 100% accuracy due to distinct difference in the result images.
ISSN:1545-598X
1558-0571
DOI:10.1109/LGRS.2016.2624820