Practical classification of different moving targets using automotive radar and deep neural networks

In this work, the authors present results for classification of different classes of targets (car, single and multiple people, bicycle) using automotive radar data and different neural networks. A fast implementation of radar algorithms for detection, tracking, and micro-Doppler extraction is propos...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IET radar, sonar & navigation Ročník 12; číslo 10; s. 1082 - 1089
Hlavní autori:	Angelov, Aleksandar, Robertson, Andrew, Murray-Smith, Roderick, Fioranelli, Francesco
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	The Institution of Engineering and Technology 01.10.2018
Predmet:	automotive radar transceiver TEF810X convolutional neural network deep neural network Doppler radar electrical engineering computing microcontroller unit SR32R274 microcontrollers microDoppler extraction NXP Semiconductors object detection object tracking radar detection radar pre‐processing radar receivers radar tracking radar transmitters recurrent neural nets recurrent neural network residual neural network road vehicle radar signal classification Special Issue: Advanced Automotive Sensing – Towards Car Autonomy target classification time 0.5 s radar transmitters radar tracking electrical engineering computing radar detection recurrent neural network recurrent neural nets convolutional neural network radar pre-processing object detection microcontroller unit SR32R274 NXP Semiconductors signal classification target classification automotive radar transceiver TEF810X time 0.5 s residual neural network radar receivers object tracking microDoppler extraction Doppler radar road vehicle radar deep neural network microcontrollers
ISSN:	1751-8784, 1751-8792
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	In this work, the authors present results for classification of different classes of targets (car, single and multiple people, bicycle) using automotive radar data and different neural networks. A fast implementation of radar algorithms for detection, tracking, and micro-Doppler extraction is proposed in conjunction with the automotive radar transceiver TEF810X and microcontroller unit SR32R274 manufactured by NXP Semiconductors. Three different types of neural networks are considered, namely a classic convolutional network, a residual network, and a combination of convolutional and recurrent network, for different classification problems across the four classes of targets recorded. Considerable accuracy (close to 100% in some cases) and low latency of the radar pre-processing prior to classification (∼0.55 s to produce a 0.5 s long spectrogram) are demonstrated in this study, and possible shortcomings and outstanding issues are discussed.
ISSN:	1751-8784 1751-8792
DOI:	10.1049/iet-rsn.2018.0103