Efficient micro-doppler based pedestrian activity classification for ADAS systems using Krawtchouk moments

A.  Aßmann; A. Izzo; Carmine Clemente

Efficient micro-doppler based pedestrian activity classification for ADAS systems using Krawtchouk moments

A. Aßmann, A. Izzo, Carmine Clemente

Electronic And Electrical Engineering

Research output: Contribution to conference › Poster › peer-review

34 Downloads (Pure)

Abstract

In this paper the application, performance and results of a fully discrete micro-Doppler feature classication processing chain utilising Krawtchouk moment invariants are presented. The approach demonstrates to be capable of running on low power hardware such as the Raspberry Pi 2. The effectiveness of the proposed approach is veried through the use of real K-band data in real-time.

Original language	English
Number of pages	6
Publication status	Published - 14 Dec 2016
Event	11th IMA International Conference on Mathematics in Signal Processing - IET Austin Court, Birmingham, United Kingdom Duration: 12 Dec 2016 → 14 Dec 2016 http://www.ima.org.uk/conferences/conferences_calendar/11th_maths_in_signal_processing.html

Conference

Conference	11th IMA International Conference on Mathematics in Signal Processing
Country/Territory	United Kingdom
City	Birmingham
Period	12/12/16 → 14/12/16
Internet address	http://www.ima.org.uk/conferences/conferences_calendar/11th_maths_in_signal_processing.html

Keywords

micro-doppler
krawtchouk moments
Raspberry Pi
autonomous systems

Access to Document

Abmann-ICMSP-2016-Efficient-micro-doppler-based-pedestrian-activity-classificationAccepted author manuscript, 1.08 MB

Cite this

@conference{2c21231d89394f1899079fc74e2dcefe,

title = "Efficient micro-doppler based pedestrian activity classification for ADAS systems using Krawtchouk moments",

abstract = "In this paper the application, performance and results of a fully discrete micro-Doppler feature classication processing chain utilising Krawtchouk moment invariants are presented. The approach demonstrates to be capable of running on low power hardware such as the Raspberry Pi 2. The effectiveness of the proposed approach is veried through the use of real K-band data in real-time.",

keywords = "micro-doppler, krawtchouk moments, Raspberry Pi, autonomous systems",

author = "A. A{\ss}mann and A. Izzo and Carmine Clemente",

year = "2016",

month = dec,

day = "14",

language = "English",

note = "11th IMA International Conference on Mathematics in Signal Processing ; Conference date: 12-12-2016 Through 14-12-2016",

url = "http://www.ima.org.uk/conferences/conferences_calendar/11th_maths_in_signal_processing.html",

}

TY - CONF

T1 - Efficient micro-doppler based pedestrian activity classification for ADAS systems using Krawtchouk moments

AU - Aßmann, A.

AU - Izzo, A.

AU - Clemente, Carmine

PY - 2016/12/14

Y1 - 2016/12/14

N2 - In this paper the application, performance and results of a fully discrete micro-Doppler feature classication processing chain utilising Krawtchouk moment invariants are presented. The approach demonstrates to be capable of running on low power hardware such as the Raspberry Pi 2. The effectiveness of the proposed approach is veried through the use of real K-band data in real-time.

AB - In this paper the application, performance and results of a fully discrete micro-Doppler feature classication processing chain utilising Krawtchouk moment invariants are presented. The approach demonstrates to be capable of running on low power hardware such as the Raspberry Pi 2. The effectiveness of the proposed approach is veried through the use of real K-band data in real-time.

KW - micro-doppler

KW - krawtchouk moments

KW - Raspberry Pi

KW - autonomous systems

UR - https://ima.org.uk/1363/11th-ima-international-conference-mathematics-signal-processing/

M3 - Poster

T2 - 11th IMA International Conference on Mathematics in Signal Processing

Y2 - 12 December 2016 through 14 December 2016

ER -

Efficient micro-doppler based pedestrian activity classification for ADAS systems using Krawtchouk moments

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this