Modification of DBSCAN and application to range/Doppler/DoA measurements for pedestrian recognition with an automotive radar system

Thomas Wagner; Reinhard Feger; Andreas Stelzer

doi:10.1109/EuRAD.2015.7346289

Modification of DBSCAN and application to range/Doppler/DoA measurements for pedestrian recognition with an automotive radar system

Thomas Wagner
, Reinhard Feger
, Andreas Stelzer

Department of RF-Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review

Abstract

We present in this paper modifications of the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm in order to detect pedestrians with a conventional automotive 77-GHz frequency modulated radar system. These modification include dimension scaling as preprocessing and a generalization of the ??-neighborhood notation by introducing a size parameter to constitute the new Ellipsoid DBSCAN (EDBSCAN) algorithm. With these modifications we could successfully cluster real-world measurement data in order to get reasonable cluster representations of pedestrians in a cluttered environment.

Original language	English
Title of host publication	Radar Conference (EuRAD), 2015 European
Pages	269-272
Number of pages	4
ISBN (Electronic)	9782874870415
DOIs	https://doi.org/10.1109/EuRAD.2015.7346289
Publication status	Published - Sept 2015

Fields of science

202019 High frequency engineering
202029 Microwave engineering
202033 Radar technology
202 Electrical Engineering, Electronics, Information Engineering

JKU Focus areas

Mechatronics and Information Processing

Access to Document

10.1109/EuRAD.2015.7346289

Cite this

@inproceedings{356c42b7b66a45dc98f0e834a2d70d4d,

title = "Modification of DBSCAN and application to range/Doppler/DoA measurements for pedestrian recognition with an automotive radar system",

abstract = "We present in this paper modifications of the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm in order to detect pedestrians with a conventional automotive 77-GHz frequency modulated radar system. These modification include dimension scaling as preprocessing and a generalization of the ??-neighborhood notation by introducing a size parameter to constitute the new Ellipsoid DBSCAN (EDBSCAN) algorithm. With these modifications we could successfully cluster real-world measurement data in order to get reasonable cluster representations of pedestrians in a cluttered environment.",

author = "Thomas Wagner and Reinhard Feger and Andreas Stelzer",

year = "2015",

month = sep,

doi = "10.1109/EuRAD.2015.7346289",

language = "English",

pages = "269--272",

booktitle = "Radar Conference (EuRAD), 2015 European",

}

TY - GEN

T1 - Modification of DBSCAN and application to range/Doppler/DoA measurements for pedestrian recognition with an automotive radar system

AU - Wagner, Thomas

AU - Feger, Reinhard

AU - Stelzer, Andreas

PY - 2015/9

Y1 - 2015/9

N2 - We present in this paper modifications of the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm in order to detect pedestrians with a conventional automotive 77-GHz frequency modulated radar system. These modification include dimension scaling as preprocessing and a generalization of the ??-neighborhood notation by introducing a size parameter to constitute the new Ellipsoid DBSCAN (EDBSCAN) algorithm. With these modifications we could successfully cluster real-world measurement data in order to get reasonable cluster representations of pedestrians in a cluttered environment.

AB - We present in this paper modifications of the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm in order to detect pedestrians with a conventional automotive 77-GHz frequency modulated radar system. These modification include dimension scaling as preprocessing and a generalization of the ??-neighborhood notation by introducing a size parameter to constitute the new Ellipsoid DBSCAN (EDBSCAN) algorithm. With these modifications we could successfully cluster real-world measurement data in order to get reasonable cluster representations of pedestrians in a cluttered environment.

UR - https://www.scopus.com/pages/publications/84962845343

U2 - 10.1109/EuRAD.2015.7346289

DO - 10.1109/EuRAD.2015.7346289

M3 - Conference proceedings

SP - 269

EP - 272

BT - Radar Conference (EuRAD), 2015 European

ER -

Modification of DBSCAN and application to range/Doppler/DoA measurements for pedestrian recognition with an automotive radar system

Abstract

Fields of science

JKU Focus areas

Access to Document

Other files and links

Cite this