Statistical Image Segmentation and Region Classification Approaches for Automotive Radar

L. Daniel; Y. Xiao; E. Hoare; M. Cherniakov; M. Gashinova

doi:10.1109/EuRAD48048.2021.00042

Statistical Image Segmentation and Region Classification Approaches for Automotive Radar

L. Daniel, Y. Xiao, E. Hoare, M. Cherniakov, M. Gashinova

Electronic, Electrical and Systems Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper discusses statistical approaches currently being investigated to perform image segmentation and region classification in high resolution automotive radar imagery in the complex urban environment. The purpose is to identify the free traversable space ahead of the vehicle which would ultimately provide input into autonomous vehicle path planning algorithms. Three general methodologies are described, all based on the image region pixel intensity statistics which vary depending on the features within the imaged scene. Results show the promising potential for segmentation with these methods and some examples of segmentation and identification have been demonstrated for chosen road scene region types of asphalt, grass, shadow and objects/other.

Original language	English
Title of host publication	2020 17th European Radar Conference (EuRAD)
Publisher	IEEE
Pages	124-127
Number of pages	4
ISBN (Electronic)	9782874870613
ISBN (Print)	9781728170602 (PoD)
DOIs	https://doi.org/10.1109/EuRAD48048.2021.00042
Publication status	Published - 3 Feb 2021
Event	17th European Radar Conference, EuRAD 2020 - Utrecht, Netherlands Duration: 13 Jan 2021 → 15 Jan 2021

Publication series

Name	European Radar Conference (EURAD)

Conference

Conference	17th European Radar Conference, EuRAD 2020
Country/Territory	Netherlands
City	Utrecht
Period	13/01/21 → 15/01/21

Bibliographical note

Funding Information:
This work was supported by Jaguar Land Rover and the UK-EPSRC grant EP/N012372/1 as part of the jointly funded Towards Autonomy: Smart and Connected Control (TASCC) Programme

Publisher Copyright:
© 2021 EuMA.

Keywords

automotive
autonomous
classification
high resolution
radar imagery
segmentation
statistical

ASJC Scopus subject areas

Computer Networks and Communications
Signal Processing
Instrumentation

Access to Document

10.1109/EuRAD48048.2021.00042

Pervasive low-TeraHz and video sensing for car autonomy and driver assistance (PATH CAD)
Cherniakov, M. (Co-Investigator), Gardner, P. (Co-Investigator) & Gashinova, M. (Principal Investigator)
JAGUAR CARS LIMITED, Engineering & Physical Science Research Council
1/12/15 → 31/03/20
Project: Research

Cite this

@inproceedings{f3ccd5910b78466a911e4724f3c8a4d6,

title = "Statistical Image Segmentation and Region Classification Approaches for Automotive Radar",

abstract = "This paper discusses statistical approaches currently being investigated to perform image segmentation and region classification in high resolution automotive radar imagery in the complex urban environment. The purpose is to identify the free traversable space ahead of the vehicle which would ultimately provide input into autonomous vehicle path planning algorithms. Three general methodologies are described, all based on the image region pixel intensity statistics which vary depending on the features within the imaged scene. Results show the promising potential for segmentation with these methods and some examples of segmentation and identification have been demonstrated for chosen road scene region types of asphalt, grass, shadow and objects/other.",

keywords = "automotive, autonomous, classification, high resolution, radar imagery, segmentation, statistical",

author = "L. Daniel and Y. Xiao and E. Hoare and M. Cherniakov and M. Gashinova",

note = "Funding Information: This work was supported by Jaguar Land Rover and the UK-EPSRC grant EP/N012372/1 as part of the jointly funded Towards Autonomy: Smart and Connected Control (TASCC) Programme Publisher Copyright: {\textcopyright} 2021 EuMA.; 17th European Radar Conference, EuRAD 2020 ; Conference date: 13-01-2021 Through 15-01-2021",

year = "2021",

month = feb,

day = "3",

doi = "10.1109/EuRAD48048.2021.00042",

language = "English",

isbn = "9781728170602 (PoD)",

series = "European Radar Conference (EURAD)",

publisher = "IEEE",

pages = "124--127",

booktitle = "2020 17th European Radar Conference (EuRAD)",

}

Daniel, L, Xiao, Y, Hoare, E , Cherniakov, M & Gashinova, M 2021, Statistical Image Segmentation and Region Classification Approaches for Automotive Radar. in 2020 17th European Radar Conference (EuRAD)., 9337399, European Radar Conference (EURAD), IEEE, pp. 124-127, 17th European Radar Conference, EuRAD 2020, Utrecht, Netherlands, 13/01/21. https://doi.org/10.1109/EuRAD48048.2021.00042

TY - GEN

T1 - Statistical Image Segmentation and Region Classification Approaches for Automotive Radar

AU - Daniel, L.

AU - Xiao, Y.

AU - Hoare, E.

AU - Cherniakov, M.

AU - Gashinova, M.

N1 - Funding Information: This work was supported by Jaguar Land Rover and the UK-EPSRC grant EP/N012372/1 as part of the jointly funded Towards Autonomy: Smart and Connected Control (TASCC) Programme Publisher Copyright: © 2021 EuMA.

PY - 2021/2/3

Y1 - 2021/2/3

N2 - This paper discusses statistical approaches currently being investigated to perform image segmentation and region classification in high resolution automotive radar imagery in the complex urban environment. The purpose is to identify the free traversable space ahead of the vehicle which would ultimately provide input into autonomous vehicle path planning algorithms. Three general methodologies are described, all based on the image region pixel intensity statistics which vary depending on the features within the imaged scene. Results show the promising potential for segmentation with these methods and some examples of segmentation and identification have been demonstrated for chosen road scene region types of asphalt, grass, shadow and objects/other.

AB - This paper discusses statistical approaches currently being investigated to perform image segmentation and region classification in high resolution automotive radar imagery in the complex urban environment. The purpose is to identify the free traversable space ahead of the vehicle which would ultimately provide input into autonomous vehicle path planning algorithms. Three general methodologies are described, all based on the image region pixel intensity statistics which vary depending on the features within the imaged scene. Results show the promising potential for segmentation with these methods and some examples of segmentation and identification have been demonstrated for chosen road scene region types of asphalt, grass, shadow and objects/other.

KW - automotive

KW - autonomous

KW - classification

KW - high resolution

KW - radar imagery

KW - segmentation

KW - statistical

UR - http://www.scopus.com/inward/record.url?scp=85100887964&partnerID=8YFLogxK

U2 - 10.1109/EuRAD48048.2021.00042

DO - 10.1109/EuRAD48048.2021.00042

M3 - Conference contribution

AN - SCOPUS:85100887964

SN - 9781728170602 (PoD)

T3 - European Radar Conference (EURAD)

SP - 124

EP - 127

BT - 2020 17th European Radar Conference (EuRAD)

PB - IEEE

T2 - 17th European Radar Conference, EuRAD 2020

Y2 - 13 January 2021 through 15 January 2021

ER -

Statistical Image Segmentation and Region Classification Approaches for Automotive Radar

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Projects

Pervasive low-TeraHz and video sensing for car autonomy and driver assistance (PATH CAD)

Cite this