Illumination invariant road detection based on learning method

Bongjoe Kim; Jongin Son; Kwanghoon Sohn

doi:10.1109/ITSC.2011.6082917

Illumination invariant road detection based on learning method

Bongjoe Kim, Jongin Son, Kwanghoon Sohn

Department of Electrical and Electronic Engineering

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

13 Citations (Scopus)

Abstract

Road detection is an essential and important component in intelligent transportation system (ITS). Generally, most road detection methods are sensitive to variation of illumination which results in increasing false detection rate. In this paper, we propose an illumination invariant road detection method to deal with variation of illumination. We adopt learning method to estimate illumination invariant direction which is specified to road surface. Once this direction is estimated, we can classify image pixel as road or not. Incorporating scene layout of road image, we reduce false positive detection rate outside the road. Experimental results on real road scenes show that the effectiveness of the proposed method.

Original language	English
Title of host publication	2011 14th International IEEE Conference on Intelligent Transportation Systems, ITSC 2011
Pages	1009-1014
Number of pages	6
DOIs	https://doi.org/10.1109/ITSC.2011.6082917
Publication status	Published - 2011
Event	14th IEEE International Intelligent Transportation Systems Conference, ITSC 2011 - Washington, DC, United States Duration: 2011 Oct 5 → 2011 Oct 7

Publication series

Name	IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC

Other

Other	14th IEEE International Intelligent Transportation Systems Conference, ITSC 2011
Country	United States
City	Washington, DC
Period	11/10/5 → 11/10/7

All Science Journal Classification (ASJC) codes

Automotive Engineering
Mechanical Engineering
Computer Science Applications

Access to Document

10.1109/ITSC.2011.6082917

Fingerprint Dive into the research topics of 'Illumination invariant road detection based on learning method'. Together they form a unique fingerprint.

Cite this

Kim, B., Son, J., & Sohn, K. (2011). Illumination invariant road detection based on learning method. In 2011 14th International IEEE Conference on Intelligent Transportation Systems, ITSC 2011 (pp. 1009-1014). [6082917] (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC). https://doi.org/10.1109/ITSC.2011.6082917

@inproceedings{e697ea802d4c4dc3b3d12603b09643d2,

title = "Illumination invariant road detection based on learning method",

abstract = "Road detection is an essential and important component in intelligent transportation system (ITS). Generally, most road detection methods are sensitive to variation of illumination which results in increasing false detection rate. In this paper, we propose an illumination invariant road detection method to deal with variation of illumination. We adopt learning method to estimate illumination invariant direction which is specified to road surface. Once this direction is estimated, we can classify image pixel as road or not. Incorporating scene layout of road image, we reduce false positive detection rate outside the road. Experimental results on real road scenes show that the effectiveness of the proposed method.",

author = "Bongjoe Kim and Jongin Son and Kwanghoon Sohn",

year = "2011",

doi = "10.1109/ITSC.2011.6082917",

language = "English",

isbn = "9781457721984",

series = "IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC",

pages = "1009--1014",

booktitle = "2011 14th International IEEE Conference on Intelligent Transportation Systems, ITSC 2011",

note = "14th IEEE International Intelligent Transportation Systems Conference, ITSC 2011 ; Conference date: 05-10-2011 Through 07-10-2011",

}

Kim, B, Son, J & Sohn, K 2011, Illumination invariant road detection based on learning method. in 2011 14th International IEEE Conference on Intelligent Transportation Systems, ITSC 2011., 6082917, IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, pp. 1009-1014, 14th IEEE International Intelligent Transportation Systems Conference, ITSC 2011, Washington, DC, United States, 11/10/5. https://doi.org/10.1109/ITSC.2011.6082917

Illumination invariant road detection based on learning method. / Kim, Bongjoe; Son, Jongin; Sohn, Kwanghoon.

2011 14th International IEEE Conference on Intelligent Transportation Systems, ITSC 2011. 2011. p. 1009-1014 6082917 (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC).

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

TY - GEN

T1 - Illumination invariant road detection based on learning method

AU - Kim, Bongjoe

AU - Son, Jongin

AU - Sohn, Kwanghoon

PY - 2011

Y1 - 2011

N2 - Road detection is an essential and important component in intelligent transportation system (ITS). Generally, most road detection methods are sensitive to variation of illumination which results in increasing false detection rate. In this paper, we propose an illumination invariant road detection method to deal with variation of illumination. We adopt learning method to estimate illumination invariant direction which is specified to road surface. Once this direction is estimated, we can classify image pixel as road or not. Incorporating scene layout of road image, we reduce false positive detection rate outside the road. Experimental results on real road scenes show that the effectiveness of the proposed method.

AB - Road detection is an essential and important component in intelligent transportation system (ITS). Generally, most road detection methods are sensitive to variation of illumination which results in increasing false detection rate. In this paper, we propose an illumination invariant road detection method to deal with variation of illumination. We adopt learning method to estimate illumination invariant direction which is specified to road surface. Once this direction is estimated, we can classify image pixel as road or not. Incorporating scene layout of road image, we reduce false positive detection rate outside the road. Experimental results on real road scenes show that the effectiveness of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=83755163710&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=83755163710&partnerID=8YFLogxK

U2 - 10.1109/ITSC.2011.6082917

DO - 10.1109/ITSC.2011.6082917

M3 - Conference contribution

AN - SCOPUS:83755163710

SN - 9781457721984

T3 - IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC

SP - 1009

EP - 1014

BT - 2011 14th International IEEE Conference on Intelligent Transportation Systems, ITSC 2011

T2 - 14th IEEE International Intelligent Transportation Systems Conference, ITSC 2011

Y2 - 5 October 2011 through 7 October 2011

ER -