Proposing a GPU based modified fuzzy nearest neighbor rule for traffic sign detection

Peyman Hosseinzadeh Kassani, Junhyuk Hyun, Euntai Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

The purpose of this study is introducing a graphical process unit (GPU) implementation of a modified fuzzy nearest neighbor rule useful for traffic sign detection (TSD). The new method tries to detect road signs using color information in order to locate regions of interest. The candidate regions of interest are obtained by color information. Afterward, candidate regions are used for making histogram of oriented gradient (HOG) feature. Finally, the features are fed into the GPU-based modified fuzzy nearest neighbor in order to detect traffic signs. The proposed rule modifies the way for fuzzification of query sample in terms of distances while the conventional fuzzy nearest neighbor (FNN) doesn't care distance of local neighbors. The accuracy of the proposed method is compared with the state of the arts k-nearest neighbor (k-NN), FNN and support vector machine algorithms on the challenging German traffic sign detection benchmark (GTSDB) data set. Results indicate that the modified rule achieves good accuracy and is competitive compared to others.

Original languageEnglish
Title of host publicationICCAS 2015 - 2015 15th International Conference on Control, Automation and Systems, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages173-176
Number of pages4
ISBN (Electronic)9788993215090
DOIs
Publication statusPublished - 2015 Dec 23
Event15th International Conference on Control, Automation and Systems, ICCAS 2015 - Busan, Korea, Republic of
Duration: 2015 Oct 132015 Oct 16

Publication series

NameICCAS 2015 - 2015 15th International Conference on Control, Automation and Systems, Proceedings

Other

Other15th International Conference on Control, Automation and Systems, ICCAS 2015
CountryKorea, Republic of
CityBusan
Period15/10/1315/10/16

Fingerprint

Traffic signs
Chemical reactions
Color
Support vector machines

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering

Cite this

Hosseinzadeh Kassani, P., Hyun, J., & Kim, E. (2015). Proposing a GPU based modified fuzzy nearest neighbor rule for traffic sign detection. In ICCAS 2015 - 2015 15th International Conference on Control, Automation and Systems, Proceedings (pp. 173-176). [7364901] (ICCAS 2015 - 2015 15th International Conference on Control, Automation and Systems, Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCAS.2015.7364901
Hosseinzadeh Kassani, Peyman ; Hyun, Junhyuk ; Kim, Euntai. / Proposing a GPU based modified fuzzy nearest neighbor rule for traffic sign detection. ICCAS 2015 - 2015 15th International Conference on Control, Automation and Systems, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 173-176 (ICCAS 2015 - 2015 15th International Conference on Control, Automation and Systems, Proceedings).
@inproceedings{16c144d752b2440895261264e32252e1,
title = "Proposing a GPU based modified fuzzy nearest neighbor rule for traffic sign detection",
abstract = "The purpose of this study is introducing a graphical process unit (GPU) implementation of a modified fuzzy nearest neighbor rule useful for traffic sign detection (TSD). The new method tries to detect road signs using color information in order to locate regions of interest. The candidate regions of interest are obtained by color information. Afterward, candidate regions are used for making histogram of oriented gradient (HOG) feature. Finally, the features are fed into the GPU-based modified fuzzy nearest neighbor in order to detect traffic signs. The proposed rule modifies the way for fuzzification of query sample in terms of distances while the conventional fuzzy nearest neighbor (FNN) doesn't care distance of local neighbors. The accuracy of the proposed method is compared with the state of the arts k-nearest neighbor (k-NN), FNN and support vector machine algorithms on the challenging German traffic sign detection benchmark (GTSDB) data set. Results indicate that the modified rule achieves good accuracy and is competitive compared to others.",
author = "{Hosseinzadeh Kassani}, Peyman and Junhyuk Hyun and Euntai Kim",
year = "2015",
month = "12",
day = "23",
doi = "10.1109/ICCAS.2015.7364901",
language = "English",
series = "ICCAS 2015 - 2015 15th International Conference on Control, Automation and Systems, Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "173--176",
booktitle = "ICCAS 2015 - 2015 15th International Conference on Control, Automation and Systems, Proceedings",
address = "United States",

}

Hosseinzadeh Kassani, P, Hyun, J & Kim, E 2015, Proposing a GPU based modified fuzzy nearest neighbor rule for traffic sign detection. in ICCAS 2015 - 2015 15th International Conference on Control, Automation and Systems, Proceedings., 7364901, ICCAS 2015 - 2015 15th International Conference on Control, Automation and Systems, Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 173-176, 15th International Conference on Control, Automation and Systems, ICCAS 2015, Busan, Korea, Republic of, 15/10/13. https://doi.org/10.1109/ICCAS.2015.7364901

Proposing a GPU based modified fuzzy nearest neighbor rule for traffic sign detection. / Hosseinzadeh Kassani, Peyman; Hyun, Junhyuk; Kim, Euntai.

ICCAS 2015 - 2015 15th International Conference on Control, Automation and Systems, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015. p. 173-176 7364901 (ICCAS 2015 - 2015 15th International Conference on Control, Automation and Systems, Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Proposing a GPU based modified fuzzy nearest neighbor rule for traffic sign detection

AU - Hosseinzadeh Kassani, Peyman

AU - Hyun, Junhyuk

AU - Kim, Euntai

PY - 2015/12/23

Y1 - 2015/12/23

N2 - The purpose of this study is introducing a graphical process unit (GPU) implementation of a modified fuzzy nearest neighbor rule useful for traffic sign detection (TSD). The new method tries to detect road signs using color information in order to locate regions of interest. The candidate regions of interest are obtained by color information. Afterward, candidate regions are used for making histogram of oriented gradient (HOG) feature. Finally, the features are fed into the GPU-based modified fuzzy nearest neighbor in order to detect traffic signs. The proposed rule modifies the way for fuzzification of query sample in terms of distances while the conventional fuzzy nearest neighbor (FNN) doesn't care distance of local neighbors. The accuracy of the proposed method is compared with the state of the arts k-nearest neighbor (k-NN), FNN and support vector machine algorithms on the challenging German traffic sign detection benchmark (GTSDB) data set. Results indicate that the modified rule achieves good accuracy and is competitive compared to others.

AB - The purpose of this study is introducing a graphical process unit (GPU) implementation of a modified fuzzy nearest neighbor rule useful for traffic sign detection (TSD). The new method tries to detect road signs using color information in order to locate regions of interest. The candidate regions of interest are obtained by color information. Afterward, candidate regions are used for making histogram of oriented gradient (HOG) feature. Finally, the features are fed into the GPU-based modified fuzzy nearest neighbor in order to detect traffic signs. The proposed rule modifies the way for fuzzification of query sample in terms of distances while the conventional fuzzy nearest neighbor (FNN) doesn't care distance of local neighbors. The accuracy of the proposed method is compared with the state of the arts k-nearest neighbor (k-NN), FNN and support vector machine algorithms on the challenging German traffic sign detection benchmark (GTSDB) data set. Results indicate that the modified rule achieves good accuracy and is competitive compared to others.

UR - http://www.scopus.com/inward/record.url?scp=84966425271&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84966425271&partnerID=8YFLogxK

U2 - 10.1109/ICCAS.2015.7364901

DO - 10.1109/ICCAS.2015.7364901

M3 - Conference contribution

AN - SCOPUS:84966425271

T3 - ICCAS 2015 - 2015 15th International Conference on Control, Automation and Systems, Proceedings

SP - 173

EP - 176

BT - ICCAS 2015 - 2015 15th International Conference on Control, Automation and Systems, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Hosseinzadeh Kassani P, Hyun J, Kim E. Proposing a GPU based modified fuzzy nearest neighbor rule for traffic sign detection. In ICCAS 2015 - 2015 15th International Conference on Control, Automation and Systems, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2015. p. 173-176. 7364901. (ICCAS 2015 - 2015 15th International Conference on Control, Automation and Systems, Proceedings). https://doi.org/10.1109/ICCAS.2015.7364901