Fast-ICA Based Lane Detection Method for Autonomous Vehicles

Hasibe Busra Dogru; Aydin Tarik Zengin

doi:10.1109/IEEECONF55059.2022.9810405

Fast-ICA Based Lane Detection Method for Autonomous Vehicles

Hasibe Busra Dogru, Aydin Tarik Zengin^*

^*Corresponding author for this work

Istanbul Sabahattin Zaim University

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

Abstract

Lane detection is an important process in autonomous vehicle systems. Noise in the image, such as object shadows and terminating lane lines, make lane detection difficult. This study proposes a Convolutional Neural Network architecture with a dimension reduction method that has not been used before in lane detection. The proposed method has been tested with the open-source TuSimple dataset. The results showed that the proposed Fast-Independent Component Analysis based model training improved performance in lane detection and reduced the mean percent error by 42.2%.

Original language	English
Title of host publication	Proceedings of the 2022 26th International Conference Electronics, ELECTRONICS 2022
Editors	Darius Andriukaitis, Algimantas Valinevicius, Tomyslav Sledevic
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665483216
DOIs	https://doi.org/10.1109/IEEECONF55059.2022.9810405
Publication status	Published - 2022
Externally published	Yes
Event	26th International Conference Electronics, ELECTRONICS 2022 - Palanga, Lithuania Duration: 13 Jun 2022 → 15 Jun 2022

Publication series

Name	Proceedings of the 2022 26th International Conference Electronics, ELECTRONICS 2022

Conference

Conference	26th International Conference Electronics, ELECTRONICS 2022
Country/Territory	Lithuania
City	Palanga
Period	13/06/22 → 15/06/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

Autonomous vehicles
Deep learning
Independent component analysis
Lane detection

Access to Document

10.1109/IEEECONF55059.2022.9810405

Cite this

Dogru, H. B., & Zengin, A. T. (2022). Fast-ICA Based Lane Detection Method for Autonomous Vehicles. In D. Andriukaitis, A. Valinevicius, & T. Sledevic (Eds.), Proceedings of the 2022 26th International Conference Electronics, ELECTRONICS 2022 (Proceedings of the 2022 26th International Conference Electronics, ELECTRONICS 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IEEECONF55059.2022.9810405

Dogru, Hasibe Busra ; Zengin, Aydin Tarik. / Fast-ICA Based Lane Detection Method for Autonomous Vehicles. Proceedings of the 2022 26th International Conference Electronics, ELECTRONICS 2022. editor / Darius Andriukaitis ; Algimantas Valinevicius ; Tomyslav Sledevic. Institute of Electrical and Electronics Engineers Inc., 2022. (Proceedings of the 2022 26th International Conference Electronics, ELECTRONICS 2022).

@inproceedings{22d3abd2e3464e5bbfca5981bf9bfc92,

title = "Fast-ICA Based Lane Detection Method for Autonomous Vehicles",

abstract = "Lane detection is an important process in autonomous vehicle systems. Noise in the image, such as object shadows and terminating lane lines, make lane detection difficult. This study proposes a Convolutional Neural Network architecture with a dimension reduction method that has not been used before in lane detection. The proposed method has been tested with the open-source TuSimple dataset. The results showed that the proposed Fast-Independent Component Analysis based model training improved performance in lane detection and reduced the mean percent error by 42.2%.",

keywords = "Autonomous vehicles, Deep learning, Independent component analysis, Lane detection",

author = "Dogru, {Hasibe Busra} and Zengin, {Aydin Tarik}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 26th International Conference Electronics, ELECTRONICS 2022 ; Conference date: 13-06-2022 Through 15-06-2022",

year = "2022",

doi = "10.1109/IEEECONF55059.2022.9810405",

language = "English",

series = "Proceedings of the 2022 26th International Conference Electronics, ELECTRONICS 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Darius Andriukaitis and Algimantas Valinevicius and Tomyslav Sledevic",

booktitle = "Proceedings of the 2022 26th International Conference Electronics, ELECTRONICS 2022",

address = "United States",

}

Dogru, HB & Zengin, AT 2022, Fast-ICA Based Lane Detection Method for Autonomous Vehicles. in D Andriukaitis, A Valinevicius & T Sledevic (eds), Proceedings of the 2022 26th International Conference Electronics, ELECTRONICS 2022. Proceedings of the 2022 26th International Conference Electronics, ELECTRONICS 2022, Institute of Electrical and Electronics Engineers Inc., 26th International Conference Electronics, ELECTRONICS 2022, Palanga, Lithuania, 13/06/22. https://doi.org/10.1109/IEEECONF55059.2022.9810405

Fast-ICA Based Lane Detection Method for Autonomous Vehicles. / Dogru, Hasibe Busra; Zengin, Aydin Tarik.
Proceedings of the 2022 26th International Conference Electronics, ELECTRONICS 2022. ed. / Darius Andriukaitis; Algimantas Valinevicius; Tomyslav Sledevic. Institute of Electrical and Electronics Engineers Inc., 2022. (Proceedings of the 2022 26th International Conference Electronics, ELECTRONICS 2022).

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

TY - GEN

T1 - Fast-ICA Based Lane Detection Method for Autonomous Vehicles

AU - Dogru, Hasibe Busra

AU - Zengin, Aydin Tarik

PY - 2022

Y1 - 2022

N2 - Lane detection is an important process in autonomous vehicle systems. Noise in the image, such as object shadows and terminating lane lines, make lane detection difficult. This study proposes a Convolutional Neural Network architecture with a dimension reduction method that has not been used before in lane detection. The proposed method has been tested with the open-source TuSimple dataset. The results showed that the proposed Fast-Independent Component Analysis based model training improved performance in lane detection and reduced the mean percent error by 42.2%.

AB - Lane detection is an important process in autonomous vehicle systems. Noise in the image, such as object shadows and terminating lane lines, make lane detection difficult. This study proposes a Convolutional Neural Network architecture with a dimension reduction method that has not been used before in lane detection. The proposed method has been tested with the open-source TuSimple dataset. The results showed that the proposed Fast-Independent Component Analysis based model training improved performance in lane detection and reduced the mean percent error by 42.2%.

KW - Autonomous vehicles

KW - Deep learning

KW - Independent component analysis

KW - Lane detection

UR - http://www.scopus.com/inward/record.url?scp=85135053197&partnerID=8YFLogxK

U2 - 10.1109/IEEECONF55059.2022.9810405

DO - 10.1109/IEEECONF55059.2022.9810405

M3 - Conference contribution

AN - SCOPUS:85135053197

T3 - Proceedings of the 2022 26th International Conference Electronics, ELECTRONICS 2022

BT - Proceedings of the 2022 26th International Conference Electronics, ELECTRONICS 2022

A2 - Andriukaitis, Darius

A2 - Valinevicius, Algimantas

A2 - Sledevic, Tomyslav

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 26th International Conference Electronics, ELECTRONICS 2022

Y2 - 13 June 2022 through 15 June 2022

ER -

Dogru HB, Zengin AT. Fast-ICA Based Lane Detection Method for Autonomous Vehicles. In Andriukaitis D, Valinevicius A, Sledevic T, editors, Proceedings of the 2022 26th International Conference Electronics, ELECTRONICS 2022. Institute of Electrical and Electronics Engineers Inc. 2022. (Proceedings of the 2022 26th International Conference Electronics, ELECTRONICS 2022). doi: 10.1109/IEEECONF55059.2022.9810405

Fast-ICA Based Lane Detection Method for Autonomous Vehicles

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this