A scalable lane detection algorithm on COTSs with OpenCL

Kai Huang; Biao Hu; Jan Botsch; Nikhil Madduri; Alois Knoll

doi:10.3850/9783981537079_0056

A scalable lane detection algorithm on COTSs with OpenCL

Kai Huang
, Biao Hu
, Jan Botsch
, Nikhil Madduri
, Alois Knoll

Informatics 6 - Chair of Robotics, Artificial Intelligence and Real-time Systems

Sun Yat-Sen University
Technical University of Munich
University of Würzburg

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

10 Scopus citations

Abstract

Road lane detection are classical requirements for advanced driving assistant systems. With new computer technologies, lane detection algorithms can be exploited on COTS platforms. This paper investigates the use of OpenCL and develop a particle-filter based lane detection algorithm that can tune the trade-off between detection accuracy and speed. Our algorithm is tested on 14 video streams from different data-sets with different scenarios on different COTS hardware. With an average deviation fewer than 5 pixels, the average frame rates for the 14 videos can reach about 400 fps on both GPU and FPGA. The peak frame rates for certain videos on GPU can reach almost 1000 fps.

Original language	English
Title of host publication	Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	229-232
Number of pages	4
ISBN (Electronic)	9783981537062
DOIs	https://doi.org/10.3850/9783981537079_0056
State	Published - 25 Apr 2016
Event	19th Design, Automation and Test in Europe Conference and Exhibition, DATE 2016 - Dresden, Germany Duration: 14 Mar 2016 → 18 Mar 2016

Publication series

Name	Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016

Conference

Conference	19th Design, Automation and Test in Europe Conference and Exhibition, DATE 2016
Country/Territory	Germany
City	Dresden
Period	14/03/16 → 18/03/16

Access to Document

10.3850/9783981537079_0056

Cite this

Huang, K., Hu, B., Botsch, J., Madduri, N., & Knoll, A. (2016). A scalable lane detection algorithm on COTSs with OpenCL. In Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016 (pp. 229-232). Article 7459309 (Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.3850/9783981537079_0056

Huang, Kai ; Hu, Biao ; Botsch, Jan et al. / A scalable lane detection algorithm on COTSs with OpenCL. Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 229-232 (Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016).

@inproceedings{201df278607043c4a994efe97ff68335,

title = "A scalable lane detection algorithm on COTSs with OpenCL",

abstract = "Road lane detection are classical requirements for advanced driving assistant systems. With new computer technologies, lane detection algorithms can be exploited on COTS platforms. This paper investigates the use of OpenCL and develop a particle-filter based lane detection algorithm that can tune the trade-off between detection accuracy and speed. Our algorithm is tested on 14 video streams from different data-sets with different scenarios on different COTS hardware. With an average deviation fewer than 5 pixels, the average frame rates for the 14 videos can reach about 400 fps on both GPU and FPGA. The peak frame rates for certain videos on GPU can reach almost 1000 fps.",

author = "Kai Huang and Biao Hu and Jan Botsch and Nikhil Madduri and Alois Knoll",

note = "Publisher Copyright: {\textcopyright} 2016 EDAA.; 19th Design, Automation and Test in Europe Conference and Exhibition, DATE 2016 ; Conference date: 14-03-2016 Through 18-03-2016",

year = "2016",

month = apr,

day = "25",

doi = "10.3850/9783981537079\_0056",

language = "English",

series = "Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016",

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

pages = "229--232",

booktitle = "Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016",

}

Huang, K, Hu, B, Botsch, J, Madduri, N & Knoll, A 2016, A scalable lane detection algorithm on COTSs with OpenCL. in Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016., 7459309, Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016, Institute of Electrical and Electronics Engineers Inc., pp. 229-232, 19th Design, Automation and Test in Europe Conference and Exhibition, DATE 2016, Dresden, Germany, 14/03/16. https://doi.org/10.3850/9783981537079_0056

A scalable lane detection algorithm on COTSs with OpenCL. / Huang, Kai; Hu, Biao; Botsch, Jan et al.
Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 229-232 7459309 (Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016).

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

TY - GEN

T1 - A scalable lane detection algorithm on COTSs with OpenCL

AU - Huang, Kai

AU - Hu, Biao

AU - Botsch, Jan

AU - Madduri, Nikhil

AU - Knoll, Alois

PY - 2016/4/25

Y1 - 2016/4/25

N2 - Road lane detection are classical requirements for advanced driving assistant systems. With new computer technologies, lane detection algorithms can be exploited on COTS platforms. This paper investigates the use of OpenCL and develop a particle-filter based lane detection algorithm that can tune the trade-off between detection accuracy and speed. Our algorithm is tested on 14 video streams from different data-sets with different scenarios on different COTS hardware. With an average deviation fewer than 5 pixels, the average frame rates for the 14 videos can reach about 400 fps on both GPU and FPGA. The peak frame rates for certain videos on GPU can reach almost 1000 fps.

AB - Road lane detection are classical requirements for advanced driving assistant systems. With new computer technologies, lane detection algorithms can be exploited on COTS platforms. This paper investigates the use of OpenCL and develop a particle-filter based lane detection algorithm that can tune the trade-off between detection accuracy and speed. Our algorithm is tested on 14 video streams from different data-sets with different scenarios on different COTS hardware. With an average deviation fewer than 5 pixels, the average frame rates for the 14 videos can reach about 400 fps on both GPU and FPGA. The peak frame rates for certain videos on GPU can reach almost 1000 fps.

UR - https://www.scopus.com/pages/publications/84973635755

U2 - 10.3850/9783981537079_0056

DO - 10.3850/9783981537079_0056

M3 - Conference contribution

AN - SCOPUS:84973635755

T3 - Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016

SP - 229

EP - 232

BT - Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 19th Design, Automation and Test in Europe Conference and Exhibition, DATE 2016

Y2 - 14 March 2016 through 18 March 2016

ER -

Huang K, Hu B, Botsch J, Madduri N, Knoll A. A scalable lane detection algorithm on COTSs with OpenCL. In Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 229-232. 7459309. (Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016). doi: 10.3850/9783981537079_0056

A scalable lane detection algorithm on COTSs with OpenCL

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this