Adas on Cots with OpenCL: A Case Study with Lane Detection

Kai Huang; Biao Hu; Long Chen; Alois Knoll; Zhihua Wang

doi:10.1109/TC.2017.2759203

Adas on Cots with OpenCL: A Case Study with Lane Detection

Kai Huang, Biao Hu, Long Chen, Alois Knoll, Zhihua Wang

nformatics 6 - Chair of IRobotics, Artificial Intelligence and Real-time Systems

Research output: Contribution to journal › Article › peer-review

7 Scopus citations

Abstract

The concept of autonomous cars is driving a boost for car electronics and the size of automotive electronics market is foreseen to double by 2025. How to benefit from this boost is an interesting question. This article presents a case study to test the feasibility of using OpenCL as the programming language and Cots components as the underlying computing platforms for Adas development. For representative Adas applications, a scalable lane detection is developed that can tune the trade-off between detection accuracy and speed. Our OpenCL implementation is tested on 14 video streams from different data-sets with different road scenarios on 5 Cots platforms. We demonstrate that the Cots platforms can provide more than sufficient computing power for the lane detection in the meanwhile our OpenCL implementation can exploit the massive parallelism provided by the Cots platforms.

Original language	English
Pages (from-to)	559-565
Number of pages	7
Journal	IEEE Transactions on Computers
Volume	67
Issue number	4
DOIs	https://doi.org/10.1109/TC.2017.2759203
State	Published - 1 Apr 2018

Keywords

Advanced driver assistance systems (ADAS)
FPGA
GPU
OpenCL
commercial of the shelf (COTS)

Access to Document

10.1109/TC.2017.2759203

Cite this

@article{6573875fed744bffadc91451e01f977c,

title = "Adas on Cots with OpenCL: A Case Study with Lane Detection",

abstract = "The concept of autonomous cars is driving a boost for car electronics and the size of automotive electronics market is foreseen to double by 2025. How to benefit from this boost is an interesting question. This article presents a case study to test the feasibility of using OpenCL as the programming language and Cots components as the underlying computing platforms for Adas development. For representative Adas applications, a scalable lane detection is developed that can tune the trade-off between detection accuracy and speed. Our OpenCL implementation is tested on 14 video streams from different data-sets with different road scenarios on 5 Cots platforms. We demonstrate that the Cots platforms can provide more than sufficient computing power for the lane detection in the meanwhile our OpenCL implementation can exploit the massive parallelism provided by the Cots platforms.",

keywords = "Advanced driver assistance systems (ADAS), FPGA, GPU, OpenCL, commercial of the shelf (COTS)",

author = "Kai Huang and Biao Hu and Long Chen and Alois Knoll and Zhihua Wang",

note = "Publisher Copyright: {\textcopyright} 1968-2012 IEEE.",

year = "2018",

month = apr,

day = "1",

doi = "10.1109/TC.2017.2759203",

language = "English",

volume = "67",

pages = "559--565",

journal = "IEEE Transactions on Computers",

issn = "0018-9340",

publisher = "IEEE Computer Society",

number = "4",

}

TY - JOUR

T1 - Adas on Cots with OpenCL

T2 - A Case Study with Lane Detection

AU - Huang, Kai

AU - Hu, Biao

AU - Chen, Long

AU - Knoll, Alois

AU - Wang, Zhihua

PY - 2018/4/1

Y1 - 2018/4/1

N2 - The concept of autonomous cars is driving a boost for car electronics and the size of automotive electronics market is foreseen to double by 2025. How to benefit from this boost is an interesting question. This article presents a case study to test the feasibility of using OpenCL as the programming language and Cots components as the underlying computing platforms for Adas development. For representative Adas applications, a scalable lane detection is developed that can tune the trade-off between detection accuracy and speed. Our OpenCL implementation is tested on 14 video streams from different data-sets with different road scenarios on 5 Cots platforms. We demonstrate that the Cots platforms can provide more than sufficient computing power for the lane detection in the meanwhile our OpenCL implementation can exploit the massive parallelism provided by the Cots platforms.

AB - The concept of autonomous cars is driving a boost for car electronics and the size of automotive electronics market is foreseen to double by 2025. How to benefit from this boost is an interesting question. This article presents a case study to test the feasibility of using OpenCL as the programming language and Cots components as the underlying computing platforms for Adas development. For representative Adas applications, a scalable lane detection is developed that can tune the trade-off between detection accuracy and speed. Our OpenCL implementation is tested on 14 video streams from different data-sets with different road scenarios on 5 Cots platforms. We demonstrate that the Cots platforms can provide more than sufficient computing power for the lane detection in the meanwhile our OpenCL implementation can exploit the massive parallelism provided by the Cots platforms.

KW - Advanced driver assistance systems (ADAS)

KW - FPGA

KW - GPU

KW - OpenCL

KW - commercial of the shelf (COTS)

UR - http://www.scopus.com/inward/record.url?scp=85030750537&partnerID=8YFLogxK

U2 - 10.1109/TC.2017.2759203

DO - 10.1109/TC.2017.2759203

M3 - Article

AN - SCOPUS:85030750537

SN - 0018-9340

VL - 67

SP - 559

EP - 565

JO - IEEE Transactions on Computers

JF - IEEE Transactions on Computers

IS - 4

ER -

Adas on Cots with OpenCL: A Case Study with Lane Detection

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this