Online stereo camera calibration for automotive vision based on HW-accelerated A-KAZE-feature extraction

Research output: Contribution to journalArticleResearchpeer review

Authors

Research Organisations

View graph of relations

Details

Original languageEnglish
Pages (from-to)335-348
Number of pages14
JournalJournal of Systems Architecture
Volume97
Early online date17 Nov 2018
Publication statusPublished - Aug 2019

Abstract

Nowadays ongoing integration of camera based advanced driver assistance systems (ADAS) in vehicles demands increasingly complex digital image processing in order to interpret the surrounding situations. To ensure a timely reaction for obstacles lying ahead, far reaching depth information of the observed scene is necessary. Using stereo camera systems, this is achievable by enlarging the camera base line. With rapid driving, the exact alignment of the stereo images is no longer ensured due to vibrations of the vehicle. Based on detection, extraction and matching of Accelerated-KAZE image features (A-KAZE), the geometric distortions are compensable by estimating the external camera parameters for image rectification. The indispensable frame rate for applications in vehicles and the limited power budget in combination with the SW-flexibility demanded for future ADAS applications requires the usage of optimized hardware architectures. Thus, an online camera calibration based on an HW-accelerated A-KAZE extraction is introduced in this work. The suitability of A-KAZE features for an online camera calibration is proven. Furthermore, the Tensilica Vision P5-processor is evaluated regarding its suitability for real-time A-KAZE feature extraction. This processor provides a comprehensive instruction-set extension for high-performance digital image processing. While preserving the initial A-KAZE accuracy, a feature descriptor length reduction of factor  × 3.8 is attained compared to the initial descriptor size and an estimated frame rate of 20 fps is achieved for A-KAZE feature extraction on the Tensilica Vision P5-processor.

Keywords

    A-KAZE, Advanced driver assistance systems, ASIP, Feature matching, Tensilica vision P5

ASJC Scopus subject areas

Cite this

Online stereo camera calibration for automotive vision based on HW-accelerated A-KAZE-feature extraction. / Mentzer, Nico; Mahr, Jannik; Payá-Vayá, Guillermo et al.
In: Journal of Systems Architecture, Vol. 97, 08.2019, p. 335-348.

Research output: Contribution to journalArticleResearchpeer review

Mentzer N, Mahr J, Payá-Vayá G, Blume H. Online stereo camera calibration for automotive vision based on HW-accelerated A-KAZE-feature extraction. Journal of Systems Architecture. 2019 Aug;97:335-348. Epub 2018 Nov 17. doi: 10.1016/j.sysarc.2018.11.003
Mentzer, Nico ; Mahr, Jannik ; Payá-Vayá, Guillermo et al. / Online stereo camera calibration for automotive vision based on HW-accelerated A-KAZE-feature extraction. In: Journal of Systems Architecture. 2019 ; Vol. 97. pp. 335-348.
Download
@article{c29ed0c88a884598903706fb6594db20,
title = "Online stereo camera calibration for automotive vision based on HW-accelerated A-KAZE-feature extraction",
abstract = "Nowadays ongoing integration of camera based advanced driver assistance systems (ADAS) in vehicles demands increasingly complex digital image processing in order to interpret the surrounding situations. To ensure a timely reaction for obstacles lying ahead, far reaching depth information of the observed scene is necessary. Using stereo camera systems, this is achievable by enlarging the camera base line. With rapid driving, the exact alignment of the stereo images is no longer ensured due to vibrations of the vehicle. Based on detection, extraction and matching of Accelerated-KAZE image features (A-KAZE), the geometric distortions are compensable by estimating the external camera parameters for image rectification. The indispensable frame rate for applications in vehicles and the limited power budget in combination with the SW-flexibility demanded for future ADAS applications requires the usage of optimized hardware architectures. Thus, an online camera calibration based on an HW-accelerated A-KAZE extraction is introduced in this work. The suitability of A-KAZE features for an online camera calibration is proven. Furthermore, the Tensilica Vision P5-processor is evaluated regarding its suitability for real-time A-KAZE feature extraction. This processor provides a comprehensive instruction-set extension for high-performance digital image processing. While preserving the initial A-KAZE accuracy, a feature descriptor length reduction of factor  × 3.8 is attained compared to the initial descriptor size and an estimated frame rate of 20 fps is achieved for A-KAZE feature extraction on the Tensilica Vision P5-processor.",
keywords = "A-KAZE, Advanced driver assistance systems, ASIP, Feature matching, Tensilica vision P5",
author = "Nico Mentzer and Jannik Mahr and Guillermo Pay{\'a}-Vay{\'a} and Holger Blume",
note = "{\textcopyright} 2018 Elsevier B.V. All rights reserved.",
year = "2019",
month = aug,
doi = "10.1016/j.sysarc.2018.11.003",
language = "English",
volume = "97",
pages = "335--348",
journal = "Journal of Systems Architecture",
issn = "1383-7621",
publisher = "Elsevier",

}

Download

TY - JOUR

T1 - Online stereo camera calibration for automotive vision based on HW-accelerated A-KAZE-feature extraction

AU - Mentzer, Nico

AU - Mahr, Jannik

AU - Payá-Vayá, Guillermo

AU - Blume, Holger

N1 - © 2018 Elsevier B.V. All rights reserved.

PY - 2019/8

Y1 - 2019/8

N2 - Nowadays ongoing integration of camera based advanced driver assistance systems (ADAS) in vehicles demands increasingly complex digital image processing in order to interpret the surrounding situations. To ensure a timely reaction for obstacles lying ahead, far reaching depth information of the observed scene is necessary. Using stereo camera systems, this is achievable by enlarging the camera base line. With rapid driving, the exact alignment of the stereo images is no longer ensured due to vibrations of the vehicle. Based on detection, extraction and matching of Accelerated-KAZE image features (A-KAZE), the geometric distortions are compensable by estimating the external camera parameters for image rectification. The indispensable frame rate for applications in vehicles and the limited power budget in combination with the SW-flexibility demanded for future ADAS applications requires the usage of optimized hardware architectures. Thus, an online camera calibration based on an HW-accelerated A-KAZE extraction is introduced in this work. The suitability of A-KAZE features for an online camera calibration is proven. Furthermore, the Tensilica Vision P5-processor is evaluated regarding its suitability for real-time A-KAZE feature extraction. This processor provides a comprehensive instruction-set extension for high-performance digital image processing. While preserving the initial A-KAZE accuracy, a feature descriptor length reduction of factor  × 3.8 is attained compared to the initial descriptor size and an estimated frame rate of 20 fps is achieved for A-KAZE feature extraction on the Tensilica Vision P5-processor.

AB - Nowadays ongoing integration of camera based advanced driver assistance systems (ADAS) in vehicles demands increasingly complex digital image processing in order to interpret the surrounding situations. To ensure a timely reaction for obstacles lying ahead, far reaching depth information of the observed scene is necessary. Using stereo camera systems, this is achievable by enlarging the camera base line. With rapid driving, the exact alignment of the stereo images is no longer ensured due to vibrations of the vehicle. Based on detection, extraction and matching of Accelerated-KAZE image features (A-KAZE), the geometric distortions are compensable by estimating the external camera parameters for image rectification. The indispensable frame rate for applications in vehicles and the limited power budget in combination with the SW-flexibility demanded for future ADAS applications requires the usage of optimized hardware architectures. Thus, an online camera calibration based on an HW-accelerated A-KAZE extraction is introduced in this work. The suitability of A-KAZE features for an online camera calibration is proven. Furthermore, the Tensilica Vision P5-processor is evaluated regarding its suitability for real-time A-KAZE feature extraction. This processor provides a comprehensive instruction-set extension for high-performance digital image processing. While preserving the initial A-KAZE accuracy, a feature descriptor length reduction of factor  × 3.8 is attained compared to the initial descriptor size and an estimated frame rate of 20 fps is achieved for A-KAZE feature extraction on the Tensilica Vision P5-processor.

KW - A-KAZE

KW - Advanced driver assistance systems

KW - ASIP

KW - Feature matching

KW - Tensilica vision P5

U2 - 10.1016/j.sysarc.2018.11.003

DO - 10.1016/j.sysarc.2018.11.003

M3 - Article

AN - SCOPUS:85056995316

VL - 97

SP - 335

EP - 348

JO - Journal of Systems Architecture

JF - Journal of Systems Architecture

SN - 1383-7621

ER -

By the same author(s)