A 3D Time-of-Flight Mixed-Criticality System for Environment Perception

Josef Steinbäck; Allan Tengg; Gerald Holweg; Norbert Druml

doi:10.1109/DSD.2017.59

A 3D Time-of-Flight Mixed-Criticality System for Environment Perception

Josef Steinbäck, Allan Tengg, Gerald Holweg, Norbert Druml

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

Abstract

Automated driving systems have to operate at the highest level of robustness and safety. Thus, redundancy and diversity of the deployed systems are inevitable in order to guarantee the functionality in any possible scenario. Today, the most used sensor technologies for environment perception are color cameras, radar, light detection and ranging (LIDAR), and ultrasonic sensors. This work evaluates the feasibility of a 3D Time-of-Flight (ToF) camera to be used as environmental perception sensor in robotics and automated/assisted driving. To examine the performance of the sensor in the field, a ToF processing platform is attached to a 1:5 scaled remote control vehicle. An algorithm, which detects and reacts to obstacles in real-time, is designed and implemented on an AURIX automotive safety-microcontroller as major part of a mixed-criticality application. The embedded system highly benefits from the low computational effort required by ToF imaging (in contrast to stereo vision). Utilizing all three cores of the AURIX, the system achieves frame-rates of up to 30 frames per second (FPS).

Original language	English
Title of host publication	Proceedings - 20th Euromicro Conference on Digital System Design, DSD 2017
Publisher	Institute of Electrical and Electronics Engineers
Pages	368-374
Number of pages	7
ISBN (Electronic)	978-1-5386-2146-2
DOIs	https://doi.org/10.1109/DSD.2017.59
Publication status	Published - 25 Sep 2017
Event	20th Euromicro Conference on Digital System Design, DSD 2017 - Vienna, Austria Duration: 30 Aug 2017 → 1 Sep 2017

Conference

Conference	20th Euromicro Conference on Digital System Design, DSD 2017
Country/Territory	Austria
City	Vienna
Period	30/08/17 → 1/09/17

Keywords

3D imaging
accident prevention
infrared image sensors
robotics
Time-of-Flight
unmanned vehicles

ASJC Scopus subject areas

Computer Science Applications
Control and Systems Engineering
Hardware and Architecture

Access to Document

10.1109/DSD.2017.59

Cite this

A 3D Time-of-Flight Mixed-Criticality System for Environment Perception. / Steinbäck, Josef; Tengg, Allan; Holweg, Gerald et al.

Proceedings - 20th Euromicro Conference on Digital System Design, DSD 2017. Institute of Electrical and Electronics Engineers, 2017. p. 368-374 8049812.

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

Steinbäck, J, Tengg, A, Holweg, G & Druml, N 2017, A 3D Time-of-Flight Mixed-Criticality System for Environment Perception. in Proceedings - 20th Euromicro Conference on Digital System Design, DSD 2017., 8049812, Institute of Electrical and Electronics Engineers, pp. 368-374, 20th Euromicro Conference on Digital System Design, DSD 2017, Vienna, Austria, 30/08/17. https://doi.org/10.1109/DSD.2017.59

@inproceedings{7daecc620a044a929f38457019cb3fc7,

title = "A 3D Time-of-Flight Mixed-Criticality System for Environment Perception",

abstract = "Automated driving systems have to operate at the highest level of robustness and safety. Thus, redundancy and diversity of the deployed systems are inevitable in order to guarantee the functionality in any possible scenario. Today, the most used sensor technologies for environment perception are color cameras, radar, light detection and ranging (LIDAR), and ultrasonic sensors. This work evaluates the feasibility of a 3D Time-of-Flight (ToF) camera to be used as environmental perception sensor in robotics and automated/assisted driving. To examine the performance of the sensor in the field, a ToF processing platform is attached to a 1:5 scaled remote control vehicle. An algorithm, which detects and reacts to obstacles in real-time, is designed and implemented on an AURIX automotive safety-microcontroller as major part of a mixed-criticality application. The embedded system highly benefits from the low computational effort required by ToF imaging (in contrast to stereo vision). Utilizing all three cores of the AURIX, the system achieves frame-rates of up to 30 frames per second (FPS).",

keywords = "3D imaging, accident prevention, infrared image sensors, robotics, Time-of-Flight, unmanned vehicles",

author = "Josef Steinb{\"a}ck and Allan Tengg and Gerald Holweg and Norbert Druml",

year = "2017",

month = sep,

day = "25",

doi = "10.1109/DSD.2017.59",

language = "English",

pages = "368--374",

booktitle = "Proceedings - 20th Euromicro Conference on Digital System Design, DSD 2017",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "20th Euromicro Conference on Digital System Design, DSD 2017 ; Conference date: 30-08-2017 Through 01-09-2017",

}

TY - GEN

T1 - A 3D Time-of-Flight Mixed-Criticality System for Environment Perception

AU - Steinbäck, Josef

AU - Tengg, Allan

AU - Holweg, Gerald

AU - Druml, Norbert

PY - 2017/9/25

Y1 - 2017/9/25

N2 - Automated driving systems have to operate at the highest level of robustness and safety. Thus, redundancy and diversity of the deployed systems are inevitable in order to guarantee the functionality in any possible scenario. Today, the most used sensor technologies for environment perception are color cameras, radar, light detection and ranging (LIDAR), and ultrasonic sensors. This work evaluates the feasibility of a 3D Time-of-Flight (ToF) camera to be used as environmental perception sensor in robotics and automated/assisted driving. To examine the performance of the sensor in the field, a ToF processing platform is attached to a 1:5 scaled remote control vehicle. An algorithm, which detects and reacts to obstacles in real-time, is designed and implemented on an AURIX automotive safety-microcontroller as major part of a mixed-criticality application. The embedded system highly benefits from the low computational effort required by ToF imaging (in contrast to stereo vision). Utilizing all three cores of the AURIX, the system achieves frame-rates of up to 30 frames per second (FPS).

AB - Automated driving systems have to operate at the highest level of robustness and safety. Thus, redundancy and diversity of the deployed systems are inevitable in order to guarantee the functionality in any possible scenario. Today, the most used sensor technologies for environment perception are color cameras, radar, light detection and ranging (LIDAR), and ultrasonic sensors. This work evaluates the feasibility of a 3D Time-of-Flight (ToF) camera to be used as environmental perception sensor in robotics and automated/assisted driving. To examine the performance of the sensor in the field, a ToF processing platform is attached to a 1:5 scaled remote control vehicle. An algorithm, which detects and reacts to obstacles in real-time, is designed and implemented on an AURIX automotive safety-microcontroller as major part of a mixed-criticality application. The embedded system highly benefits from the low computational effort required by ToF imaging (in contrast to stereo vision). Utilizing all three cores of the AURIX, the system achieves frame-rates of up to 30 frames per second (FPS).

KW - 3D imaging

KW - accident prevention

KW - infrared image sensors

KW - robotics

KW - Time-of-Flight

KW - unmanned vehicles

UR - http://www.scopus.com/inward/record.url?scp=85034441512&partnerID=8YFLogxK

U2 - 10.1109/DSD.2017.59

DO - 10.1109/DSD.2017.59

M3 - Conference paper

AN - SCOPUS:85034441512

SP - 368

EP - 374

BT - Proceedings - 20th Euromicro Conference on Digital System Design, DSD 2017

PB - Institute of Electrical and Electronics Engineers

T2 - 20th Euromicro Conference on Digital System Design, DSD 2017

Y2 - 30 August 2017 through 1 September 2017

ER -

A 3D Time-of-Flight Mixed-Criticality System for Environment Perception

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this