IMACS: a framework for performance evaluation of image approximation in a closed-loop system

Sajid Mohamed, Sayandip De, Konstantinos Bimpisidis, Vishak Nathan, Dip Goswami, Henk Corporaal, Twan Basten

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

Image Processing (IP) applications have become popular with the advent of efficient algorithms and low-cost CMOS cameras with high resolution. However, IP applications are compute-intensive, consume a lot of energy and have long processing times. Image approximation has been proposed by recent works for an energy-efficient design of these applications. It also reduces the impact of long processing times. The challenge here is that the IP applications often work as a part of bigger closed-loop control systems, e.g. advanced driver assistance system (ADAS). The impact of image approximations that tolerate certain error on these image-based control (IBC) systems is very important. However, there is a lack of tool support to evaluate the performance of such closed-loop IBC systems when the IP is approximated. We propose a framework - for both software-in-the-loop (SiL) and hardware-in-the-loop (HiL) simulation - for performance evaluation of image approximation on a closed-loop automotive IBC system (IMACS). Both simulation setups model the 3D environment in 3ds Max, and simulate the system dynamics, camera position and environment in V-REP. Our SiL setup simulates the system software in C++ or Matlab. Here, V-REP runs as a server and the software as a client in synchronous mode. Our HiL simulation setup runs the system software in the NVIDIA Drive PX2 platform and communicates to V-REP using application programming interfaces (APIs) for synchronous execution. We show the effectiveness of our framework using a vision-based lateral control example.
LanguageEnglish
Title of host publication8th Mediterranean Conference on Embedded Computing (MECO)
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers
Number of pages4
ISBN (Electronic)978-1-7281-1740-9
ISBN (Print)978-1-7281-1739-3
DOIs
StatePublished - 2019
Event8th Mediterranean Conference on Embedded Computing (MECO) - Budva, Montenegro
Duration: 10 Jun 201914 Jun 2019

Conference

Conference8th Mediterranean Conference on Embedded Computing (MECO)
CountryMontenegro
CityBudva
Period10/06/1914/06/19

Fingerprint

Closed loop systems
Image processing
Control systems
Cameras
Advanced driver assistance systems
Hardware
Closed loop control systems
Processing
Application programming interfaces (API)
Dynamical systems
Servers
Costs

Cite this

Mohamed, S., De, S., Bimpisidis, K., Nathan, V., Goswami, D., Corporaal, H., & Basten, T. (2019). IMACS: a framework for performance evaluation of image approximation in a closed-loop system. In 8th Mediterranean Conference on Embedded Computing (MECO) [8760055] Piscataway: Institute of Electrical and Electronics Engineers. DOI: 10.1109/MECO.2019.8760055
Mohamed, Sajid ; De, Sayandip ; Bimpisidis, Konstantinos ; Nathan, Vishak ; Goswami, Dip ; Corporaal, Henk ; Basten, Twan. / IMACS : a framework for performance evaluation of image approximation in a closed-loop system. 8th Mediterranean Conference on Embedded Computing (MECO). Piscataway : Institute of Electrical and Electronics Engineers, 2019.
@inproceedings{89303fbff58049c3a572cd5487753653,
title = "IMACS: a framework for performance evaluation of image approximation in a closed-loop system",
abstract = "Image Processing (IP) applications have become popular with the advent of efficient algorithms and low-cost CMOS cameras with high resolution. However, IP applications are compute-intensive, consume a lot of energy and have long processing times. Image approximation has been proposed by recent works for an energy-efficient design of these applications. It also reduces the impact of long processing times. The challenge here is that the IP applications often work as a part of bigger closed-loop control systems, e.g. advanced driver assistance system (ADAS). The impact of image approximations that tolerate certain error on these image-based control (IBC) systems is very important. However, there is a lack of tool support to evaluate the performance of such closed-loop IBC systems when the IP is approximated. We propose a framework - for both software-in-the-loop (SiL) and hardware-in-the-loop (HiL) simulation - for performance evaluation of image approximation on a closed-loop automotive IBC system (IMACS). Both simulation setups model the 3D environment in 3ds Max, and simulate the system dynamics, camera position and environment in V-REP. Our SiL setup simulates the system software in C++ or Matlab. Here, V-REP runs as a server and the software as a client in synchronous mode. Our HiL simulation setup runs the system software in the NVIDIA Drive PX2 platform and communicates to V-REP using application programming interfaces (APIs) for synchronous execution. We show the effectiveness of our framework using a vision-based lateral control example.",
author = "Sajid Mohamed and Sayandip De and Konstantinos Bimpisidis and Vishak Nathan and Dip Goswami and Henk Corporaal and Twan Basten",
year = "2019",
doi = "10.1109/MECO.2019.8760055",
language = "English",
isbn = "978-1-7281-1739-3",
booktitle = "8th Mediterranean Conference on Embedded Computing (MECO)",
publisher = "Institute of Electrical and Electronics Engineers",
address = "United States",

}

Mohamed, S, De, S, Bimpisidis, K, Nathan, V, Goswami, D, Corporaal, H & Basten, T 2019, IMACS: a framework for performance evaluation of image approximation in a closed-loop system. in 8th Mediterranean Conference on Embedded Computing (MECO)., 8760055, Institute of Electrical and Electronics Engineers, Piscataway, 8th Mediterranean Conference on Embedded Computing (MECO), Budva, Montenegro, 10/06/19. DOI: 10.1109/MECO.2019.8760055

IMACS : a framework for performance evaluation of image approximation in a closed-loop system. / Mohamed, Sajid; De, Sayandip; Bimpisidis, Konstantinos; Nathan, Vishak; Goswami, Dip; Corporaal, Henk; Basten, Twan.

8th Mediterranean Conference on Embedded Computing (MECO). Piscataway : Institute of Electrical and Electronics Engineers, 2019. 8760055.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - IMACS

T2 - a framework for performance evaluation of image approximation in a closed-loop system

AU - Mohamed,Sajid

AU - De,Sayandip

AU - Bimpisidis,Konstantinos

AU - Nathan,Vishak

AU - Goswami,Dip

AU - Corporaal,Henk

AU - Basten,Twan

PY - 2019

Y1 - 2019

N2 - Image Processing (IP) applications have become popular with the advent of efficient algorithms and low-cost CMOS cameras with high resolution. However, IP applications are compute-intensive, consume a lot of energy and have long processing times. Image approximation has been proposed by recent works for an energy-efficient design of these applications. It also reduces the impact of long processing times. The challenge here is that the IP applications often work as a part of bigger closed-loop control systems, e.g. advanced driver assistance system (ADAS). The impact of image approximations that tolerate certain error on these image-based control (IBC) systems is very important. However, there is a lack of tool support to evaluate the performance of such closed-loop IBC systems when the IP is approximated. We propose a framework - for both software-in-the-loop (SiL) and hardware-in-the-loop (HiL) simulation - for performance evaluation of image approximation on a closed-loop automotive IBC system (IMACS). Both simulation setups model the 3D environment in 3ds Max, and simulate the system dynamics, camera position and environment in V-REP. Our SiL setup simulates the system software in C++ or Matlab. Here, V-REP runs as a server and the software as a client in synchronous mode. Our HiL simulation setup runs the system software in the NVIDIA Drive PX2 platform and communicates to V-REP using application programming interfaces (APIs) for synchronous execution. We show the effectiveness of our framework using a vision-based lateral control example.

AB - Image Processing (IP) applications have become popular with the advent of efficient algorithms and low-cost CMOS cameras with high resolution. However, IP applications are compute-intensive, consume a lot of energy and have long processing times. Image approximation has been proposed by recent works for an energy-efficient design of these applications. It also reduces the impact of long processing times. The challenge here is that the IP applications often work as a part of bigger closed-loop control systems, e.g. advanced driver assistance system (ADAS). The impact of image approximations that tolerate certain error on these image-based control (IBC) systems is very important. However, there is a lack of tool support to evaluate the performance of such closed-loop IBC systems when the IP is approximated. We propose a framework - for both software-in-the-loop (SiL) and hardware-in-the-loop (HiL) simulation - for performance evaluation of image approximation on a closed-loop automotive IBC system (IMACS). Both simulation setups model the 3D environment in 3ds Max, and simulate the system dynamics, camera position and environment in V-REP. Our SiL setup simulates the system software in C++ or Matlab. Here, V-REP runs as a server and the software as a client in synchronous mode. Our HiL simulation setup runs the system software in the NVIDIA Drive PX2 platform and communicates to V-REP using application programming interfaces (APIs) for synchronous execution. We show the effectiveness of our framework using a vision-based lateral control example.

UR - http://www.es.ele.tue.nl/cps/automotive/#imacs

U2 - 10.1109/MECO.2019.8760055

DO - 10.1109/MECO.2019.8760055

M3 - Conference contribution

SN - 978-1-7281-1739-3

BT - 8th Mediterranean Conference on Embedded Computing (MECO)

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

ER -

Mohamed S, De S, Bimpisidis K, Nathan V, Goswami D, Corporaal H et al. IMACS: a framework for performance evaluation of image approximation in a closed-loop system. In 8th Mediterranean Conference on Embedded Computing (MECO). Piscataway: Institute of Electrical and Electronics Engineers. 2019. 8760055. Available from, DOI: 10.1109/MECO.2019.8760055