CiThruS2: Open-Source Simulation Framework for Vision-Based ADAS Development

Arttu Leppäaho; Panu Sjövall; Guillaume Gautier; Jarno Vanne

doi:10.1109/iavvc61942.2025.11219636

CiThruS2: Open-Source Simulation Framework for Vision-Based ADAS Development

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

8 Downloads (Pure)

Abstract

Vision-based Advanced Driver Assistance Systems (ADAS) rely on cameras and other sensor modalities whose correct functionality tends to be guaranteed through rigorous physical testing. However, the increasing complexity of ADAS makes exhaustive real-world testing impractical, so the automotive sector is increasingly turning to more agile virtual test environments. This paper presents the latest version of our open-source CiThruS2 traffic simulation framework that introduces a flexible vision pipeline system for seamlessly transitioning between virtual and physical worlds. The system supports visual data streaming in the High Efficiency Video Coding (HEVC) format over the Real-time Transport Protocol (RTP), thereby offering an efficient and standardized communication interface for vision-based ADAS testing and validation. The pipeline usage is illustrated with a diminished reality (DR) use case, where depth image-based rendering is applied to virtually eliminate blind spots in the driver's field of view and raise their awareness of occluded road users.

Original language	English
Title of host publication	2025 IEEE International Automated Vehicle Validation Conference (IAVVC)
Publisher	IEEE
Pages	1-6
ISBN (Electronic)	979-8-3315-2526-2
ISBN (Print)	979-8-3315-2527-9
DOIs	https://doi.org/10.1109/iavvc61942.2025.11219636
Publication status	Published - 2025
Publication type	A4 Article in conference proceedings
Event	IEEE International Automated Vehicle Validation Conference - Baden-Baden, Germany Duration: 30 Sept 2025 → 2 Oct 2025

Conference

Conference	IEEE International Automated Vehicle Validation Conference
Country/Territory	Germany
City	Baden-Baden
Period	30/09/25 → 2/10/25

Funding

This work was supported by the SHAPEFUTURE project co-funded by the European Union under the Grant Agreement no. 101139996-2 and national authorities including Business Finland.

Funders	Funder number
European Union	101139996-2

Keywords

open-source software
real-time simulation
advanced driver assistance systems (ADAS)
diminished reality

Publication forum classification

Publication forum level 1

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Computer Graphics and Computer-Aided Design
Safety, Risk, Reliability and Quality
Instrumentation

Access to Document

10.1109/iavvc61942.2025.11219636

CiThruS2_Vision-Based_ADAS_2025Accepted author manuscript, 890 KB

https://urn.fi/URN:NBN:fi:tuni-2025121811907

Cite this

@inproceedings{bb451d01bf7640988463cdd0fad2f2d5,

title = "CiThruS2: Open-Source Simulation Framework for Vision-Based ADAS Development",

abstract = "Vision-based Advanced Driver Assistance Systems (ADAS) rely on cameras and other sensor modalities whose correct functionality tends to be guaranteed through rigorous physical testing. However, the increasing complexity of ADAS makes exhaustive real-world testing impractical, so the automotive sector is increasingly turning to more agile virtual test environments. This paper presents the latest version of our open-source CiThruS2 traffic simulation framework that introduces a flexible vision pipeline system for seamlessly transitioning between virtual and physical worlds. The system supports visual data streaming in the High Efficiency Video Coding (HEVC) format over the Real-time Transport Protocol (RTP), thereby offering an efficient and standardized communication interface for vision-based ADAS testing and validation. The pipeline usage is illustrated with a diminished reality (DR) use case, where depth image-based rendering is applied to virtually eliminate blind spots in the driver's field of view and raise their awareness of occluded road users.",

keywords = "open-source software, real-time simulation, advanced driver assistance systems (ADAS), diminished reality",

author = "Arttu Lepp{\"a}aho and Panu Sj{\"o}vall and Guillaume Gautier and Jarno Vanne",

year = "2025",

doi = "10.1109/iavvc61942.2025.11219636",

language = "English",

isbn = "979-8-3315-2527-9",

pages = "1--6",

booktitle = "2025 IEEE International Automated Vehicle Validation Conference (IAVVC)",

publisher = "IEEE",

address = "United States",

note = "IEEE International Automated Vehicle Validation Conference ; Conference date: 30-09-2025 Through 02-10-2025",

}

TY - GEN

T1 - CiThruS2: Open-Source Simulation Framework for Vision-Based ADAS Development

AU - Leppäaho, Arttu

AU - Sjövall, Panu

AU - Gautier, Guillaume

AU - Vanne, Jarno

PY - 2025

Y1 - 2025

N2 - Vision-based Advanced Driver Assistance Systems (ADAS) rely on cameras and other sensor modalities whose correct functionality tends to be guaranteed through rigorous physical testing. However, the increasing complexity of ADAS makes exhaustive real-world testing impractical, so the automotive sector is increasingly turning to more agile virtual test environments. This paper presents the latest version of our open-source CiThruS2 traffic simulation framework that introduces a flexible vision pipeline system for seamlessly transitioning between virtual and physical worlds. The system supports visual data streaming in the High Efficiency Video Coding (HEVC) format over the Real-time Transport Protocol (RTP), thereby offering an efficient and standardized communication interface for vision-based ADAS testing and validation. The pipeline usage is illustrated with a diminished reality (DR) use case, where depth image-based rendering is applied to virtually eliminate blind spots in the driver's field of view and raise their awareness of occluded road users.

AB - Vision-based Advanced Driver Assistance Systems (ADAS) rely on cameras and other sensor modalities whose correct functionality tends to be guaranteed through rigorous physical testing. However, the increasing complexity of ADAS makes exhaustive real-world testing impractical, so the automotive sector is increasingly turning to more agile virtual test environments. This paper presents the latest version of our open-source CiThruS2 traffic simulation framework that introduces a flexible vision pipeline system for seamlessly transitioning between virtual and physical worlds. The system supports visual data streaming in the High Efficiency Video Coding (HEVC) format over the Real-time Transport Protocol (RTP), thereby offering an efficient and standardized communication interface for vision-based ADAS testing and validation. The pipeline usage is illustrated with a diminished reality (DR) use case, where depth image-based rendering is applied to virtually eliminate blind spots in the driver's field of view and raise their awareness of occluded road users.

KW - open-source software

KW - real-time simulation

KW - advanced driver assistance systems (ADAS)

KW - diminished reality

UR - http://dx.doi.org/10.1109/iavvc61942.2025.11219636

U2 - 10.1109/iavvc61942.2025.11219636

DO - 10.1109/iavvc61942.2025.11219636

M3 - Conference contribution

SN - 979-8-3315-2527-9

SP - 1

EP - 6

BT - 2025 IEEE International Automated Vehicle Validation Conference (IAVVC)

PB - IEEE

T2 - IEEE International Automated Vehicle Validation Conference

Y2 - 30 September 2025 through 2 October 2025

ER -

CiThruS2: Open-Source Simulation Framework for Vision-Based ADAS Development

Abstract

Conference

Funding

Keywords

Publication forum classification

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this