Automative Video Compression for Remote Driving via Safety Considerations

Dan Peled; Armin Shmilovici; Ofer Hadar

doi:10.1109/CSCN60443.2023.10453135

Automative Video Compression for Remote Driving via Safety Considerations

Dan Peled, Armin Shmilovici, Ofer Hadar

Ben-Gurion University of the Negev

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

Abstract

Remote driving serves as a viable solution in situations where fully autonomous vehicles encounter critical events, such as sensor failures. However, implementing remote driving poses certain technical challenges, including the need to ensure high-quality video transmission to the remote driver. Additionally, in scenarios involving poor road conditions, multiple autonomous vehicles may simultaneously require remote driving assistance at specific locations, straining the communication infrastructure. To address these challenges, we propose a novel approach that involves compression of the driving video using a driving safety model. This model intelligently prioritizes key objects within the frame, resulting in improved compression quality. An initial experiment demonstrated that 60% of the required bitrate can be reduced while retaining 90% of the perceived quality.

Original language	American English
Title of host publication	2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023
Pages	54-58
Number of pages	5
ISBN (Electronic)	9798350395389
DOIs	https://doi.org/10.1109/CSCN60443.2023.10453135
State	Published - 1 Jan 2023
Event	2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023 - Munich, Germany Duration: 6 Nov 2023 → 8 Nov 2023

Publication series

Name	2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023

Conference

Conference	2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023
Country/Territory	Germany
City	Munich
Period	6/11/23 → 8/11/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Autonomous Cars
Region of Interest
Remote Driver
Safety
Video Compression

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Hardware and Architecture
Safety, Risk, Reliability and Quality

Access to Document

10.1109/CSCN60443.2023.10453135

Cite this

@inproceedings{f7060b4ddc684ca2bf3100ef96520eb6,

title = "Automative Video Compression for Remote Driving via Safety Considerations",

abstract = "Remote driving serves as a viable solution in situations where fully autonomous vehicles encounter critical events, such as sensor failures. However, implementing remote driving poses certain technical challenges, including the need to ensure high-quality video transmission to the remote driver. Additionally, in scenarios involving poor road conditions, multiple autonomous vehicles may simultaneously require remote driving assistance at specific locations, straining the communication infrastructure. To address these challenges, we propose a novel approach that involves compression of the driving video using a driving safety model. This model intelligently prioritizes key objects within the frame, resulting in improved compression quality. An initial experiment demonstrated that 60\% of the required bitrate can be reduced while retaining 90\% of the perceived quality.",

keywords = "Autonomous Cars, Region of Interest, Remote Driver, Safety, Video Compression",

author = "Dan Peled and Armin Shmilovici and Ofer Hadar",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023 ; Conference date: 06-11-2023 Through 08-11-2023",

year = "2023",

month = jan,

day = "1",

doi = "10.1109/CSCN60443.2023.10453135",

language = "American English",

series = "2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023",

pages = "54--58",

booktitle = "2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023",

}

Peled, D, Shmilovici, A & Hadar, O 2023, Automative Video Compression for Remote Driving via Safety Considerations. in 2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023. 2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023, pp. 54-58, 2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023, Munich, Germany, 6/11/23. https://doi.org/10.1109/CSCN60443.2023.10453135

Automative Video Compression for Remote Driving via Safety Considerations. / Peled, Dan; Shmilovici, Armin ; Hadar, Ofer.
2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023. 2023. p. 54-58 (2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023).

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

TY - GEN

T1 - Automative Video Compression for Remote Driving via Safety Considerations

AU - Peled, Dan

AU - Shmilovici, Armin

AU - Hadar, Ofer

PY - 2023/1/1

Y1 - 2023/1/1

N2 - Remote driving serves as a viable solution in situations where fully autonomous vehicles encounter critical events, such as sensor failures. However, implementing remote driving poses certain technical challenges, including the need to ensure high-quality video transmission to the remote driver. Additionally, in scenarios involving poor road conditions, multiple autonomous vehicles may simultaneously require remote driving assistance at specific locations, straining the communication infrastructure. To address these challenges, we propose a novel approach that involves compression of the driving video using a driving safety model. This model intelligently prioritizes key objects within the frame, resulting in improved compression quality. An initial experiment demonstrated that 60% of the required bitrate can be reduced while retaining 90% of the perceived quality.

AB - Remote driving serves as a viable solution in situations where fully autonomous vehicles encounter critical events, such as sensor failures. However, implementing remote driving poses certain technical challenges, including the need to ensure high-quality video transmission to the remote driver. Additionally, in scenarios involving poor road conditions, multiple autonomous vehicles may simultaneously require remote driving assistance at specific locations, straining the communication infrastructure. To address these challenges, we propose a novel approach that involves compression of the driving video using a driving safety model. This model intelligently prioritizes key objects within the frame, resulting in improved compression quality. An initial experiment demonstrated that 60% of the required bitrate can be reduced while retaining 90% of the perceived quality.

KW - Autonomous Cars

KW - Region of Interest

KW - Remote Driver

KW - Safety

KW - Video Compression

UR - http://www.scopus.com/inward/record.url?scp=85187805895&partnerID=8YFLogxK

U2 - 10.1109/CSCN60443.2023.10453135

DO - 10.1109/CSCN60443.2023.10453135

M3 - Conference contribution

T3 - 2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023

SP - 54

EP - 58

BT - 2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023

T2 - 2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023

Y2 - 6 November 2023 through 8 November 2023

ER -

Automative Video Compression for Remote Driving via Safety Considerations

Abstract

Publication series

Conference

UN SDGs

Keywords

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this