A glance over the past decade: road scene parsing towards safe and comfortable autonomous driving

Rui Fan; Jiahang Li; Jiaqi Li; Jiale Wang; Ziwei Long; Ning Jia; Yanan Liu; Wenshuo Wang; Mohammud J. Bocus; Sergey Vityazev; Xieyuanli Chen; Junhao Xiao; Stepan Andreev; Huimin Lu; Alexander Dvorkovich

doi:10.1007/s43684-025-00096-y

A glance over the past decade: road scene parsing towards safe and comfortable autonomous driving

Rui Fan^*, Jiahang Li, Jiaqi Li, Jiale Wang, Ziwei Long, Ning Jia, Yanan Liu, Wenshuo Wang, Mohammud J. Bocus, Sergey Vityazev, Xieyuanli Chen, Junhao Xiao, Stepan Andreev, Huimin Lu, Alexander Dvorkovich

^*Corresponding author for this work

School of Mechanical Engineering

Research output: Contribution to journal › Review article › peer-review

Abstract

Road scene parsing is a crucial capability for self-driving vehicles and intelligent road inspection systems. Recent research has increasingly focused on enhancing driving safety and comfort by improving the detection of both drivable areas and road defects. This article reviews state-of-the-art networks developed over the past decade for both general-purpose semantic segmentation and specialized road scene parsing tasks. It also includes extensive experimental comparisons of these networks across five public datasets. Additionally, we explore the key challenges and emerging trends in the field, aiming to guide researchers toward developing next-generation models for more effective and reliable road scene parsing.

Original language	English
Article number	8
Journal	Autonomous Intelligent Systems
Volume	5
Issue number	1
DOIs	https://doi.org/10.1007/s43684-025-00096-y
Publication status	Published - Dec 2025

Keywords

Drivable area
Intelligent road inspection
Road defect
Road scene parsing
Self-driving vehicle

Access to Document

10.1007/s43684-025-00096-y

Cite this

@article{8695f9e458d342f0b3b3b20bd7e6ae8b,

title = "A glance over the past decade: road scene parsing towards safe and comfortable autonomous driving",

abstract = "Road scene parsing is a crucial capability for self-driving vehicles and intelligent road inspection systems. Recent research has increasingly focused on enhancing driving safety and comfort by improving the detection of both drivable areas and road defects. This article reviews state-of-the-art networks developed over the past decade for both general-purpose semantic segmentation and specialized road scene parsing tasks. It also includes extensive experimental comparisons of these networks across five public datasets. Additionally, we explore the key challenges and emerging trends in the field, aiming to guide researchers toward developing next-generation models for more effective and reliable road scene parsing.",

keywords = "Drivable area, Intelligent road inspection, Road defect, Road scene parsing, Self-driving vehicle",

author = "Rui Fan and Jiahang Li and Jiaqi Li and Jiale Wang and Ziwei Long and Ning Jia and Yanan Liu and Wenshuo Wang and Bocus, {Mohammud J.} and Sergey Vityazev and Xieyuanli Chen and Junhao Xiao and Stepan Andreev and Huimin Lu and Alexander Dvorkovich",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2025.",

year = "2025",

month = dec,

doi = "10.1007/s43684-025-00096-y",

language = "English",

volume = "5",

journal = "Autonomous Intelligent Systems",

issn = "2730-616X",

publisher = "Springer",

number = "1",

}

TY - JOUR

T1 - A glance over the past decade

T2 - road scene parsing towards safe and comfortable autonomous driving

AU - Fan, Rui

AU - Li, Jiahang

AU - Li, Jiaqi

AU - Wang, Jiale

AU - Long, Ziwei

AU - Jia, Ning

AU - Liu, Yanan

AU - Wang, Wenshuo

AU - Bocus, Mohammud J.

AU - Vityazev, Sergey

AU - Chen, Xieyuanli

AU - Xiao, Junhao

AU - Andreev, Stepan

AU - Lu, Huimin

AU - Dvorkovich, Alexander

PY - 2025/12

Y1 - 2025/12

N2 - Road scene parsing is a crucial capability for self-driving vehicles and intelligent road inspection systems. Recent research has increasingly focused on enhancing driving safety and comfort by improving the detection of both drivable areas and road defects. This article reviews state-of-the-art networks developed over the past decade for both general-purpose semantic segmentation and specialized road scene parsing tasks. It also includes extensive experimental comparisons of these networks across five public datasets. Additionally, we explore the key challenges and emerging trends in the field, aiming to guide researchers toward developing next-generation models for more effective and reliable road scene parsing.

AB - Road scene parsing is a crucial capability for self-driving vehicles and intelligent road inspection systems. Recent research has increasingly focused on enhancing driving safety and comfort by improving the detection of both drivable areas and road defects. This article reviews state-of-the-art networks developed over the past decade for both general-purpose semantic segmentation and specialized road scene parsing tasks. It also includes extensive experimental comparisons of these networks across five public datasets. Additionally, we explore the key challenges and emerging trends in the field, aiming to guide researchers toward developing next-generation models for more effective and reliable road scene parsing.

KW - Drivable area

KW - Intelligent road inspection

KW - Road defect

KW - Road scene parsing

KW - Self-driving vehicle

UR - http://www.scopus.com/inward/record.url?scp=105000078853&partnerID=8YFLogxK

U2 - 10.1007/s43684-025-00096-y

DO - 10.1007/s43684-025-00096-y

M3 - Review article

AN - SCOPUS:105000078853

SN - 2730-616X

VL - 5

JO - Autonomous Intelligent Systems

JF - Autonomous Intelligent Systems

IS - 1

M1 - 8

ER -

A glance over the past decade: road scene parsing towards safe and comfortable autonomous driving

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this