Enhancing ADAS Reliability Under Adverse Weather: Computer Vision Challenges and Advanced Dehazing Solutions

Bowen Guan

doi:10.1145/3801228.3801338

Enhancing ADAS Reliability Under Adverse Weather: Computer Vision Challenges and Advanced Dehazing Solutions

Bowen Guan^*

^*Corresponding author for this work

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

Abstract

The environmental perception capability of autonomous driving assistance systems is highly dependent on computer vision and pattern recognition technologies. However, complex road conditions such as image degradation in rainy or foggy days pose severe challenges to visual feature extraction and target pattern recognition. This article focuses on the core scenarios: “Image degradation processing in rainy/foggy days”, analyzes the pain points of computer vision, and systematically expounds technical response strategies from traditional algorithms to deep learning, providing ideas for improving the scene robustness of autonomous driving assistance systems.

Original language	English
Title of host publication	Proceedings of 2026 5th International Conference on Big Data, Information and Computer Network, BDICN 2026
Place of Publication	New York, NY, USA
Publisher	Association for Computing Machinery (ACM)
Pages	709–715
Number of pages	7
ISBN (Electronic)	9798400721755
ISBN (Print)	9798400721755
DOIs	https://doi.org/10.1145/3801228.3801338
Publication status	Published - 9 Jan 2026
Event	BDICN 2026: 2026 5th International Conference on Big Data, Information and Computer Network - Kuala Lumpur, Malaysia Duration: 9 Jan 2026 → 11 Jan 2026

Publication series

Name	Proceedings of the International Conference on Big Data, Information and Computer Network
Publisher	Association for Computing Machinery

Conference

Conference	BDICN 2026: 2026 5th International Conference on Big Data, Information and Computer Network
Country/Territory	Malaysia
City	Kuala Lumpur
Period	9/01/26 → 11/01/26

UN SDGs

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

SDG 9 Industry, Innovation, and Infrastructure

User-Defined Keywords

Autonomous Driving Assistance Systems
Computer Vision
Dark Channel Prior
Deep Learning
Image Degradation
Image Dehazing
Robustness

Access to Document

10.1145/3801228.3801338

Cite this

Guan, B. (2026). Enhancing ADAS Reliability Under Adverse Weather: Computer Vision Challenges and Advanced Dehazing Solutions. In Proceedings of 2026 5th International Conference on Big Data, Information and Computer Network, BDICN 2026 (pp. 709–715). (Proceedings of the International Conference on Big Data, Information and Computer Network). Association for Computing Machinery (ACM). https://doi.org/10.1145/3801228.3801338

Guan, Bowen. / Enhancing ADAS Reliability Under Adverse Weather: Computer Vision Challenges and Advanced Dehazing Solutions. Proceedings of 2026 5th International Conference on Big Data, Information and Computer Network, BDICN 2026. New York, NY, USA : Association for Computing Machinery (ACM), 2026. pp. 709–715 (Proceedings of the International Conference on Big Data, Information and Computer Network).

@inproceedings{1f1ec283f0f14dd7becab3e154cf2483,

title = "Enhancing ADAS Reliability Under Adverse Weather: Computer Vision Challenges and Advanced Dehazing Solutions",

abstract = "The environmental perception capability of autonomous driving assistance systems is highly dependent on computer vision and pattern recognition technologies. However, complex road conditions such as image degradation in rainy or foggy days pose severe challenges to visual feature extraction and target pattern recognition. This article focuses on the core scenarios: “Image degradation processing in rainy/foggy days”, analyzes the pain points of computer vision, and systematically expounds technical response strategies from traditional algorithms to deep learning, providing ideas for improving the scene robustness of autonomous driving assistance systems.",

keywords = "Autonomous Driving Assistance Systems, Computer Vision, Dark Channel Prior, Deep Learning, Image Degradation, Image Dehazing, Robustness",

author = "Bowen Guan",

note = "Major Scientific Research Project of Higher Education Institutions in Anhui Province (Natural Science Category): “Research on a Deep Learning-Based Deepfake Media Forensics System” (Project No.: 2024AH040213). Publisher Copyright: {\textcopyright} 2026 Copyright held by the owner/author(s).; BDICN 2026: 2026 5th International Conference on Big Data, Information and Computer Network ; Conference date: 09-01-2026 Through 11-01-2026",

year = "2026",

month = jan,

day = "9",

doi = "10.1145/3801228.3801338",

language = "English",

isbn = "9798400721755",

series = "Proceedings of the International Conference on Big Data, Information and Computer Network",

publisher = "Association for Computing Machinery (ACM)",

pages = "709–715",

booktitle = "Proceedings of 2026 5th International Conference on Big Data, Information and Computer Network, BDICN 2026",

address = "United States",

}

Guan, B 2026, Enhancing ADAS Reliability Under Adverse Weather: Computer Vision Challenges and Advanced Dehazing Solutions. in Proceedings of 2026 5th International Conference on Big Data, Information and Computer Network, BDICN 2026. Proceedings of the International Conference on Big Data, Information and Computer Network, Association for Computing Machinery (ACM), New York, NY, USA, pp. 709–715, BDICN 2026: 2026 5th International Conference on Big Data, Information and Computer Network, Kuala Lumpur, Malaysia, 9/01/26. https://doi.org/10.1145/3801228.3801338

Enhancing ADAS Reliability Under Adverse Weather: Computer Vision Challenges and Advanced Dehazing Solutions. / Guan, Bowen.
Proceedings of 2026 5th International Conference on Big Data, Information and Computer Network, BDICN 2026. New York, NY, USA: Association for Computing Machinery (ACM), 2026. p. 709–715 (Proceedings of the International Conference on Big Data, Information and Computer Network).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Enhancing ADAS Reliability Under Adverse Weather: Computer Vision Challenges and Advanced Dehazing Solutions

AU - Guan, Bowen

N1 - Major Scientific Research Project of Higher Education Institutions in Anhui Province (Natural Science Category): “Research on a Deep Learning-Based Deepfake Media Forensics System” (Project No.: 2024AH040213). Publisher Copyright: © 2026 Copyright held by the owner/author(s).

PY - 2026/1/9

Y1 - 2026/1/9

N2 - The environmental perception capability of autonomous driving assistance systems is highly dependent on computer vision and pattern recognition technologies. However, complex road conditions such as image degradation in rainy or foggy days pose severe challenges to visual feature extraction and target pattern recognition. This article focuses on the core scenarios: “Image degradation processing in rainy/foggy days”, analyzes the pain points of computer vision, and systematically expounds technical response strategies from traditional algorithms to deep learning, providing ideas for improving the scene robustness of autonomous driving assistance systems.

AB - The environmental perception capability of autonomous driving assistance systems is highly dependent on computer vision and pattern recognition technologies. However, complex road conditions such as image degradation in rainy or foggy days pose severe challenges to visual feature extraction and target pattern recognition. This article focuses on the core scenarios: “Image degradation processing in rainy/foggy days”, analyzes the pain points of computer vision, and systematically expounds technical response strategies from traditional algorithms to deep learning, providing ideas for improving the scene robustness of autonomous driving assistance systems.

KW - Autonomous Driving Assistance Systems

KW - Computer Vision

KW - Dark Channel Prior

KW - Deep Learning

KW - Image Degradation

KW - Image Dehazing

KW - Robustness

UR - https://www.scopus.com/pages/publications/105038036264

U2 - 10.1145/3801228.3801338

DO - 10.1145/3801228.3801338

M3 - Conference proceeding

SN - 9798400721755

T3 - Proceedings of the International Conference on Big Data, Information and Computer Network

SP - 709

EP - 715

BT - Proceedings of 2026 5th International Conference on Big Data, Information and Computer Network, BDICN 2026

PB - Association for Computing Machinery (ACM)

CY - New York, NY, USA

T2 - BDICN 2026: 2026 5th International Conference on Big Data, Information and Computer Network

Y2 - 9 January 2026 through 11 January 2026

ER -

Guan B. Enhancing ADAS Reliability Under Adverse Weather: Computer Vision Challenges and Advanced Dehazing Solutions. In Proceedings of 2026 5th International Conference on Big Data, Information and Computer Network, BDICN 2026. New York, NY, USA: Association for Computing Machinery (ACM). 2026. p. 709–715. (Proceedings of the International Conference on Big Data, Information and Computer Network). doi: 10.1145/3801228.3801338

Enhancing ADAS Reliability Under Adverse Weather: Computer Vision Challenges and Advanced Dehazing Solutions

Abstract

Publication series

Conference

UN SDGs

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this