Road Line Marking Segmentation Using Multi Variants of YOLOv8 and YOLOv11 in CCTV Traffic Videos

Fandisya Rahman; Anny Yuniarti; Ahmad Saikhu

doi:10.1109/ISITIA66279.2025.11137473

Road Line Marking Segmentation Using Multi Variants of YOLOv8 and YOLOv11 in CCTV Traffic Videos

Fandisya Rahman
, Anny Yuniarti^*
, Ahmad Saikhu

^*Corresponding author for this work

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

Abstract

Vehicle speed measurement plays a pivotal role in terms of detecting speed violations by the transport user. To measure vehicle speed in CCTV camera manner, a homography transformation network is used to transform video scene as a bird-eye view paradigm. However, an approach that can help initiate this algorithm only once when processing the first frame of a video is needed. This paper proposed segmentation of the road line marking to help produce homography transformation to measure vehicle speed in the CCTV video scene. YOLOv8 and YOLOv11 with small, medium, large, and extra large variants are used to segment road line marking from road line marking data set. The results of the segmentation metrics show that all variants of YOLOv8 beat all variants of YOLOv11 in the majority of the segmentation metrics. Then, YOLOv8 medium has the best mAP50 with value of 0.868 while YOLOv8 large has the best mAP50-95 with value of 0.468. The inference analysis result also shows that the large variant of YOLOv11 beat all variants of YOLOv8 and YOLOv11 in test images which are totally different from the dataset given.

Original language	English
Title of host publication	26th International Seminar on Intelligent Technology and Its Applications
Subtitle of host publication	Fostering Equal Opportunities for Breakthrough Technology Innovations, ISITIA 2025 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	254-259
Number of pages	6
Edition	2025
ISBN (Electronic)	9798331537609
DOIs	https://doi.org/10.1109/ISITIA66279.2025.11137473
Publication status	Published - 2025
Event	26th International Seminar on Intelligent Technology and Its Applications, ISITIA 2025 - Hybrid, Surabaya, Indonesia Duration: 23 Jul 2025 → 25 Jul 2025

Conference

Conference	26th International Seminar on Intelligent Technology and Its Applications, ISITIA 2025
Country/Territory	Indonesia
City	Hybrid, Surabaya
Period	23/07/25 → 25/07/25

UN SDGs

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

SDG 7 Affordable and Clean Energy

Keywords

CCTV Videos
Road Line Marking Segmentation
Sustainable Cities And Communities
YOLOv11
YOLOv8

Access to Document

10.1109/ISITIA66279.2025.11137473

Cite this

Rahman, F., Yuniarti, A., & Saikhu, A. (2025). Road Line Marking Segmentation Using Multi Variants of YOLOv8 and YOLOv11 in CCTV Traffic Videos. In 26th International Seminar on Intelligent Technology and Its Applications: Fostering Equal Opportunities for Breakthrough Technology Innovations, ISITIA 2025 - Proceedings (2025 ed., pp. 254-259). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISITIA66279.2025.11137473

Rahman, Fandisya ; Yuniarti, Anny ; Saikhu, Ahmad. / Road Line Marking Segmentation Using Multi Variants of YOLOv8 and YOLOv11 in CCTV Traffic Videos. 26th International Seminar on Intelligent Technology and Its Applications: Fostering Equal Opportunities for Breakthrough Technology Innovations, ISITIA 2025 - Proceedings. 2025. ed. Institute of Electrical and Electronics Engineers Inc., 2025. pp. 254-259

@inproceedings{3b1a369391964582a2379cd4859bbc74,

title = "Road Line Marking Segmentation Using Multi Variants of YOLOv8 and YOLOv11 in CCTV Traffic Videos",

abstract = "Vehicle speed measurement plays a pivotal role in terms of detecting speed violations by the transport user. To measure vehicle speed in CCTV camera manner, a homography transformation network is used to transform video scene as a bird-eye view paradigm. However, an approach that can help initiate this algorithm only once when processing the first frame of a video is needed. This paper proposed segmentation of the road line marking to help produce homography transformation to measure vehicle speed in the CCTV video scene. YOLOv8 and YOLOv11 with small, medium, large, and extra large variants are used to segment road line marking from road line marking data set. The results of the segmentation metrics show that all variants of YOLOv8 beat all variants of YOLOv11 in the majority of the segmentation metrics. Then, YOLOv8 medium has the best mAP50 with value of 0.868 while YOLOv8 large has the best mAP50-95 with value of 0.468. The inference analysis result also shows that the large variant of YOLOv11 beat all variants of YOLOv8 and YOLOv11 in test images which are totally different from the dataset given.",

keywords = "CCTV Videos, Road Line Marking Segmentation, Sustainable Cities And Communities, YOLOv11, YOLOv8",

author = "Fandisya Rahman and Anny Yuniarti and Ahmad Saikhu",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 26th International Seminar on Intelligent Technology and Its Applications, ISITIA 2025 ; Conference date: 23-07-2025 Through 25-07-2025",

year = "2025",

doi = "10.1109/ISITIA66279.2025.11137473",

language = "English",

pages = "254--259",

booktitle = "26th International Seminar on Intelligent Technology and Its Applications",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

edition = "2025",

}

Rahman, F, Yuniarti, A & Saikhu, A 2025, Road Line Marking Segmentation Using Multi Variants of YOLOv8 and YOLOv11 in CCTV Traffic Videos. in 26th International Seminar on Intelligent Technology and Its Applications: Fostering Equal Opportunities for Breakthrough Technology Innovations, ISITIA 2025 - Proceedings. 2025 edn, Institute of Electrical and Electronics Engineers Inc., pp. 254-259, 26th International Seminar on Intelligent Technology and Its Applications, ISITIA 2025, Hybrid, Surabaya, Indonesia, 23/07/25. https://doi.org/10.1109/ISITIA66279.2025.11137473

Road Line Marking Segmentation Using Multi Variants of YOLOv8 and YOLOv11 in CCTV Traffic Videos. / Rahman, Fandisya; Yuniarti, Anny ; Saikhu, Ahmad.
26th International Seminar on Intelligent Technology and Its Applications: Fostering Equal Opportunities for Breakthrough Technology Innovations, ISITIA 2025 - Proceedings. 2025. ed. Institute of Electrical and Electronics Engineers Inc., 2025. p. 254-259.

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

TY - GEN

T1 - Road Line Marking Segmentation Using Multi Variants of YOLOv8 and YOLOv11 in CCTV Traffic Videos

AU - Rahman, Fandisya

AU - Yuniarti, Anny

AU - Saikhu, Ahmad

PY - 2025

Y1 - 2025

N2 - Vehicle speed measurement plays a pivotal role in terms of detecting speed violations by the transport user. To measure vehicle speed in CCTV camera manner, a homography transformation network is used to transform video scene as a bird-eye view paradigm. However, an approach that can help initiate this algorithm only once when processing the first frame of a video is needed. This paper proposed segmentation of the road line marking to help produce homography transformation to measure vehicle speed in the CCTV video scene. YOLOv8 and YOLOv11 with small, medium, large, and extra large variants are used to segment road line marking from road line marking data set. The results of the segmentation metrics show that all variants of YOLOv8 beat all variants of YOLOv11 in the majority of the segmentation metrics. Then, YOLOv8 medium has the best mAP50 with value of 0.868 while YOLOv8 large has the best mAP50-95 with value of 0.468. The inference analysis result also shows that the large variant of YOLOv11 beat all variants of YOLOv8 and YOLOv11 in test images which are totally different from the dataset given.

AB - Vehicle speed measurement plays a pivotal role in terms of detecting speed violations by the transport user. To measure vehicle speed in CCTV camera manner, a homography transformation network is used to transform video scene as a bird-eye view paradigm. However, an approach that can help initiate this algorithm only once when processing the first frame of a video is needed. This paper proposed segmentation of the road line marking to help produce homography transformation to measure vehicle speed in the CCTV video scene. YOLOv8 and YOLOv11 with small, medium, large, and extra large variants are used to segment road line marking from road line marking data set. The results of the segmentation metrics show that all variants of YOLOv8 beat all variants of YOLOv11 in the majority of the segmentation metrics. Then, YOLOv8 medium has the best mAP50 with value of 0.868 while YOLOv8 large has the best mAP50-95 with value of 0.468. The inference analysis result also shows that the large variant of YOLOv11 beat all variants of YOLOv8 and YOLOv11 in test images which are totally different from the dataset given.

KW - CCTV Videos

KW - Road Line Marking Segmentation

KW - Sustainable Cities And Communities

KW - YOLOv11

KW - YOLOv8

UR - https://www.scopus.com/pages/publications/105016905514

U2 - 10.1109/ISITIA66279.2025.11137473

DO - 10.1109/ISITIA66279.2025.11137473

M3 - Conference contribution

AN - SCOPUS:105016905514

SP - 254

EP - 259

BT - 26th International Seminar on Intelligent Technology and Its Applications

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 26th International Seminar on Intelligent Technology and Its Applications, ISITIA 2025

Y2 - 23 July 2025 through 25 July 2025

ER -

Rahman F, Yuniarti A , Saikhu A. Road Line Marking Segmentation Using Multi Variants of YOLOv8 and YOLOv11 in CCTV Traffic Videos. In 26th International Seminar on Intelligent Technology and Its Applications: Fostering Equal Opportunities for Breakthrough Technology Innovations, ISITIA 2025 - Proceedings. 2025 ed. Institute of Electrical and Electronics Engineers Inc. 2025. p. 254-259 doi: 10.1109/ISITIA66279.2025.11137473

Road Line Marking Segmentation Using Multi Variants of YOLOv8 and YOLOv11 in CCTV Traffic Videos

Abstract

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this