Comparative Analysis of YOLOv8 and YOLOv9 on a Unified Traffic Sign Dataset

Vivek Srivastava; Sumita Mishra; Nishu Gupta; Apoorva Saxena

doi:10.1007/978-981-96-6053-7_33

Comparative Analysis of YOLOv8 and YOLOv9 on a Unified Traffic Sign Dataset

Vivek Srivastava^*
, Sumita Mishra
, Nishu Gupta
, Apoorva Saxena

^*Corresponding author for this work

BA6402 Future communication networks

Amity University

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

Abstract

Employing a unique set of traffic signs, this research examines the effectiveness of two versions of the You Only Look Once (YOLO) object detection framework: YOLOv8 and YOLOv9. The aim is to provide a detailed understanding of each version’s strengths and weaknesses in traffic sign detection, with implications for enhancing real-world object detection in dynamic traffic scenarios. Preliminary findings indicate that YOLOv9 outperforms YOLOv8, demonstrating higher precision and F1-score. This highlights YOLOv9’s potential for robust traffic sign detection solutions. Despite assessment, our research represents an essential contribution to the discipline of computer vision including applications to traffic sign recognition. The study’s results offer a useful resource for practitioners and researchers selecting optimal models for similar applications, ultimately contributing to developing smarter and more efficient transportation networks.

Original language	English
Title of host publication	Data Mining and Information Security: Proceedings of ICDMIS 2024
Editors	Abhishek Bhattacharya, Soumi Dutta, Md. Abdur Razzak, Debabrata Samanta
Publisher	Springer
Pages	509-520
Number of pages	12
Volume	2
ISBN (Electronic)	978-981-96-6053-7
ISBN (Print)	978-981-96-6052-0
DOIs	https://doi.org/10.1007/978-981-96-6053-7_33
Publication status	Published - 2026
MoE publication type	A4 Article in a conference publication
Event	International Conference on Data Mining and Information Security, ICDMIS 2024 - Kolkata, India Duration: 7 Oct 2024 → 8 Oct 2024

Publication series

Series	Lecture Notes in Networks and Systems
Volume	1386 LNNS
ISSN	2367-3370

Conference

Conference	International Conference on Data Mining and Information Security, ICDMIS 2024
Country/Territory	India
City	Kolkata
Period	7/10/24 → 8/10/24

Keywords

Computer vision
Dynamic traffic scenarios
Traffic sign recognition
YOLOv8
YOLOv9 algorithm

Access to Document

10.1007/978-981-96-6053-7_33

Cite this

Srivastava, Vivek ; Mishra, Sumita ; Gupta, Nishu et al. / Comparative Analysis of YOLOv8 and YOLOv9 on a Unified Traffic Sign Dataset. Data Mining and Information Security: Proceedings of ICDMIS 2024. editor / Abhishek Bhattacharya ; Soumi Dutta ; Md. Abdur Razzak ; Debabrata Samanta. Vol. 2 Springer, 2026. pp. 509-520 (Lecture Notes in Networks and Systems, Vol. 1386 LNNS).

@inproceedings{eb878471fc8a451aa41bea4a0265a493,

title = "Comparative Analysis of YOLOv8 and YOLOv9 on a Unified Traffic Sign Dataset",

abstract = "Employing a unique set of traffic signs, this research examines the effectiveness of two versions of the You Only Look Once (YOLO) object detection framework: YOLOv8 and YOLOv9. The aim is to provide a detailed understanding of each version{\textquoteright}s strengths and weaknesses in traffic sign detection, with implications for enhancing real-world object detection in dynamic traffic scenarios. Preliminary findings indicate that YOLOv9 outperforms YOLOv8, demonstrating higher precision and F1-score. This highlights YOLOv9{\textquoteright}s potential for robust traffic sign detection solutions. Despite assessment, our research represents an essential contribution to the discipline of computer vision including applications to traffic sign recognition. The study{\textquoteright}s results offer a useful resource for practitioners and researchers selecting optimal models for similar applications, ultimately contributing to developing smarter and more efficient transportation networks.",

keywords = "Computer vision, Dynamic traffic scenarios, Traffic sign recognition, YOLOv8, YOLOv9 algorithm",

author = "Vivek Srivastava and Sumita Mishra and Nishu Gupta and Apoorva Saxena",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.; International Conference on Data Mining and Information Security, ICDMIS 2024 ; Conference date: 07-10-2024 Through 08-10-2024",

year = "2026",

doi = "10.1007/978-981-96-6053-7\_33",

language = "English",

isbn = "978-981-96-6052-0",

volume = "2",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer",

pages = "509--520",

editor = "Abhishek Bhattacharya and Soumi Dutta and Razzak, \{Md. Abdur\} and Debabrata Samanta",

booktitle = "Data Mining and Information Security: Proceedings of ICDMIS 2024",

address = "Germany",

}

Srivastava, V, Mishra, S, Gupta, N & Saxena, A 2026, Comparative Analysis of YOLOv8 and YOLOv9 on a Unified Traffic Sign Dataset. in A Bhattacharya, S Dutta, MA Razzak & D Samanta (eds), Data Mining and Information Security: Proceedings of ICDMIS 2024. vol. 2, Springer, Lecture Notes in Networks and Systems, vol. 1386 LNNS, pp. 509-520, International Conference on Data Mining and Information Security, ICDMIS 2024, Kolkata, India, 7/10/24. https://doi.org/10.1007/978-981-96-6053-7_33

Comparative Analysis of YOLOv8 and YOLOv9 on a Unified Traffic Sign Dataset. / Srivastava, Vivek; Mishra, Sumita; Gupta, Nishu et al.
Data Mining and Information Security: Proceedings of ICDMIS 2024. ed. / Abhishek Bhattacharya; Soumi Dutta; Md. Abdur Razzak; Debabrata Samanta. Vol. 2 Springer, 2026. p. 509-520 (Lecture Notes in Networks and Systems, Vol. 1386 LNNS).

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

TY - GEN

T1 - Comparative Analysis of YOLOv8 and YOLOv9 on a Unified Traffic Sign Dataset

AU - Srivastava, Vivek

AU - Mishra, Sumita

AU - Gupta, Nishu

AU - Saxena, Apoorva

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.

PY - 2026

Y1 - 2026

N2 - Employing a unique set of traffic signs, this research examines the effectiveness of two versions of the You Only Look Once (YOLO) object detection framework: YOLOv8 and YOLOv9. The aim is to provide a detailed understanding of each version’s strengths and weaknesses in traffic sign detection, with implications for enhancing real-world object detection in dynamic traffic scenarios. Preliminary findings indicate that YOLOv9 outperforms YOLOv8, demonstrating higher precision and F1-score. This highlights YOLOv9’s potential for robust traffic sign detection solutions. Despite assessment, our research represents an essential contribution to the discipline of computer vision including applications to traffic sign recognition. The study’s results offer a useful resource for practitioners and researchers selecting optimal models for similar applications, ultimately contributing to developing smarter and more efficient transportation networks.

AB - Employing a unique set of traffic signs, this research examines the effectiveness of two versions of the You Only Look Once (YOLO) object detection framework: YOLOv8 and YOLOv9. The aim is to provide a detailed understanding of each version’s strengths and weaknesses in traffic sign detection, with implications for enhancing real-world object detection in dynamic traffic scenarios. Preliminary findings indicate that YOLOv9 outperforms YOLOv8, demonstrating higher precision and F1-score. This highlights YOLOv9’s potential for robust traffic sign detection solutions. Despite assessment, our research represents an essential contribution to the discipline of computer vision including applications to traffic sign recognition. The study’s results offer a useful resource for practitioners and researchers selecting optimal models for similar applications, ultimately contributing to developing smarter and more efficient transportation networks.

KW - Computer vision

KW - Dynamic traffic scenarios

KW - Traffic sign recognition

KW - YOLOv8

KW - YOLOv9 algorithm

UR - https://www.scopus.com/pages/publications/105019645091

U2 - 10.1007/978-981-96-6053-7_33

DO - 10.1007/978-981-96-6053-7_33

M3 - Conference article in proceedings

AN - SCOPUS:105019645091

SN - 978-981-96-6052-0

VL - 2

T3 - Lecture Notes in Networks and Systems

SP - 509

EP - 520

BT - Data Mining and Information Security: Proceedings of ICDMIS 2024

A2 - Bhattacharya, Abhishek

A2 - Dutta, Soumi

A2 - Razzak, Md. Abdur

A2 - Samanta, Debabrata

PB - Springer

T2 - International Conference on Data Mining and Information Security, ICDMIS 2024

Y2 - 7 October 2024 through 8 October 2024

ER -

Srivastava V, Mishra S, Gupta N, Saxena A. Comparative Analysis of YOLOv8 and YOLOv9 on a Unified Traffic Sign Dataset. In Bhattacharya A, Dutta S, Razzak MA, Samanta D, editors, Data Mining and Information Security: Proceedings of ICDMIS 2024. Vol. 2. Springer. 2026. p. 509-520. (Lecture Notes in Networks and Systems, Vol. 1386 LNNS). doi: 10.1007/978-981-96-6053-7_33