Comparative Evaluation of Yolo-Based Models for Multi-Class Weapon Detection

Selinay Erdinç; Mehmet Dikmen

doi:10.33769/aupse.1772978

Comparative Evaluation of Yolo-Based Models for Multi-Class Weapon Detection

Abstract

This study explores the effectiveness of various real-time object detectors for the problem of classifying different weapon types. To that end, the performance of YOLOv9, YOLOv10, YOLOv11, YOLOX, and YOLOR models were evaluated on a balanced dataset of 15,387 images across 5 weapon classes. All models are trained with 5-fold stratified cross-validation and YOLOR achieved the best overall performance with an mAP@0.5 of 0.8654 and mAP@0.5:0.95 of 0.8380. In addition, YOLOR obtained a precision of 0.8550, recall of 0.9570, and F1-score of 0.9210. Results show YOLOR’s suitability for high-precision, critical applications, while YOLOX offers advantages for recall-focused, resource-constrained deployments with a recall of 0.9628 despite a lower precision of 0.6902. The experiments highlighted the potential of real-time AI-based object detectors for enhancing security systems.

Keywords

References

D. G. Lowe, “Object Recognition from Local Scale-Invariant Features,” 1999.
N. Dalal and B. Triggs, “Histograms of Oriented Gradients for Human Detection.” [Online]. Available: http://lear.inrialpes.fr
P. Yadav, N. Gupta, and P. K. Sharma, “A comprehensive study towards high-level approaches for weapon detection using classical machine learning and deep learning methods,” Feb. 01, 2023, Elsevier Ltd.
N. Hnoohom, P. Chotivatunyu, and A. Jitpattanakul, “ACF: An Armed CCTV Footage Dataset for Enhancing Weapon Detection,” Sensors, vol. 22, no. 19, Oct. 2022.
S. Yellapragada et al., “CCTV-Gun: Benchmarking Handgun Detection in CCTV Images,” Jul. 2023, [Online]. Available: http://arxiv.org/abs/2303.10703
Y. Gu, X. Liao, and X. Qin, “YouTube-GDD: A challenging gun detection dataset with rich contextual information,” Mar. 2022, [Online]. Available: http://arxiv.org/abs/2203.04129
D. Berardini, L. Migliorelli, A. Galdelli, E. Frontoni, A. Mancini, and S. Moccia, “A deep-learning framework running on edge devices for handgun and knife detection from indoor video-surveillance cameras,” Multimed. Tools Appl., vol. 83, no. 7, pp. 19109–19127, Feb. 2024.
J.-S. Lim, M. Astrid, H.-J. Yoon, and S.-I. Lee, “Small Object Detection using Context and Attention,” Dec. 2019, [Online]. Available: http://arxiv.org/abs/1912.06319

T. S. S. Hashmi, N. U. Haq, M. M. Fraz, and M. Shahzad, “Application of Deep Learning for Weapons Detection in Surveillance Videos,” in 2021 International Conference on Digital Futures and Transformative Technologies, ICoDT2 2021, Institute of Electrical and Electronics Engineers Inc., May 2021.
S. Ahmed, M. T. Bhatti, M. G. Khan, B. Lövström, and M. Shahid, “Development and Optimization of Deep Learning Models for Weapon Detection in Surveillance Videos,” Applied Sciences (Switzerland), vol. 12, no. 12, Jun. 2022.
J. Lai and S. Maples, “Developing a Real-Time Gun Detection Classifier.”
J. Redmon and A. Farhadi, “YOLOv3: An Incremental Improvement,” Apr. 2018, [Online]. Available: http://arxiv.org/abs/1804.02767
R. Dugyala, M. Vishnu Vardhan Reddy, C. Tharun Reddy, and G. Vijendar, “Weapon Detection in Surveillance Videos Using YOLOV8 and PELSF-DCNN,” in E3S Web of Conferences, EDP Sciences, Jun. 2023.
K. Tekİndor and E. Ayan, “Advancements in Weapon Detection Systems: Leveraging Deep Learning for Enhanced Security,” in 2025 9th International Symposium on Innovative Approaches in Smart Technologies (ISAS), IEEE, Jun. 2025, pp. 1–4.
J. Hsueh and C.-T. Yang, “Using a High-Precision YOLO Surveillance System for Gun Detection to Prevent Mass Shootings,” AI, vol. 6, no. 9, p. 198, Aug. 2025.
L. Sumi and S. Dey, “A Deep Learning Approach to Gun Detection in Surveillance System using YOLOv9,” in 2024 Control Instrumentation System Conference (CISCON), IEEE, Aug. 2024, pp. 1–5.
Glenn Jocher; Ayush Chaurasia; Jing Qiu, “Ultralytics YOLOv8,” https://github.com/ultralytics/ultralytic. Accessed: Feb. 16, 2026. [Online]. Available: https://github.com/ultralytics/ultralytic
A. Wang et al., “YOLOv10: Real-Time End-to-End Object Detection,” Oct. 2024, [Online]. Available: http://arxiv.org/abs/2405.14458
R. Khanam and M. Hussain, “YOLOv11: An Overview of the Key Architectural Enhancements,” Oct. 2024, [Online]. Available: http://arxiv.org/abs/2410.17725
A. Q. Aloraibi, A. N. Hasoon, and M. S. Yassen, “YOLOv10: Toward a Promising Improvement of Gun Detection Based on a Proposed Image Enhancement Technique,” in 2025 3rd International Conference on Business Analytics for Technology and Security (ICBATS), IEEE, May 2025, pp. 1–8. doi: 10.1109/ICBATS66542.2025.11258182.
C.-Y. Wang, I.-H. Yeh, and H.-Y. M. Liao, “You Only Learn One Representation: Unified Network for Multiple Tasks,” May 2021, [Online]. Available: http://arxiv.org/abs/2105.04206
Z. Ge, S. Liu, F. Wang, Z. Li, and J. Sun, “YOLOX: Exceeding YOLO Series in 2021,” Aug. 2021, [Online]. Available: http://arxiv.org/abs/2107.08430
C.-Y. Wang, I.-H. Yeh, and H.-Y. M. Liao, “YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information,” Feb. 2024, [Online]. Available: http://arxiv.org/abs/2402.13616
M. Mao, A. Lee, and M. Hong, “Efficient Fabric Classification and Object Detection Using YOLOv10,” Electronics (Switzerland), vol. 13, no. 19, Oct. 2024.
M. A. R. Alif and M. Hussain, “YOLOv1 to YOLOv10: A comprehensive review of YOLO variants and their application in the agricultural domain,” Jun. 2024, [Online]. Available: http://arxiv.org/abs/2406.10139
S Nikhileswara Rao, “YOLOv11 Architecture Explained: Next-Level Object Detection with Enhanced Speed and Accuracy.” Accessed: Aug. 05, 2025. [Online]. Available: https://medium.com/@nikhil-rao-20/yolov11-explained-next-level-object-detection-with-enhanced-speed-and-accuracy-2dbe2d376f71
H. Sun, D. Lu, X. Li, J. Tan, J. Zhao, and D. Hou, “Research on multi-apparent defects detection of concrete bridges based on YOLOR,” Structures, vol. 65, Jul. 2024.
“Monash Guns Dataset.” Accessed: Jul. 17, 2025. [Online]. Available:https://github.com/MarcusLimJunYi/Monash-Guns-Dataset
“Different Weapon Types Datase.” Accessed: Jul. 17, 2025. [Online]. Available: https://github.com/vkaya24100/Different-Weapon-Types-datasets
“DeepCam GitHub - Gun Detection Datasets.” Accessed: Jul. 17, 2025. [Online]. Available: https://github.com/deepcam-cn/gun-detection-datasets?tab=readme-ov-file
“DeepKnowledge - US Real-time Gun Detection in CCTV.” Accessed: Jul. 17, 2025. [Online]. Available: https://deepknowledge-us.github.io/US-Real-time-gun-detection-in-CCTV-An-open-problem-dataset/
“HeeebsInc - Weapon Detection.” Accessed: Jul. 17, 2025. [Online]. Available: https://github.com/HeeebsInc/WeaponDetection
“OD Weapon Detection.” Accessed: Jul. 17, 2025. [Online]. Available: https://github.com/ari-dasci/OD-WeaponDetection
“DASCI Open Data - Weapon Detection.” Accessed: Jul. 17, 2025. [Online]. Available: https://dasci.es/transferencia/open-data/24705/
“TUVDC Dataset.” Accessed: Jul. 17, 2025. [Online]. Available: https://www.mkbhowmik.in/tuvdCsa.aspx
“Erdinç Weapon Detection Dataset.” Accessed: Jul. 17, 2025. [Online]. Available: https://github.com/slny08/Erdinc-Weapon-Detection-Dataset
“Google Colab,” https://en.wikipedia.org/wiki/Google_Colab. Accessed: Sep. 12, 2025. [Online]. Available: https://en.wikipedia.org/wiki/Google_Colab

Details

Primary Language

English

Subjects

Image Processing

Journal Section

Research Article

Authors

Selinay Erdinç ^*
0009-0002-5061-429X
Türkiye

Mehmet Dikmen
0000-0002-0584-5577
Türkiye

Publication Date

June 30, 2026

Submission Date

August 28, 2025

Acceptance Date

April 9, 2026

Published in Issue

Year 2026 Volume: 68 Number: 1

DOI

https://doi.org/10.33769/aupse.1772978

IZ

https://izlik.org/JA82GW24SX

Cite

RIS / Bibtex

APA

Erdinç, S., & Dikmen, M. (2026). Comparative Evaluation of Yolo-Based Models for Multi-Class Weapon Detection. Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering, 68(1), 38-56. https://doi.org/10.33769/aupse.1772978

AMA

1.Erdinç S, Dikmen M. Comparative Evaluation of Yolo-Based Models for Multi-Class Weapon Detection. Commun.Fac.Sci.Univ.Ank.Series A2-A3: Phys.Sci. and Eng. 2026;68(1):38-56. doi:10.33769/aupse.1772978

Chicago

Erdinç, Selinay, and Mehmet Dikmen. 2026. “Comparative Evaluation of Yolo-Based Models for Multi-Class Weapon Detection”. Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering 68 (1): 38-56. https://doi.org/10.33769/aupse.1772978.

EndNote

Erdinç S, Dikmen M (June 1, 2026) Comparative Evaluation of Yolo-Based Models for Multi-Class Weapon Detection. Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering 68 1 38–56.

IEEE

[1]S. Erdinç and M. Dikmen, “Comparative Evaluation of Yolo-Based Models for Multi-Class Weapon Detection”, Commun.Fac.Sci.Univ.Ank.Series A2-A3: Phys.Sci. and Eng., vol. 68, no. 1, pp. 38–56, June 2026, doi: 10.33769/aupse.1772978.

ISNAD

Erdinç, Selinay - Dikmen, Mehmet. “Comparative Evaluation of Yolo-Based Models for Multi-Class Weapon Detection”. Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering 68/1 (June 1, 2026): 38-56. https://doi.org/10.33769/aupse.1772978.

JAMA

1.Erdinç S, Dikmen M. Comparative Evaluation of Yolo-Based Models for Multi-Class Weapon Detection. Commun.Fac.Sci.Univ.Ank.Series A2-A3: Phys.Sci. and Eng. 2026;68:38–56.

MLA

Erdinç, Selinay, and Mehmet Dikmen. “Comparative Evaluation of Yolo-Based Models for Multi-Class Weapon Detection”. Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering, vol. 68, no. 1, June 2026, pp. 38-56, doi:10.33769/aupse.1772978.

Vancouver

1.Selinay Erdinç, Mehmet Dikmen. Comparative Evaluation of Yolo-Based Models for Multi-Class Weapon Detection. Commun.Fac.Sci.Univ.Ank.Series A2-A3: Phys.Sci. and Eng. 2026 Jun. 1;68(1):38-56. doi:10.33769/aupse.1772978