Comparative Evaluation of YOLOv5 and YOLOv8 Models in Detecting Smoking Behavior

Muhammad Andaru Megaarta

doi:10.59934/jaiea.v4i3.1089

Authors

Muhammad Andaru Megaarta Politeknik Negeri Sriwijaya

DOI:

https://doi.org/10.59934/jaiea.v4i3.1089

Keywords:

Smoking Behavior Detection, YOLOv5, YOLOv8, Object Detection, Deep learning

Abstract

Smoking behavior in public spaces has become a serious concern in public health efforts, as it poses health risks not only to active smokers but also to passive smokers. This study presents a comparative evaluation of two state-of-the-art object detection models, YOLOv5 and YOLOv8, for the automatic detection of smoking behavior. The models were trained on a labeled image dataset containing cigarettes, faces, and smoking activities. Evaluation metrics used in this study include precision, recall, F1-score, and mean Average Precision (mAP). The experimental results show that both models achieved strong detection performance, with precision, recall, and F1-scores above 0.95. YOLOv5 obtained slightly higher precision (0.98064), recall (0.96388), and F1-score (0.97), while YOLOv8 achieved a marginally higher mAP (0.97782), indicating better generalization across varying IoU thresholds. YOLOv8 also showed improved classification performance in detecting faces (0.69) and smoking behavior (0.54), benefiting from its anchor-free architecture and advanced loss functions. These findings demonstrate that while both models are highly effective, YOLOv8 offers greater robustness and accuracy for real-time smoking detection in complex public environments, supporting efforts to minimize cigarette exposure and improve public health awareness.

Downloads

Download data is not yet available.

References

S. A. Putri, “Implementasi Algoritma YOLOv5 untuk Otomatisasi Iklan Layananan Publik tentang Larangan Merokok,” pp. 195–202, 2023.

A. M. Fathoni, E. Zuliarso, and U. S. Semarang, “IMPLEMENTATION OF YOLOv5 METHOD IN THE CIGARETTE DETECTION,” vol. 7, pp. 1449–1454, 2024.

J. Redmon and A. Farhadi, “YOLOv3: An Incremental Improvement,” 2018, [Online]. Available: http://arxiv.org/abs/1804.02767

A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” 2020, [Online]. Available: http://arxiv.org/abs/2004.10934

I. P. Sary, S. Andromeda, and E. U. Armin, “Performance Comparison of YOLOv5 and YOLOv8 Architectures in Human Detection using Aerial Images,” Ultim. Comput. J. Sist. Komput., vol. 15, no. 1, pp. 8–13, 2023, doi: 10.31937/sk.v15i1.3204.

C. Paramita, C. Supriyanto, and K. Rahmyanto Putra, “Comparative Analysis of YOLOv5 and YOLOv8 Cigarette Detection in Social Media Content,” Sci. J. Informatics, vol. 11, no. 2, pp. 341–352, 2024, doi: 10.15294/sji.v11i2.2808.

yeolduri, “smoking Dataset,” Mar. 2025, Roboflow. [Online]. Available: https://universe.roboflow.com/yeolduri/smoking-hvni4

C. Shorten and T. M. Khoshgoftaar, “A survey on Image Data Augmentation for Deep Learning,” J. Big Data, vol. 6, no. 1, 2019, doi: 10.1186/s40537-019-0197-0.

C. Y. Wang, H. Y. Mark Liao, Y. H. Wu, P. Y. Chen, J. W. Hsieh, and I. H. Yeh, “CSPNet: A new backbone that can enhance learning capability of CNN,” IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. Work., vol. 2020-June, no. June, pp. 1571–1580, 2020, doi: 10.1109/CVPRW50498.2020.00203.

J. Terven, D. M. Córdova-Esparza, and J. A. Romero-González, “A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS,” Mach. Learn. Knowl. Extr., vol. 5, no. 4, pp. 1680–1716, 2023, doi: 10.3390/make5040083.

X. Li, T. Lai, S. Wang, Q. Chen, C. Yang, and R. Chen, “Weighted feature pyramid networks for object detection,” Proc. - 2019 IEEE Intl Conf Parallel Distrib. Process. with Appl. Big Data Cloud Comput. Sustain. Comput. Commun. Soc. Comput. Networking, ISPA/BDCloud/SustainCom/SocialCom 2019, pp. 1500–1504, 2019, doi: 10.1109/ISPA-BDCloud-SustainCom-SocialCom48970.2019.00217.

S. Liu, L. Qi, H. Qin, J. Shi, and J. Jia, “Path Aggregation Network for Instance Segmentation,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 8759–8768, 2018, doi: 10.1109/CVPR.2018.00913.

Z. Guo, W. Zhang, Z. Liang, Y. Shi, and Q. Huang, “Multi-Scale Object Detection Using Feature Fusion Recalibration Network,” IEEE Access, vol. 8, pp. 51664–51673, 2020, doi: 10.1109/ACCESS.2020.2980737.

J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2016-Decem, pp. 779–788, 2016, doi: 10.1109/CVPR.2016.91.

K. Duan, S. Bai, L. Xie, H. Qi, Q. Huang, and Q. Tian, “CenterNet: Keypoint triplets for object detection,” Proc. IEEE Int. Conf. Comput. Vis., vol. 2019-October, pp. 6568–6577, 2019, doi: 10.1109/ICCV.2019.00667.

K. He, G. Gkioxari, P. Dollár, and R. Girshick, “Mask R-CNN,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 42, no. 2, pp. 386–397, 2020, doi: 10.1109/TPAMI.2018.2844175.

Z. Zheng, P. Wang, W. Liu, J. Li, R. Ye, and D. Ren, “Distance-IoU loss: Faster and better learning for bounding box regression,” AAAI 2020 - 34th AAAI Conf. Artif. Intell., no. February, pp. 12993–13000, 2020, doi: 10.1609/aaai.v34i07.6999.

M. M. Sebatubun and C. Haryawan, “Implementasi Algoritma Convolutional Neural Network untuk Klasifikasi Jenis Keris,” J. Teknol. Inf. dan Ilmu Komput., vol. 11, no. 3, pp. 595–602, 2024, doi: 10.25126/jtiik.937260.