Search

Smoke Detection Based on YOLOv5 and MediaPipe

Author(s)

Yusong Wang, Rouyi Fan, Xiaofeng Li*

Affiliation(s)

School of Artificial Intelligence and Big Data, Henan University of Technology, Zhengzhou, Henan, China *Corresponding Author

Abstract

As awareness of smoking prohibition in public places increases, technology that automatically detects smoking behavior is particularly important. With the rapid development of deep learning and neural networks, the typical You Only Look Once version 5 (YOLOv5) algorithm can be used for prediction, the traditional algorithm performs well on the picture, but the detection on the video will have false detection, so the MediaPipe machine learning framework is introduced to improve the accuracy of video detection, and the relative distance calculation of the target’s hand, mouth, and the position of the cigarette detected by YOLOv5 can comprehensively judge whether the object smokes. Deploy an improved algorithm to call the camera or import the video for detection, and the items similar to cigarettes in the video can be eliminated, reducing the probability of false detection.

Keywords

Object Detection; Deep Learning; Machine Learning; MediaPipE; YOLOv5

References

[1] Liu Z D. Building a Smoke-Free Environment Together, Creating a Healthy Life Together. Population & Health, 2024, (09): 81-82. [2] Li L, Wang S L. Research on the Implementation of a Smoking Monitoring System Based on Digital Technology. Electronic Engineering & Product World, 2024, 31(10): 32-35. [3] Cheng C, Liu Q H, Chen Y T, et al. Analysis and Implementation of a Smoking Behavior Recognition and Detection System Based on YOLOv5. Computer Knowledge and Technology, 2024, 20(30): 17-20. [4] Jiang X, Hu H, Liu X, et al. A smoking behavior detection method based on the YOLOv5 network. Journal of Physics: Conference Series. IOP Publishing, 2022, 2232(1): 012001. [5] Maia F W, Lopes M A, David A S. Automatic sign language to text translation using MediaPipe and transformer architectures. Neurocomputing, 2025, 642: 130421. [6] Guo H, Sun C, Zhang J, et al. MMYFnet: Multi-Modality YOLO Fusion Network for Object Detection in Remote Sensing Images. Remote Sensing, 2024, 16(23): 4451. [7] Wang Z, Wu L, Li T, et al. A smoke detection model based on improved YOLOv5. Mathematics, 2022, 10(7): 1190. [8] Zheng Y P, Xu B Y, Wang Z Y. An Improved YOLOv5 Smoke Detection Model. Journal of Computer Engineering and Applications, 2023, 59(7). [9] Zhang J, Yin L, Gong X F, et al. Small Target Smoke Detection Algorithm Based on Improved YOLOv5. China Safety Science Journal, 2023, 33(11): 75. [10] Wang R B, Dou Q L, Zhang Q, et al. MediaPipe-Based Hand Gesture Recognition for Teleoperated Control of Excavators. Journal of Information Technology in Civil Engineering and Architecture, 2022, 14(4): 9-16. [11] Ni G X, Xu H, Wang C. Research on Hand Gesture Recognition Integrating Improved YOLOv5 and Mediapipe. Journal of Computer Engineering and Applications, 2024, 60(7). [12] Cao W, Lu P, Cao W. Multimodal Gesture Recognition with Spatio-Temporal Features Fusion Based on YOLOv5 and MediaPipe. International Journal of Pattern Recognition and Artificial Intelligence, 2024, 38(08). [13] Shi F, Zhou H, Ye C, et al. Faster detection method of driver smoking based on decomposed YOLOv5. Journal of Physics: Conference Series. IOP Publishing, 2021, 1993(1): 012035. [14] Paramita C, Supriyanto C, Putra K R. Comparative analysis of YOLOv5 and YOLOv8 cigarette detection in social media content. Scientific Journal of Informatics, 2024, 11(2): 341-352. [15] Cui Z W, Liu X F, Xia S N, et al. Research on Hand Gesture Recognition Based on Deep Learning. Journal of Sensor Technology and Application, 2024, 12: 570.