Detection of Helmet Use in Motorcycle Drivers Using Convolutional Neural Network

Jaime Mercado Reyna; Huizilopoztli Luna-Garcia; Carlos H. Espino-Salinas; José M. Celaya-Padilla; Hamurabi Gamboa-Rosales; Jorge I. Galván-Tejada; Carlos E. Galván-Tejada; Roberto Solís Robles; David Rondon; Klinge Orlando Villalba-Condori

doi:10.3390/app13105882

Detection of Helmet Use in Motorcycle Drivers Using Convolutional Neural Network

Jaime Mercado Reyna, Huizilopoztli Luna-Garcia, Carlos H. Espino-Salinas, José M. Celaya-Padilla, Hamurabi Gamboa-Rosales, Jorge I. Galván-Tejada, Carlos E. Galván-Tejada, Roberto Solís Robles, David Rondon, Klinge Orlando Villalba-Condori

Vocational School of Secondary Education

Research output: Contribution to journal › Article › peer-review

Abstract

The lack of helmet use in motorcyclists is one of the main risk factors with severe consequences in traffic accidents. Wearing a certified motorcycle helmet can reduce the risk of head injuries by 69% and fatalities by 42%. At present there are systems that detect the use of the helmet in a very precise way, however they are not robust enough to guarantee a safe journey, that is why is proposed an intelligent model for detecting the helmet in real time using training images of a camera mounted on the motorcycle, and convolutional neural networks that allow constant monitoring of the region of interest to identify the use of the helmet. As a result, a model was obtained capable of identifying when the helmet is used or not in an objective and constant manner while the user is making a journey, with a performance of 97.24%. Thus, it was possible to conclude that this new safety perspective provides a first approach to the generation of new preventive systems that help reduce accident rates in these means of transport. As future work, it is proposed to improve the model with different images that may violate the helmet detection.

Original language	English
Article number	5882
Journal	Applied Sciences (Switzerland)
Volume	13
Issue number	10
DOIs	https://doi.org/10.3390/app13105882
State	Published - May 2023

Keywords

InceptionV3
convolutional neural network
deep learning
helmet detection
motorcyclist safety

Access to Document

10.3390/app13105882

Cite this

Mercado Reyna, J., Luna-Garcia, H., Espino-Salinas, C. H., Celaya-Padilla, J. M., Gamboa-Rosales, H., Galván-Tejada, J. I., Galván-Tejada, C. E., Solís Robles, R., Rondon, D., & Villalba-Condori, K. O. (2023). Detection of Helmet Use in Motorcycle Drivers Using Convolutional Neural Network. Applied Sciences (Switzerland), 13(10), Article 5882. https://doi.org/10.3390/app13105882

@article{bbf27316ec5c497780fd744ccba1c74a,

title = "Detection of Helmet Use in Motorcycle Drivers Using Convolutional Neural Network",

abstract = "The lack of helmet use in motorcyclists is one of the main risk factors with severe consequences in traffic accidents. Wearing a certified motorcycle helmet can reduce the risk of head injuries by 69% and fatalities by 42%. At present there are systems that detect the use of the helmet in a very precise way, however they are not robust enough to guarantee a safe journey, that is why is proposed an intelligent model for detecting the helmet in real time using training images of a camera mounted on the motorcycle, and convolutional neural networks that allow constant monitoring of the region of interest to identify the use of the helmet. As a result, a model was obtained capable of identifying when the helmet is used or not in an objective and constant manner while the user is making a journey, with a performance of 97.24%. Thus, it was possible to conclude that this new safety perspective provides a first approach to the generation of new preventive systems that help reduce accident rates in these means of transport. As future work, it is proposed to improve the model with different images that may violate the helmet detection.",

keywords = "InceptionV3, convolutional neural network, deep learning, helmet detection, motorcyclist safety",

author = "{Mercado Reyna}, Jaime and Huizilopoztli Luna-Garcia and Espino-Salinas, {Carlos H.} and Celaya-Padilla, {Jos{\'e} M.} and Hamurabi Gamboa-Rosales and Galv{\'a}n-Tejada, {Jorge I.} and Galv{\'a}n-Tejada, {Carlos E.} and {Sol{\'i}s Robles}, Roberto and David Rondon and Villalba-Condori, {Klinge Orlando}",

note = "Publisher Copyright: {\textcopyright} 2023 by the authors.",

year = "2023",

month = may,

doi = "10.3390/app13105882",

language = "English",

volume = "13",

journal = "Applied Sciences (Switzerland)",

issn = "2076-3417",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "10",

}

TY - JOUR

T1 - Detection of Helmet Use in Motorcycle Drivers Using Convolutional Neural Network

AU - Mercado Reyna, Jaime

AU - Luna-Garcia, Huizilopoztli

AU - Espino-Salinas, Carlos H.

AU - Celaya-Padilla, José M.

AU - Gamboa-Rosales, Hamurabi

AU - Galván-Tejada, Jorge I.

AU - Galván-Tejada, Carlos E.

AU - Solís Robles, Roberto

AU - Rondon, David

AU - Villalba-Condori, Klinge Orlando

PY - 2023/5

Y1 - 2023/5

N2 - The lack of helmet use in motorcyclists is one of the main risk factors with severe consequences in traffic accidents. Wearing a certified motorcycle helmet can reduce the risk of head injuries by 69% and fatalities by 42%. At present there are systems that detect the use of the helmet in a very precise way, however they are not robust enough to guarantee a safe journey, that is why is proposed an intelligent model for detecting the helmet in real time using training images of a camera mounted on the motorcycle, and convolutional neural networks that allow constant monitoring of the region of interest to identify the use of the helmet. As a result, a model was obtained capable of identifying when the helmet is used or not in an objective and constant manner while the user is making a journey, with a performance of 97.24%. Thus, it was possible to conclude that this new safety perspective provides a first approach to the generation of new preventive systems that help reduce accident rates in these means of transport. As future work, it is proposed to improve the model with different images that may violate the helmet detection.

AB - The lack of helmet use in motorcyclists is one of the main risk factors with severe consequences in traffic accidents. Wearing a certified motorcycle helmet can reduce the risk of head injuries by 69% and fatalities by 42%. At present there are systems that detect the use of the helmet in a very precise way, however they are not robust enough to guarantee a safe journey, that is why is proposed an intelligent model for detecting the helmet in real time using training images of a camera mounted on the motorcycle, and convolutional neural networks that allow constant monitoring of the region of interest to identify the use of the helmet. As a result, a model was obtained capable of identifying when the helmet is used or not in an objective and constant manner while the user is making a journey, with a performance of 97.24%. Thus, it was possible to conclude that this new safety perspective provides a first approach to the generation of new preventive systems that help reduce accident rates in these means of transport. As future work, it is proposed to improve the model with different images that may violate the helmet detection.

KW - InceptionV3

KW - convolutional neural network

KW - deep learning

KW - helmet detection

KW - motorcyclist safety

UR - http://www.scopus.com/inward/record.url?scp=85160818850&partnerID=8YFLogxK

U2 - 10.3390/app13105882

DO - 10.3390/app13105882

M3 - Article

AN - SCOPUS:85160818850

SN - 2076-3417

VL - 13

JO - Applied Sciences (Switzerland)

JF - Applied Sciences (Switzerland)

IS - 10

M1 - 5882

ER -

Detection of Helmet Use in Motorcycle Drivers Using Convolutional Neural Network

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this