TY - GEN
T1 - Development of a Personal Protective Equipment Detection Algorithm Using Computer Vision with Python in State School Construction Sites
AU - León, Ryan
AU - Alvarez, Paolo
AU - Cavero, Ana
AU - Espinoza, Valeria
AU - Quiroz, Fabricio
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
PY - 2024
Y1 - 2024
N2 - The development of this project emerged as a response to the issue of inadequate use of personal protective equipment in Peru, in line with the country’s Law 29783. The primary aim was to create an algorithm for the detection of personal protective equipment through computer vision using Python, specifically on public school construction sites. The chosen algorithm was MASK-RCNN, executed on a Lenovo IdeaPad 5 laptop connected to the rear camera of a Xiaomi 11T smartphone using the DroidCam application to capture images of workers wearing helmets, vests, and closed-toe shoes. The overall accuracy of the algorithm reached 97.22%, calculated by comparing true positive values to the total of 108 values sampled in the confusion matrix, with improvement observed through further training, which involved using images with varying lighting conditions, quality, colors, etc. In summary, the algorithm demonstrated its ability to correctly detect the proper use of the studied personal protective equipment (helmet, vest, and closed-toe shoes).
AB - The development of this project emerged as a response to the issue of inadequate use of personal protective equipment in Peru, in line with the country’s Law 29783. The primary aim was to create an algorithm for the detection of personal protective equipment through computer vision using Python, specifically on public school construction sites. The chosen algorithm was MASK-RCNN, executed on a Lenovo IdeaPad 5 laptop connected to the rear camera of a Xiaomi 11T smartphone using the DroidCam application to capture images of workers wearing helmets, vests, and closed-toe shoes. The overall accuracy of the algorithm reached 97.22%, calculated by comparing true positive values to the total of 108 values sampled in the confusion matrix, with improvement observed through further training, which involved using images with varying lighting conditions, quality, colors, etc. In summary, the algorithm demonstrated its ability to correctly detect the proper use of the studied personal protective equipment (helmet, vest, and closed-toe shoes).
KW - algorithm
KW - Computer vision
KW - Python
UR - https://www.scopus.com/pages/publications/85202643252
U2 - 10.1007/978-3-031-66961-3_4
DO - 10.1007/978-3-031-66961-3_4
M3 - Conference contribution
AN - SCOPUS:85202643252
SN - 9783031669606
T3 - Smart Innovation, Systems and Technologies
SP - 39
EP - 50
BT - Proceedings of the 9th Brazilian Technology Symposium (BTSym’23) - Emerging Trends and Challenges in Technology
A2 - Iano, Yuzo
A2 - Arthur, Rangel
A2 - Saotome, Osamu
A2 - Kemper Vásquez, Guillermo Leopoldo
A2 - de Moraes Gomes Rosa, Maria Thereza
A2 - Gomes de Oliveira, Gabriel
T2 - 9th Brazilian Technology Symposium on Emerging Trends and Challenges in Technology, BTSym 2023
Y2 - 24 October 2023 through 26 October 2023
ER -