Analysis of convolutional neural networks for the recognition of violation of labor safety rules in the workplace.

Keywords: machine learning, convolutional neural network, occupational Safety and Health, data markup, labelImg, Python.

Abstract

Labor protection is a series of measures and tools aimed at preserving human health and performance. In various industries, employees are exposed to various negative factors on their health, for example, wearing a helmet can save an employee from the destruction of the skull bones, a concussion, all these injuries are classified as severe with all the ensuing consequences. The work is devoted to finding the best model of a convolutional neural network, which will have the best performance in determining the objects on which the model has been trained and is optimal for using the software. The data was marked using the labelImg program, all other stages of training and testing were carried out in the Python environment. The dataset includes several labeled classes, namely: a person with and without a helmet, a person with dielectric gloves and without gloves, a person with and without a cigarette, a person in special work shoes and without them, a person in work clothes and in normal clothes..

References

Di Benedetto, Marco & Carrara, Fabio & Meloni, Enrico & Amato, Giuseppe & Falchi, Fabrizio & Gennaro, Claudio. (2021). Learning accurate personal protective equipment detection from virtual worlds. Multimedia Tools and Applications. 80. 1-13. 10.1007/s11042-020-09597-9.

Souto Maior, Caio & Santana, João & Nascimento, Lucas & Macedo, July & Moura, Marcio & Isis, D.L. & Droguett, Enrique. (2018). Personal protective equipment detection in industrial facilities using camera video streaming. 10.1201/9781351174664-359.

Wang, Zijian & Wu, Yimin & Yang, Lichao & Thirunavukarasu, Arjun & Evison, Colin & Zhao, Yifan. (2021). Fast Personal Protective Equipment Detection for Real Construction Sites Using Deep Learning Approaches. Sensors. 21. 3478. 10.3390/s21103478.

Racheed, Dora & Muin, Rahmatullah & Jaylan, Ahmed. (2020). Object detection and object classification using machine learning Algorithms. International Journal of Information Technology and Applied Sciences (IJITAS). 2. 21-29. 10.52502/ijitas.v2i3.12.

Cooley, Christopher & Coleman, Sonya & Gardiner, B. & Scotney, Bryan. (2017). Saliency Detection and Object Classification.

Morabia, Keval & Arora, Jatin & Vijaykumar, Tara. (2020). Attention-based Joint Detection of Object and Semantic Part.

Shah, Syed. (2013). Automatic object detection using objectness measure.

Chao, Yu-Wei & Liu, Yunfan & Liu, Michael & Zeng, Huayi & Deng, Jia. (2017). Learning to Detect Human-Object Interactions.

Anshul Pundhir, Deepak Verma, Puneet Kumar, & Balasubramanian Raman. (2021). Region extraction based approach for cigarette usage classification using deep learning.

Zhibo Fan, Yuchen Ma, Zeming Li, & Jian Sun. (2021). Generalized Few-Shot Object Detection without Forgetting.

Alexey Bochkovskiy, Chien-Yao Wang, & Hong-Yuan Mark Liao. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection.

He, K., Zhang, X., Ren, S., & Sun, J. (2014). Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. Lecture Notes in Computer Science, 346–361.

Abstract views: 0
PDF Downloads: 0
Published
2021-11-02
How to Cite
Pronina , O., & Yaremko , O. (2021). Analysis of convolutional neural networks for the recognition of violation of labor safety rules in the workplace. COMPUTER-INTEGRATED TECHNOLOGIES: EDUCATION, SCIENCE, PRODUCTION, (44), 134-140. https://doi.org/10.36910/6775-2524-0560-2021-44-21
Section
Computer science and computer engineering