НЕФТЯНАЯ ПРОВИНЦИЯ

Abstract

​

The work is aimed at elaboration of mining algorithms for HSE (Health, safety and environmental protection) rules violations based on video content both at industrial facilities and in office premises.

The results are the following:

1. mining algorithms have been developed;

2. dataset for model training has been generated;

3. neural network type has been selected;

4. models have been trained;

5. accuracy of the algorithms has been estimated;

6. supplement testing has been performed using video footage from Taas-Yuryakh Neftegazodobycha.

Key words:

​

video content analysis, HSE, data science

References

​​

1. Vidy i prichiny neschastnyh sluchaev na proizvodstve [Types and causes of health and safety incidents]. [Electronic resource]. – URL: https://www.rsuh.ru (date of treatment: 27.09.2021).

2. Bengio Y., Lecun Y. Convolutional Networks for Images, Speech, and Time-Series [Electronic resource]. – URL: https://www.researchgate.net/ (date of treatment: 27.09.2021).

3. Girshick R., Donahue J., Darrell T., Malik J. Rich feature hierarchies for accurate object detection and semantic segmentation [Electronic resource]. – URL: https://arxiv.org/pdf/1311.2524.pdf (date of treatment: 27.09.2021).

4. Girshick R. Fast R-CNN [Electronic resource]. – URL: https://arxiv.org/pdf/1504.08083.pdf (date of treatment: 27.09.2021).

5. Redmon J., Divvala S., Girshick R., Farhadi A. You Only Look Once: Unified, Real-Time Object Detection [Electronic resource]. – URL: https://arxiv.org/pdf/1506.02640.pdf (date of treatment: 27.09.2021).

6. Liu W., Anguelov D., Erhan D., Szegedy C., Reed S., Cheng-Yang Fu, Berg A. SSD: Single Shot MultiBox Detector [Electronic resource]. – URL: https://arxiv.org/pdf/1512.02325.pdf (date of treatment: 27.09.2021).

7. Simonyan K., Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition [Electronic resource]. – URL: https://arxiv.org/pdf/1409.1556.pdf (date of treatment: 27.09.2021).

8.  Lin T., Maire M., Belongie S., Bourdev L., Girshick R., Hays J., Perona P., Ramanan D., Zitnick C., Dollár P. Microsoft COCO: Common Objects in Context [Electronic resource]. – URL: https://arxiv.org/pdf/1405.0312.pdf (date of treatment: 27.09.2021).

9. EVA [Electronic resource]. – URL: https://github.com/Ericsson/eva (date of treatment: 27.09.2021).

10. PyTorch: From researh to production [Electronic resource]. – URL: https://pytorch.org (date of treatment: 27.09.2021).

​

Authors

​

V.A. Grinchenko, LLC «Taas-Yuryakh Neftegazodobycha»

291, Baikal st., Irkutsk, 664050, Russian Federation

E-mail: grinchenkova@tyngd.rosneft.ru

 

N.A. Popova, Irkutsk National Research Technical University

83, Lermontov st., Irkutsk, 664074, Russian Federation

E-mail: russiacova95@mail.ru

 

P.I. Chermyanin, Tyumen Petroleum Research Center

79/1, Osipenko st., Tyumen, 625002, Russian Federation

E-mail: ichermyanin2@tnnc.rosneft.ru

 

M.B. Koshelev, Tyumen Petroleum Research Center

79/1, Osipenko st., Tyumen, 625002, Russian Federation

E-mail: mbkoshelev@tnnc.rosneft.ru

 

A.F. Khabibullin, Tyumen Petroleum Research Center

79/1, Osipenko st., Tyumen, 625002, Russian Federation

E-mail: afkhabibullin@tnnc.rosneft.ru

 

D.V. Polyakov, Tyumen Petroleum Research Center

79/1, Osipenko st., Tyumen, 625002, Russian Federation

E-mail: dvpolyakov3-tnk@tnnc.rosneft.ru

For citation:

​

V.A. Grinchenko, N.A. Popova, P.I. Chermyanin, M.B. Koshelev, A.F. Khabibullin, D.V. Polyakov Cifrovoj supervajzing [Digital supervising]. Neftyanaya Provintsiya, No. 4(28), Part 1, Special issue, 2021. pp. 246-259. DOI https://doi.org/10.25689/NP.2021.4.246-259 (in Russian)