Evaluation of oil workers' performance based on surveillance video | Научно-инновационный портал СФУ

Evaluation of oil workers' performance based on surveillance video

Тип публикации: доклад, тезисы доклада, статья из сборника материалов конференций

Конференция: 2019 International Multi-Conference on Engineering, Computer and Information Sciences, SIBIRCON 2019

Год издания: 2019

Идентификатор DOI: 10.1109/SIBIRCON48586.2019.8958352

Ключевые слова: ArUco, computer vision, convolutional neural networks, CTPN, Faster R-CNN, fiducial markers, OCR, RUNETag, single-shot detectors, surveillance, Tesseract, uniform numbers, workers' performance

Аннотация: We present our research on the applicability of computer vision techniques for extracting various oil workers' performance metrics. This paper focuses on learning two metrics associated with the workers' location. The first metric \boldsymbol{e}-{1} is the percent of frames in which only some part of the crew is present. If its value is bigger than some threshold value, the crew's performance is declared inefficient. We propose to perform human detection in each video frame and count people present in order to calculate \boldsymbol{e}-{1}. The Faster R-CNN and single-shot detectors with several types of feature extractors were tested on a specially collected dataset. By finetuning the most accurate of them we've achieved 0.99 precision and 0.91 recall. The second metric \boldsymbol{e}-{2} considers workers' distance from an automated gas control system, which is the main subject of maintenance. We propose using some markers on the uniform for worker recognition and estimation of his/her position relative to an automated gas control system. We've tested the ArUco and the RUNETag markers on synthetic data and proved that they cannot be applied to our problem. We've also carried out some preliminary research on uniform numbers detection, as they can be also considered as markers. The Connectionist Text Proposal Network (CTPN) used for text detection achieved an accuracy of 0.76. Text recognition performed by Tesseract OCR failed with 0.05 recall. However, we plan to collect a dataset for number detection and recognition in the future and test more approaches. © 2019 IEEE.

Ссылки на полный текст

Издание

Журнал: SIBIRCON 2019 - International Multi-Conference on Engineering, Computer and Information Sciences, Proceedings

Номера страниц: 432-435

Издатель: Institute of Electrical and Electronics Engineers Inc.8958352

Авторы

  • Lebedeva E. (Novosibirsk State University, Faculty of Information Technologies, Novosibirsk, Russian Federation)
  • Zubkov A. (ITMS.Pro, General Department, Novosibirsk, Russian Federation)
  • Bondarenko D. (ITMS.Pro, General Department, Novosibirsk, Russian Federation)
  • Rymarenko K. (SIANT RnD, SIANT, Novosibirsk, Russian Federation)
  • Nukhaev M. (School of Petroleum and Natural Gas Engineering, Siberian Federal University, Krasnoyarsk, Russian Federation)
  • Grishchenko S. (SIANT RnD, SIANT, Novosibirsk, Russian Federation)

Вхождение в базы данных

Информация о публикациях загружается с сайта службы поддержки публикационной активности СФУ. Сообщите, если заметили неточности.

Вы можете отметить интересные фрагменты текста, которые будут доступны по уникальной ссылке в адресной строке браузера.