Мы используем файлы cookie для быстрой и удобной работы сайта. Выберите, какие файлы cookie вы разрешаете нам использовать. Подробнее в Политике конфиденциальности.
Обсудить проект
Отправьте запрос, и наши специалисты свяжутся с вами в течение 1 часа
Нажимая кнопку «Отправить», Вы даете однозначное согласие на обработку своих персональных данных в объеме и с целями, определенными Политикой в отношении обработки персональных данных.
Detection of safety violations
computer vision and image analysis
oil and gas industry
15
30
the average time to detect a violation has been reduced
by
by
the time for generating reports has been reduced
times
times
Customer
A major operator of main oil pipelines
CHALLENGES/FEATURES
various, including non-standard, cases of determining violations
variety of operating conditions for special equipment
very low quality of video data
processing large amounts of data for training models
Development of a system for the automated detection of safety violations based on the analysis of video data obtained from video recorders installed on special equipment
Task
solution
Technical solution
1. Conducted an analysis and designed the client-server architecture of the system
2. Created an automatic pipeline for preparing video data for training models
3. Trained neural network models for various violation detection tasks, such as:
lack of personal protective equipment, workers being in a hazardous area
4. We developed the front-end, the client part of the application, in React, with access authorization and reporting on the processing results.
5. Implemented the backend, the server side of the solution based on Python
6. Conducted an assessment of the system's performance using test data
(90% - average accuracy for identifying several classes of violations)
7. Ensured system deployment using Docker Compose
2. Created an automatic pipeline for preparing video data for training models
3. Trained neural network models for various violation detection tasks, such as:
lack of personal protective equipment, workers being in a hazardous area
4. We developed the front-end, the client part of the application, in React, with access authorization and reporting on the processing results.
5. Implemented the backend, the server side of the solution based on Python
6. Conducted an assessment of the system's performance using test data
(90% - average accuracy for identifying several classes of violations)
7. Ensured system deployment using Docker Compose
Result
Business values
Automate processes and reduce labor costs
The system significantly reduces the time and resources needed to analyze video data, allowing occupational safety personnel to focus on more important tasks. The average time to detect a violation has been reduced by 15 times.
identification of factors threatening the safety and reliability of operation of main oil pipelines, which helps reduce the risk of accidents and incidents
Monitoring and reducing reporting time by 30 times
The ability to generate reports and notifications about detected violations allows you to quickly respond to changes and take measures to eliminate problems
Innovative technologies
The use of artificial intelligence to detect violations demonstrates the company's commitment to implementing modern technologies and increasing competitiveness in the market.
improving the quality and speed of control and supervisory operations, which contributes to increasing the overall efficiency of the organization
Improving security
Effectiveness of control and supervisory operations
By clicking the "Submit" button, you expressly consent to the processing of your personal data to the extent and for the purposes defined in the Personal Data Processing Policy.
Development of software
and Big Data solutions
and Big Data solutions
Send a request and our specialists will contact you within 1 hour.
Choose a convenient method of communication
You can attach three files up to 3 MB each. Formats: doc, docx, pdf, ppt, pptx
Сообщение об успешной отправке!