Back to cases

Next case

ML model and data processing pipeline for manufacturing

Project for image analysis using ML to detect harmful emissions in manufacturing

Project definition

  • Location

    North America

  • Client

    Furniture factory

  • Industry

    Manufacturing and energy

  • Project type

    ML model

  • Service list

    ML Engineering / Computer Vision

  • Problem

    The main task of this project was to develop an ML model capable of detecting and annotating smoke coming from factory chimneys in images. In addition to the model itself, a data pipeline needed to be implemented to process a large number of surveillance camera images in real-time for smoke detection. The model was trained using manually annotated data with images of smoke coming from chimneys in various weather conditions

  • Solution

    The model and data pipeline were successfully implemented at various client factories in North America. The solution enabled real-time monitoring of factory conditions, alerting to unforeseen situations related to the emission of harmful substances into the air, as well as detecting emergency situations. With a model accuracy of 81%, the system reduced the number of incorrect decisions made by personnel and allowed the implementation of an external automated system for starting and stopping production based on the situation assessment

  • Python
  • Azure
  • Apache
  • OpenCV
  • numpy PyTorch
💡 Have same request?

We will create an ML model to solve your business challenges

Project highlights

Highlights of the developed ML model

  • 01

    Data processing from 150 cameras

    Developed a data pipeline capable of processing a large number of images from 150 cameras in real-time

  • 02

    81%

    The accuracy of the ML model recognition is 81%

Technologies
  • Python

    Python

  • Azure

    Azure

  • Apache

    Apache

  • OpenCV

    OpenCV

  • numpy PyTorch

    numpy PyTorch

Our workflow

Development Process

In FTECH-IT we have a cohesive team of professionals across various IT fields, enabling us to handle projects end-to-end without needing external specialists. No matter how complex the project is, all you need to provide is the idea — FTECH-IT will take care of everything else

01

Contact us

At first, we will try to understand the clients needs and propose proper solution

02

Requirements Gathering and Business Analysis

Our business analysts will gather all the details of the upcoming project and create a scope of tasks for the technical team

03

Budget Estimation and Coordination

The project is structured into a comprehensive set of tasks and subtasks, each of them is estimated in terms of hours with fixed pricing depending on the specialist performing the work. In FTECH-IT we ensure that our final budget estimates are both clear and transparent. We provide a detailed breakdown of how each dollar of your budget will be allocated.

04

Development

Whether it's a web or mobile application, FTECH-IT will always recommend the optimal tech stack for your idea or professionally implement your technical vision of the project

05

Testing

Strong team of AQA and QA professionals will ensure the stability and reliability of your application

06

Production Deployment

Our DevOps specialists will deploy your project on the server and help you choose the optimal hardware configuration based on your load

07

Project Support

If needed we are ready to provide long-term support for your solution. Also we offer a warranty period during which any discovered issues or bugs will be fixed completely free of charge

ML model and data processing pipeline for manufacturing

Project for image analysis using ML to detect harmful emissions in manufacturing

Contact us

Our team is dedicated to providing excellent customer service and ensuring your experience with us is a positive one. We look forward to hearing from you soon!

Next the best matching case

ML model for detecting contamination

Machine learning model for detecting contamination levels in tanks at manufacturing facilities

Python
Azure
Apache
OpenCV
numpy PyTorch