Steel Bar Counting

csdetb-icono

Customer

One of Japan’s leading steel manufacturing plants.

Project Details

  • Duration: 1 Month +

Technologies:

  • Deep Learning
  • OpenCV
  • Python
  • PyQt
  • Edge Computing devices
  • SQLlite
problem-img

Problem

  • The steel plant workers face challenges in accurately counting steel bars during production due to:
  • Low Lighting Conditions
  • Constantly Moving Steel Bars
  • Impossible to visualise the Entire Steel Bar due to its length.
  • Steel Rods can be of different Widths & Breadth.

 

solution-img

Solution

  • We have developed a Desktop Build that runs our detection Model.
  • It counts steel bars within the dynamically drawn region of interest (ROI) using a segmentation model.
  • Object bounding boxes are utilized to count the steel bars, and the real-time count is displayed on the screen.
  • The Model is trained under varying lighting conditions
  • Due to the limited Dataset, the new dataset was generally using Augmentation methods.

 

100%

Accuracy

Insights on innovation

Stay updated with the trending and most impactful tech insights. Check out the expert analyses, real-world applications, and forward-thinking ideas that shape the future of AI Computer Vision and innovation.