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.

March 25, 2026 - 7 minutes to read

How AI-Powered OCR is Revolutionizing Reefer Yard Management

Busy container terminal at 6 AM. Trucks queuing at the gate, vessels berthing, yard equipment moving in every direction, and somewhere in the middle of all that organized chaos, a gate clerk squinting at a container number that’s half-obscured by road grime, trying to type it correctly into a system that will not forgive a […]

Read More

Ruchir Kakkad

CEO & Co-founder

March 24, 2026 - 6 minutes to read

The Future of Cold Chain Logistics Automating Reefer Temperature Monitoring

There’s a strawberry sitting in a warehouse in a port somewhere in Europe right now. It was picked three days ago. And if someone doesn’t know exactly what temperature it’s been kept at for the last 72 hours, that strawberry, and about 40,000 others just like it, might be quietly rotting. Nobody talks about that […]

Read More

Ruchir Kakkad

CEO & Co-founder

March 6, 2026 - 5 minutes to read

The Real Cost of Blind Spots in Supply Chains (and How Visual Recordkeeping solves them)

At midnight, a high value shipment enters a regional logistics hub. By morning, the factory waited for those parts to halt production. The system shows the shipment as “received.” The yard team insists it was unloaded. The transporter says it left in perfect condition. No one is lying. No one can prove anything either. This […]

Read More

Ruchir Kakkad

CEO & Co-founder

Whatsapp Img