Skip to content

Latest commit

 

History

History
37 lines (30 loc) · 2.15 KB

README.md

File metadata and controls

37 lines (30 loc) · 2.15 KB

ConveyorVision-Bag-Counter

📄 Abstract

ConveyorVision is an innovative real-time system designed to automate the counting and tracking of cement bags on conveyor belts. Utilizing cutting-edge deep learning techniques like YOLOv8 for object detection and Byte tracker for precise tracking, ConveyorVision accurately monitors cement bags as they traverse the conveyor belt. Its seamless integration, reliable counting at the referee line, and robust performance in complex environments make it a valuable tool for optimizing industrial processes and enhancing productivity.

🏁 Dependencies

  1. NVIDIA Driver (Official Download Link)
  2. CUDA Toolkit (Official Link)
  3. Miniconda (Official Link)
  4. PyTorch (Official Link)
  5. Ultralytics YOLOv8 (Official Link)
  6. ByteTracker (Official Link)
  7. Supervision (Official Link)
  8. Onemetric (Official Link)

⚙️ Install

  1. Create conda env.
  2. Install dependencies into env.
  3. Annotate your datasets of cement bags. A good online data annotation tool is Roboflow or VGG Image Annotator. A data.yaml file must get created along with train, valid and test folders containing the images and labels.
  4. Follow Official Link to train network and generate yolo8.pt file with your network architecture of choice, along with your dataset.

🤖 To Use

  1. Update the video file and .pt file paths in counter.py in the main() function.
  2. Run python counter.py inside your conda env.

📊 Result

📑 Report

A brief REPORT can be read to better understand the algorithm.

🪪 License

See the LICENSE file for details.