Smart Shopping Basket with YOLOv11 + BoT-SORT
🛒💡 Imagine walking into a store, filling your basket, and watching your budget update in real time — no checkout scanners, no manual tallying.
That’s exactly what I set out to simulate with my latest Computer Vision project:
🚀 Smart Shopping Basket with YOLOv11 + BoT-SORT
🔍 How it works:
I trained a YOLOv11 instance segmentation model to detect grocery items directly inside a basket.
Integrated BoT-SORT, a state-of-the-art multi-object tracker, to give every detected item a unique ID and keep track of it across frames (no duplicates).
Connected it to a price dictionary stored in JSON — whenever a new item is detected, its price is automatically subtracted from a variable called budget.
The system overlays segmentation masks, bounding boxes, IDs, item names, and the live remaining budget 💰 on the video stream in real time.
🛠️ Tech stack I used:
Ultralytics (YOLOv11) → instance segmentation
BoT-SORT → robust multi-object tracking
OpenCV → visualization and real-time overlays
Python + JSON → budget logic and item pricing
✨ Why this matters:
This project shows how AI can transform retail and shopping experiences:
Faster, frictionless checkout (no barcode scanning).
Real-time budget management for shoppers.
Potential for loss prevention and inventory tracking for retailers.
This is just a prototype, but it’s easy to see the real-world applications in smart retail, autonomous checkout systems, and AI-driven shopping assistants.
🔮 I’m excited to explore how projects like this can bridge the gap between AI research and everyday convenience.
👉 What do you think? Could this kind of system replace traditional checkouts in the future?