Problem Statement

Checkout aisles in grocery stores are inefficient. There are better ways to process transactions that don’t involve waiting in long lines for a cashier.

Approach

In stores, every item is marked with a barcode that uniquely identifies it. These barcodes can be processed using computer vision techniques.

Our team will create an embedded system for shopping carts that will process orders in a passive manner, requiring no intervention from the shopper. As items are placed in the cart, a camera will “scan” the item and send data to the cloud to process the order.

Project Requirements

1. Recognize barcode as item is placed in cart
2. Detect when item is removed from cart
3. Display item list and current balance
4. Detect an unscanned item to prevent theft
5. Sustain power for a full business day

System Specifications

1. 18 hours of continuous operation
2. One item entered / removed per two-second interval
3. Barcode surface must be reasonably flat
4. Maximum system latency of four seconds