Self-Checkout Vehicle Vision for Automatic Item Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The process of purchasing items in a shopping environment is cumbersome and time-consuming due to the need to manually scan barcodes and weigh produce, leading to long checkout lines and increased complexity.
Innovation Solution
A self-checkout vehicle system equipped with cameras and weight sensors that automatically identify and calculate the price of merchandise using computer vision and OCR techniques, allowing shoppers to place items in a cart without separate scanning or weighing steps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual barcode scanning and weighing processes are used, then item identification and pricing can be achieved, but the shopping process becomes time-consuming and complex
Solution Approach 1:
The system enables automatic self-service item identification through computer vision. Cameras mounted on the shopping cart automatically capture images of items, and the processor identifies them without customer intervention. This eliminates the need for customers to manually scan barcodes or weigh produce, directly improving shopping speed while reducing process complexity.
Solution Approach 2:
The patent replaces mechanical barcode scanning devices and physical weighing scales with an optical-based computer vision system. Cameras capture images of items, and image processing algorithms automatically identify products and determine their weights by comparing images with reference databases, eliminating the need for separate mechanical scanning and weighing steps.
2Measurement precision
If separate scanning and weighing locations are used, then accurate item identification and weight measurement can be achieved, but the shopping experience becomes cumbersome
Solution Approach 1:
The system merges the functions of item identification and weight measurement into a single integrated process. The camera captures an image of the item in the shopping cart, and the processor simultaneously performs both identification (by recognizing the item in the image) and weight determination (by comparing the image with reference images of the same item from different angles), eliminating the need for separate scanning and weighing locations.
Solution Approach 2:
The camera system serves multiple functions: it identifies items by capturing their visual appearance, determines weights by comparing images with reference databases, and can recognize items from various angles. This multi-functional approach maintains measurement precision while greatly improving shopping convenience by eliminating the need for customers to move items between different stations.
3Measurement precision
If multiple images from different angles are used, then item identification accuracy is improved, but image processing complexity increases
Solution Approach 1:
The system performs preliminary actions by capturing multiple images of items from different angles and storing them in a reference database before the actual shopping transaction. During checkout, the processor compares the captured image with these pre-stored reference images to rapidly identify the item and determine its weight, improving accuracy without requiring complex real-time processing of multiple angles.
Data Source
AI summary
Self-checkout vehicle systems and methods comprising a self-checkout vehicle having a camera(s), a weight sensor(s), and a processor configured to: (i) identify via computer vision a merchandise item selected by a shopper based on an identifier affixed to the selected item, and (ii) calculate a price of the merchandise item based on the identification and weight of the selected item. Computer vision systems and methods for identifying merchandise selected by a shopper comprising a processor configured to: (i) identify an identifier affixed to the selected merchandise and an item category of the selected merchandise, and (ii) compare the identifier and item category identified in each respective image to determine the most likely identification of the merchandise.