Camera-Weight Sensing Storage Cabinet for Secure Self-Checkout
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing micro-markets and vending machines provide a poor user experience, are limited in product selection, require manual scanning or tagging, and lack real-time communication, making them unattractive and prone to theft and operational inefficiencies.
Innovation Solution
An automated micro-store equipment with built-in cameras and sensors, using machine learning computer vision and weight sensors to identify products and interactions, enabling self-checkout and allowing customers to select items manually, with a mobile application for authorization and payment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional vending machines are used, then security and automated operation are improved, but user experience and product accessibility deteriorate
Solution Approach 1:
The patent replaces mechanical product dispensing systems with optical sensing systems. Cameras and computer vision algorithms detect product interactions, replacing the mechanical take-and-pay system of traditional vending machines. This allows users to freely access products while the system automatically tracks and charges for items taken, resolving the contradiction between security and user experience.
Solution Approach 2:
The system implements self-service through automated product identification and charging. The computer vision system automatically detects when products are removed or returned, and the mobile application handles payment without human intervention. This eliminates the need for cash handling or manual scanning while maintaining secure automated operation.
2Productivity
If RFID technology is used, then automated product identification is improved, but operational complexity and product costs worsen
Solution Approach 1:
The patent replaces RFID tagging systems with passive optical sensing. Instead of requiring active RFID tags in each product, the system uses cameras to visually identify products based on their appearance, packaging, and position. This eliminates the need for complex RFID infrastructure while maintaining automated product identification capabilities.
Solution Approach 2:
The system creates visual copies (images) of products and their positions, then uses computer vision algorithms to identify and track them. This optical copying approach replaces the need for physical RFID tags, simplifying the system while maintaining automated identification functionality.
3Measurement precision
If barcode scanning is used, then product identification accuracy is improved, but device complexity and operational requirements worsen
Solution Approach 1:
The patent merges the product identification function into the existing camera system. The same cameras used for monitoring and security also perform product identification through computer vision, eliminating the need for separate barcode scanners. This integration reduces device complexity while maintaining identification accuracy.
Solution Approach 2:
The camera system serves multiple functions: security monitoring, product identification, and interaction detection. By making the camera system universal, the patent eliminates the need for dedicated barcode scanning equipment, reducing overall system complexity while maintaining accurate product identification.
4Ease of operation
If open shelves are used, then user experience is improved, but security and loss prevention deteriorate
Solution Approach 1:
The patent implements continuous feedback through camera monitoring of open shelves. The computer vision system real-time detects product removals and tracks them until payment is confirmed or the shopping session ends. This feedback loop maintains security while allowing the benefits of open shelf access, as the system automatically charges users for items taken.
Solution Approach 2:
The patent replaces physical security barriers (locked shelves, gates) with optical monitoring systems. Cameras and computer vision algorithms provide virtual surveillance that prevents theft through automated detection and charging, allowing open shelves to remain secure without physical constraints.
Data Source
AI summary
Disclosed is a storage cabinet. An embodiment has one or more shelves, one or more doors for enclosing the cabinet, and an electromagnetic lock for locking the door or doors. The shelves have one or more cameras, an opened- or closed-door state sensor, and a weight sensor arranged to measure weight of products placed on said shelves. An electronic data processor carries out a machine learning computer vision method for processing data received from cameras and sensors to identify products removed from said shelves. The processor detects when a cabinet door is in an open state, acquires image and weight data from the associated camera and weight sensor. When a weight change at a shelf is detected, processing of image data acquired including when the weight change occurred occurs, with said machine learning computer vision method.