Multi-Signal Bulk Item Identification for In-Motion Retail Checkout
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional self-checkout and cashier-assisted checkout processes are cumbersome for consumers with large numbers of items, requiring serial item identification, which can be inefficient and inaccurate, especially when handling bulk items.
Innovation Solution
A hybrid checkout system combining computer vision with RFID sensors to capture multi-signal inputs from multiple angles and positions, enabling bulk item identification and recognition while items are in motion, using a conveyor belt with markings for item placement and multiple cameras with non-overlapping fields of view.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional self-checkout uses linear item identification process, then each item can be identified individually, but the process becomes cumbersome and inefficient for consumers with large numbers of items
Solution Approach 1:
The patent combines multiple sensing modalities (optical sensors for image capture, RFID sensors for wireless identification, weight sensors for detection) into a unified detection system. This merging allows simultaneous identification of multiple items through bulk scanning rather than individual processing, dramatically increasing transaction velocity while reducing operator burden.
Solution Approach 2:
The patent replaces manual mechanical item identification processes with automated sensor-based detection systems. Optical cameras capture images of items, RFID readers wirelessly identify items without physical contact, and weight sensors detect items on the conveyor belt. This substitution eliminates the need for consumers to manually scan or enter each item, transforming the linear process into a parallel bulk processing system.
2Measurement precision
If conventional checkout processes items serially one by one, then each item can be accurately identified, but the time required increases significantly for bulk items
Solution Approach 1:
The patent implements continuous detection as items move along the conveyor belt. Sensors operate continuously to detect, identify, and recognize items without interruption. The system maintains constant monitoring through optical cameras capturing images, RFID readers scanning wireless identifiers, and weight sensors detecting item presence, enabling parallel processing of multiple items simultaneously while preserving identification accuracy.
Solution Approach 2:
The patent transitions from one-dimensional serial processing to multi-dimensional parallel processing by incorporating multiple sensing modalities operating simultaneously. The system processes items through optical detection, RFID wireless identification, and weight detection dimensions concurrently, allowing bulk item identification in a single pass rather than sequential processing, thereby reducing identification time while maintaining precision.
3Measurement precision
If multiple sensors capture data from different vantage points, then item recognition accuracy improves, but device complexity increases
Solution Approach 1:
The patent employs a multi-functional sensing system where optical cameras, RFID readers, and weight sensors work together as complementary components. Each sensor type performs a specific function (visual identification, wireless data reading, weight detection) that contributes to overall item recognition accuracy. The system integrates these diverse sensing modalities into a unified checkout process, managing complexity through functional specialization rather than redundant systems.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system significantly improves transaction velocity and accuracy by transforming the linear item identification process into a bulk process, reducing operator burden and enhancing item recognition capabilities.
Implementation Method 1
capturing, by one or more cameras, image data including a plurality of images of a plurality of items as the plurality of items is conveyed along a moving surface
Implementation Method 2
the one or more sensors are RFID sensors, and the additional sensor data is RFID data received from a respective RFID tag affixed to each of one or more of the plurality of items
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A hybrid checkout system that enables in-motion, multi-signal, bulk item identification is disclosed. The hybrid checkout system includes a computer vision apparatus that includes a plurality of cameras fixed at different locations relative to a conveyor belt. The conveyor belt includes markings that assist a user with item placement. RFID sensors are provided with the hybrid checkout apparatus. The cameras capture multiple images of items placed on the belt as the items are in motion. Each camera captures multiple images of the items captured from different vantage points as the items are in motion. In addition, the RFID sensors gather RFID data from RFID tags affixed to the items, as the items are in motion. The image data and other sensor data is provided as a multi-signal input to a machine learning model that is trained to recognize items and output item identifiers for the items. Pricing information corresponding to the item identifiers received from the model is determined and the items and their respective prices are added to a transaction record.