Item Identification Using Similarity Thresholds for Real-Time Tracking

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Identifying and tracking multiple items in real-time is computationally intensive and time-consuming, making it incompatible with real-time applications, and maintaining accuracy in item tracking is challenging due to potential shifts in camera, 3D sensor, and platform positions.

Innovation Solution

A system using cameras and 3D sensors to identify and track items on a platform, with techniques for recalibrating homographies and reducing search spaces based on container categories, transaction histories, and item heights to improve accuracy and efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If item identification compares features against every item in a database containing thousands of items, then identification accuracy is maintained, but processing time increases significantly making it incompatible with real-time applications

Engineering Contradiction:

Improveitem identification accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent segments the item identification process into multiple stages: first capturing images and extracting features, then comparing features only against items in the same category rather than the entire database. This segmentation reduces the comparison scope from thousands of items to a smaller subset, maintaining accuracy while reducing processing time for real-time applications

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary actions by pre-organizing items into categories and pre-extracting features before the actual identification process. This preliminary organization allows the system to quickly narrow down candidates within categories without comparing against every item in the database, thereby reducing processing time while maintaining identification accuracy

Inventive Principle:

Principle #10Preliminary action

2Productivity

If the system processes images to identify multiple items simultaneously, then throughput increases, but computational complexity increases making the process intractable

Engineering Contradiction:

Improveitem identification throughputVSAvoidcomputational complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent divides the computational task by segmenting the database into categories and processing items within each category separately. This segmentation allows parallel processing of different categories while reducing the computational burden within each segment, enabling simultaneous identification of multiple items without making the overall process intractable

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent applies partial action by comparing features only against relevant items within the same category rather than performing exhaustive comparisons against the entire database. This partial comparison approach maintains sufficient identification accuracy while significantly reducing computational complexity for processing multiple items simultaneously

Inventive Principle:

Principle #16Partial or excessive action

3Measurement precision

If user manual scanning or identification is required, then identification accuracy is ensured, but system throughput decreases creating a bottleneck

Engineering Contradiction:

Improveitem identification accuracyVSAvoidsystem throughput

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent implements self-service by enabling the system to automatically identify items through image capture and feature comparison without requiring user intervention for scanning or manual identification. The system autonomously processes images, extracts features, compares them against database items within categories, and returns identification results, thereby eliminating the throughput bottleneck created by manual user actions while maintaining identification accuracy

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS20260080007A1System and method for selecting an item from a plurality of identified items based on a similarity value

Publication Date: 2026.03.19 7-ELEVEN INC

AI summary

A plurality of images are captured of the first item and a plurality of cropped images are generated based on the first images. An item identifier is identified based on each cropped image, wherein each item identifier is associated with a numerical similarity value. Item identifiers associated with a highest and next highest similarity values are selected. When a difference between the highest and the next highest similarity values equals or exceeds a threshold, the item identifier associated with the highest similarity value is associated with the first item placed on the platform. An indicator of the item identifier is displayed on a user interface device.