Store Action Detection Using Skeletal Tracking for Scan Omission
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems struggle to accurately detect scan omission of products during self-scan due to variations in product types, sizes, and unit prices, leading to inaccurate identification of fraudulent behavior.
Innovation Solution
An information processing program that generates skeletal information from captured images, specifies actions related to product handling, and adjusts evaluation parameters based on setting information to improve detection accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a surveillance camera system is used to detect scan omission, then the ability to detect fraudulent behavior is improved, but the accuracy of detection deteriorates due to variations in product types, sizes, and unit prices
Solution Approach 1:
The system applies different detection parameters and thresholds for different product areas based on their characteristics. Each product area is assigned specific settings that account for variations in product types, sizes, and prices, allowing the system to accurately detect scan omission behavior specific to each local area rather than using a uniform detection approach across the entire store.
Solution Approach 2:
The system dynamically adjusts detection parameters based on real-time analysis of customer behavior patterns in different product areas. By continuously learning and adapting to variations in how customers interact with different products, the system maintains high detection accuracy despite changes in product inventory, arrangement, and customer demographics.
2Measurement precision
If detection parameters are adjusted for different product areas, then the accuracy of scan omission detection is improved, but the system complexity increases
Solution Approach 1:
The system pre-configures detection parameters for different product areas during setup, allowing administrators to define area-specific settings before actual operation begins. This preliminary configuration enables the system to automatically adapt to different product types and customer behaviors without requiring complex real-time calculations or manual adjustments during detection operations.
Solution Approach 2:
The system automatically learns and adapts to detection patterns by analyzing customer behavior data, reducing the need for manual configuration and adjustment. Through self-learning mechanisms, the system autonomously optimizes detection parameters for each product area based on observed patterns, minimizing the operational complexity while maintaining high detection accuracy.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An information processing program that causes a computer to execute a process, the process includes generating skeletal information of a person who stays in a store from a captured image; detecting a specific action of the person for a product using the skeletal information; specifying an area where the person is staying when having detected the specific action in the store using positional information of the person in the image; specifying setting information associated with the specified area; and changing a parameter that evaluates a behavior of the person for the product on the basis of the specified setting information.