Familiarity Estimation Using Hand Viewing and Item Holding Cues
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods struggle to accurately determine which item among many is viewed by a user based solely on face and line of sight direction, making it difficult to estimate the user's familiarity with individual items.
Innovation Solution
A familiarity degree estimation apparatus and method that calculates the time a customer views a hand and holds an item using video processing units, estimating familiarity based on the time spent viewing and holding the item.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If only face direction and line of sight direction are used to detect viewed items, then the detection method is simple, but the accuracy of identifying which item is viewed cannot be achieved
Solution Approach 1:
The detection process is segmented into multiple independent components: face direction detection, line of sight detection, and hand holding detection. Each component processes specific visual information separately, and the results are combined to achieve accurate item identification. This segmentation allows the system to handle complex scenarios by breaking down the detection task into manageable parts.
Solution Approach 2:
The system transitions from two-dimensional detection (face direction and line of sight) to three-dimensional detection by incorporating hand holding information. This dimensional expansion enables the system to accurately identify items even when the customer's face direction and line of sight do not directly point to the held item, resolving the accuracy issue.
2Measurement precision
If hand viewing time and item holding time are measured, then customer familiarity can be accurately estimated, but more video processing is required
Solution Approach 1:
The video processing units perform multiple functions: the first video processing unit detects face direction and line of sight, while the second video processing unit detects hand holding and item identification. Both units process video data independently and contribute to the overall familiarity estimation, making the system efficient despite the increased processing requirements.
Solution Approach 2:
The familiarity degree estimation unit acts as an intermediary that receives processed data from both video processing units and synthesizes the results. It calculates the time while hand is being viewed and time while item is being held, then uses these values to estimate customer familiarity, simplifying the overall process by centralizing the estimation logic.
Data Source
AI summary
In a familiarity degree estimation apparatus, a first video process unit calculates a time while a hand being viewed, which is a time when a customer is viewing the hand. A second video process unit calculates a time while an item being held, which is a time when the customer is holding an item. A familiarity degree estimation unit calculates a time while the item being viewed based on the time while a hand being viewed and the time while the item being held, and estimates that the longer the time while the item being viewed, the lower the degree of familiarity of the customer with respect to the item.