Gesture Recognition System for Multi-User Engagement Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic apparatuses using gesture recognition technology often misrecognize user intentions, leading to unintended function executions when multiple users are present, which deteriorates user convenience and satisfaction.
Innovation Solution
An electronic apparatus equipped with a camera, memory, and processor that detects objects, identifies engagement and gesture information, and determines a target object based on operation status, engagement, and gesture information to accurately execute functions corresponding to user intentions, thereby preventing misrecognition and ensuring intended actions are performed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If gesture recognition technology is applied to recognize user gestures and execute corresponding functions, then user interaction capability is improved, but misrecognition of user intention occurs when multiple users are present, leading to wrong function execution
Solution Approach 1:
The system segments the recognition process into multiple independent analysis dimensions: engagement level assessment (gaze direction, head orientation, body posture), gesture recognition, and operation status detection. Each dimension is processed separately and then integrated to make the final determination, allowing the system to distinguish between primary and secondary users accurately
Solution Approach 2:
The system introduces an intermediary engagement level assessment mechanism that acts as a mediator between gesture detection and function execution. Before executing a function, the system evaluates the user's engagement level through gaze direction, head orientation, and body posture analysis. This intermediary step filters out accidental or unintended gestures from secondary users, resolving the contradiction between maintaining versatile interaction and ensuring reliable recognition
2Speed
If the electronic apparatus executes functions based on recognized gestures in multi-user environments, then response speed is improved, but user convenience deteriorates due to unintended function execution
Solution Approach 1:
The system performs preliminary engagement level assessment and operation status detection before executing functions. By pre-evaluating gaze direction, head orientation, body posture, and current operation status, the system identifies the primary user and validates gesture intent beforehand. This preliminary action prevents unintended function execution while maintaining fast response during valid interactions
Solution Approach 2:
The system implements feedback mechanisms that continuously monitor engagement levels and operation status. When a gesture is detected, the system provides feedback by validating whether the gesture comes from the primary user based on accumulated engagement data. This feedback loop ensures that functions are executed only when appropriate, maintaining both speed and convenience
3Adaptability or versatility
If the electronic apparatus recognizes gestures from any detected object, then interaction coverage is improved, but measurement precision deteriorates due to inability to distinguish primary user from secondary users
Solution Approach 1:
The system applies different quality thresholds and evaluation criteria for different users based on their engagement levels. The primary user, identified through sustained engagement indicators (gaze direction, head orientation, body posture), receives higher weight in gesture validation. This local quality differentiation allows the system to maintain broad interaction coverage while precisely identifying the primary user's intentions
Data Source
AI summary
An electronic apparatus is provided. The electronic apparatus includes a camera; a memory configured to store at least one instruction; and at least one processor configured to execute the at least one instruction to: detect at least one object included in an image captured by the camera; identify information on an engagement of each of the at least one object with the electronic apparatus; obtain gesture information of each of the at least one object; obtain a target object from among the at least one object based on an operation status of the electronic apparatus, the information on the engagement of each of the at least one object, and the obtained gesture information of each of the at least one object; identify a function corresponding to gesture information of the target object; and execute the identified function.