Gesture Recognition by User Distance for Mobile Object Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing gesture recognition systems for robots guiding users or transporting baggage lack user convenience due to inefficiencies in recognizing user gestures, particularly in varying distances and environments.
Innovation Solution
A gesture recognition apparatus and method that employs multiple image capture regions and corresponding recognition information, prioritizing gesture recognition based on the user's position relative to the imaging device, using first and second information for accurate gesture recognition, and controlling mobile objects accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single gesture recognition system is used for all user positions, then the system structure is simple, but the gesture recognition accuracy deteriorates due to varying distances and imaging conditions
Solution Approach 1:
The imaging space is segmented into multiple regions (first region within predetermined distance, second region beyond predetermined distance, third region between first and second regions). Different gesture recognition processing methods are applied to each region, improving recognition accuracy for users at various distances while maintaining manageable system complexity through structured segmentation.
Solution Approach 2:
Different recognition information types are applied to different spatial regions: first information (hand/finger motion) for close range, second information (arm motion) for far range, and combined information for intermediate range. This local differentiation optimizes recognition accuracy for each specific imaging condition without requiring a completely different system for each region.
2Measurement precision
If multiple recognition information types are used for different regions, then the gesture recognition accuracy improves, but the information processing complexity increases
Solution Approach 1:
The system dynamically selects and combines recognition information types based on the user's real-time position. The processor determines which region the user is in and applies the appropriate recognition method (first information only, second information only, or both), making the processing complexity adaptive rather than static, thus managing complexity while maintaining high accuracy across all regions.
Solution Approach 2:
The system automatically determines the user's region and selects the appropriate recognition information type without requiring manual intervention. The processor self-manages the complexity by autonomously deciding whether to use first information, second information, or both, based on the captured image analysis and region determination.
3Measurement precision
If the system processes both first and second information for all users, then the gesture recognition accuracy is maximized, but the processing load increases
Solution Approach 1:
The system applies partial processing (using only first information or only second information) when appropriate for the user's region, rather than always processing both information types. This reduces the processing load for users in regions where one information type is sufficient, while still maintaining high recognition accuracy by using both types when needed for users in the third region.
Data Source
AI summary
A gesture recognition apparatus acquires an image capturing a user, recognizes a region where the user is present when the image is captured, and in a case in which the user is present in a first region when the image is captured, recognizes a gesture of the user on the basis of the image and first information for recognizing the gesture of the user, and in a case in which the user is present in a second region when the image is captured, recognizes a gesture of the user on the basis of the image and second information for recognizing the gesture of the user.