Gesture Recognition Device Using Human Body Model for User Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing gesture recognition devices fail to accurately identify the user performing a gesture when multiple users are present, leading to incorrect correlation of gestures with input commands.
Innovation Solution
A gesture recognition device that uses an image acquisition unit to detect gestures and faces, with a correlation unit employing a human body model to associate the detected target region with the corresponding face, enabling accurate user identification and command generation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If face detection is used to identify users performing gestures, then user identification capability is improved, but accuracy deteriorates when multiple users are present in the image
Solution Approach 1:
The system segments the image processing task into two distinct stages: first detecting faces to identify potential users, then detecting gesture target regions (hands) to determine actual gesture performers. This segmentation allows the system to separately process face identification and gesture localization, ultimately correlating them through spatial relationship analysis to accurately identify which detected face corresponds to the gesture performer even when multiple users are present
Solution Approach 2:
The system introduces the gesture target region (hand detection result) as an intermediary element that bridges the gap between face detection and user identification. By detecting the hand position and using it as a mediator to link back to the corresponding face, the system resolves the ambiguity of which face belongs to the gesture performer among multiple detected faces
2Device complexity
If only face detection is performed, then system complexity is reduced, but the ability to correctly identify gesture performers in multi-user scenarios is lost
Solution Approach 1:
The system merges face detection results with gesture target region detection results by correlating their spatial positions. Instead of relying solely on face detection or gesture detection alone, the system combines both detection outcomes and uses position-based correlation to identify the gesture performer, achieving accurate user identification without excessively increasing system complexity
Data Source
AI summary
A gesture recognition device configured to detect a gesture from acquired image and generate command issued to a control target instrument according to the gesture, the gesture recognition device comprising: an image acquisition unit configured to acquire an image; a gesture acquisition unit configured to detect a target region performing a gesture from the acquired image, and acquire the gesture based on motion or a shape of the detected target region; a face detection unit configured to detect a face comprised in the acquired image; a correlation unit configured to correlate the detected target region with the detected face using a human body model representing a shape of a human body; a personal identification unit configured to identify a user corresponding to the detected face; and a command generation unit configured to generate a command issued to the control target instrument based on the identified user and the acquired gesture.