Gesture Recognition Using Preparatory Hand Actions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing gesture recognition systems suffer from erroneous detection due to external interference and difficulty in distinguishing similar user gestures, leading to poor interaction experience.
Innovation Solution
A method that includes recognizing preparatory actions before performing gesture recognition, using a first image stream to detect preparatory actions and a second image stream to confirm gesture actions, enhancing accuracy by considering habitual or natural preparation actions such as hovers or pauses, and utilizing a neural network for gesture classification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a gesture classifier is used to recognize gesture actions, then gesture recognition can be performed, but similar gesture actions cannot be well distinguished causing erroneous detection
Solution Approach 1:
The system performs preliminary detection of preparatory actions (such as hand hovers or pauses) before the actual gesture action occurs. By identifying these preparatory states first, the system can prepare for the upcoming gesture and distinguish it from similar actions, thereby improving detection accuracy while maintaining ease of operation.
2Speed
If gesture recognition is performed continuously, then real-time response is achieved, but external interference causes frequent erroneous detection
Solution Approach 1:
The system detects preparatory actions that occur before the actual gesture is performed. This preliminary detection allows the system to anticipate the upcoming gesture and filter out external interference more effectively, maintaining real-time response while improving reliability by only triggering recognition when a preparatory action is detected.
3Extent of automation
If a hierarchical structure with gesture detector and classifier is used, then gesture recognition is implemented, but similar gesture actions remain indistinguishable
Solution Approach 1:
The system adds a preliminary detection stage that identifies preparatory actions before the main gesture classification. This extra stage provides additional contextual information that helps the hierarchical structure distinguish between similar gesture actions, improving classification accuracy while maintaining automatic operation.
Data Source
AI summary
A gesture recognition method, an electronic device, a computer-readable storage medium, and a chip, are provided, and relate to the field of artificial intelligence. The gesture recognition method includes: obtaining an image stream, and determining, based on a plurality of consecutive frames of hand images in the image stream, whether a user makes a preparatory action; when the user makes the preparatory action, continuing to obtain an image stream, and determining a gesture action of the user based on a plurality of consecutive frames of hand images in the continuously obtained image stream; and next, further responding to the gesture action to implement gesture interaction with the user. In this application, the preparatory action is determined before gesture recognition is performed, so that erroneous recognition occurring in a gesture recognition process can be reduced, thereby improving a gesture recognition effect.