Motion Gesture Recognition Using Dynamic Field of View Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic devices face challenges in accurately recognizing repetitive motion gestures, often mistakenly recognizing unintended gestures, which decreases usability by incorrectly interpreting user inputs.
Innovation Solution
An electronic device equipped with a camera and processor that acquires image frames to determine the field of view of an object's motion, distinguishing between different directions and critical field of views to accurately recognize specific motion gestures, thereby preventing misinterpretation of user intentions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If gesture recognition technology is implemented in electronic devices, then user interaction convenience is improved, but false recognition of repetitive motion gestures occurs
Solution Approach 1:
The patent applies dynamics by making the gesture recognition system adaptive and responsive to changing motion patterns. The processor dynamically adjusts recognition parameters based on the detected motion characteristics, including calculating motion vectors between consecutive image frames and determining gesture validity based on motion continuity. This dynamic approach allows the system to distinguish between intentional repetitive gestures and unintentional hand movements, resolving the contradiction between ease of operation and recognition reliability.
Solution Approach 2:
The patent implements feedback mechanisms by continuously monitoring motion patterns and using this information to refine gesture recognition. The system calculates motion vectors, compares them against threshold values, and uses this feedback to determine whether detected motions represent valid gestures. This feedback loop enables the system to maintain high recognition accuracy for repetitive gestures while filtering out false detections, thereby improving reliability without compromising user interaction convenience.
2Adaptability or versatility
If motion gesture recognition is performed using camera and image processing, then contactless interaction is enabled, but computational complexity increases
Solution Approach 1:
The patent extracts only the essential motion information needed for gesture recognition from the full image frames. Instead of processing entire images, the system identifies specific regions containing hands or objects, calculates motion vectors only for these regions, and uses this extracted motion data for gesture determination. This extraction approach enables contactless interaction while significantly reducing computational complexity by focusing processing resources on relevant motion patterns rather than analyzing complete image frames.
3Measurement precision
If critical field of view thresholds are used to distinguish gestures, then gesture recognition precision is improved, but system complexity increases
Solution Approach 1:
The patent employs parameter changes by establishing critical field of view thresholds that define valid gesture ranges. The processor calculates the field of view for detected motions and compares it against these predetermined threshold parameters to determine gesture validity. This parameter-based approach improves gesture recognition precision by providing clear decision criteria, while the use of simple threshold comparisons keeps the system complexity manageable rather than requiring complex algorithms.
Data Source
AI summary
An electronic device including a camera, a processor and memory storing instructions is provided. The instructions, when executed by the processor, cause the electronic device to acquire image frames including a first image frame and a second image frame by using a camera, determine, as a first field of view (FOV), a FOV between a first axis and a first direction, in which an object related to motion is oriented, when the object is recognized in the first image frame, determine, as a second FOV, a FOV between the first axis and a second direction in which the object recognized in the second image frame following the first image frame is oriented, recognize a first motion gesture in response to the first FOV being at most a first critical FOV, the second FOV being at least a second critical FOV, and perform a first function corresponding to the first motion gesture in response to the recognition of the first motion gesture.