Gesture Recognition via Skeletal Cross-Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current natural user interface technologies face challenges in accurately recognizing and interpreting complex human body motions, particularly in noisy environments and with varying levels of user skill, which affects the reliability and precision of gesture recognition in applications like video games.
Innovation Solution
A real-time gesture classification system using a cascaded correlation-based classifier with angular representation of skeletal motion, dynamic time-warping distance metric, and robust feature extraction methods to align and compare user input with prototype gestures, enhancing recognition accuracy and robustness.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional gesture recognition systems are used, then the system is simple to implement, but the recognition accuracy deteriorates in noisy environments and with varying user skill levels
Solution Approach 1:
The gesture recognition system is divided into multiple independent modules: skeletal motion data extraction module, feature extraction module, classification module, and prototype comparison module. Each module handles a specific aspect of the recognition process, improving overall accuracy while maintaining manageable complexity through modular design.
Solution Approach 2:
The patent introduces skeletal motion data as an intermediary representation between raw camera input and gesture classification. This intermediate skeletal model abstracts the complex visual data into meaningful motion features, enhancing recognition accuracy while simplifying the comparison process against gesture prototypes.
2Reliability
If the system processes all prototype motion features, then comprehensive classification is achieved, but processing time increases
Solution Approach 1:
The system performs feature extraction and initial comparison on a subset of relevant prototype motion features rather than all possible gestures. This partial processing approach maintains reliable classification for the most likely gestures while significantly reducing processing time by avoiding exhaustive comparison with every prototype in the database.
Data Source
AI summary
Human body motion is represented by a skeletal model derived from image data of a user. Skeletal model data may be used to perform motion recognition and/or similarity analysis of body motion. An example method of motion recognition includes receiving skeletal motion data representative of a user data motion feature from a capture device relating to a position of a user within a scene. A cross-correlation of the received skeletal motion data relative to a plurality of prototype motion features from a prototype motion feature database is determined. Likelihoods that the skeletal motion data corresponds to each of the plurality of prototype motion features are ranked. The likelihoods are determined using the cross-correlation. A classifying operation is performed on a subset of the plurality of prototype motion features. The subset of the plurality of prototype motion features is chosen because its members have the relatively highest likelihoods of corresponding to the skeletal motion data.