Static Posture Person Identification via Skeleton Feature Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for identifying individuals based on skeletal data face challenges in accuracy and efficiency due to dynamic feature sets and high memory requirements, especially when identifying individuals at a distance without their cooperation.
Innovation Solution
A system and method for identifying an unknown person based on their static posture, using a skeleton recording device to capture and process data from skeleton joints, extracting feature vectors for static postures, and training a classifier to match these features for accurate identification, reducing processing load and memory requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If dynamic skeleton data is used for person identification, then the identification can capture person characteristics, but the processing load and processing time substantially increase
Solution Approach 1:
The patent extracts only the essential static posture features from the complete skeleton data, isolating the specific joint coordinates and body part positions that are sufficient for identification while discarding redundant dynamic information. This extraction of necessary features reduces processing time while maintaining identification accuracy.
Solution Approach 2:
The patent uses a simplified feature set that is computationally inexpensive to process, replacing complex dynamic skeleton analysis with static posture measurements. This disposable approach to data processing achieves identification without requiring substantial computational resources or time.
2Measurement precision
If dynamic skeleton data is used for person identification, then the identification can capture person characteristics, but the memory space substantially increases
Solution Approach 1:
The patent extracts only the essential static posture features from the complete skeleton data, isolating the specific joint coordinates and body part positions that are sufficient for identification while discarding redundant dynamic information. This extraction of necessary features reduces processing time while maintaining identification accuracy.
Solution Approach 2:
The patent uses a simplified feature set that is computationally inexpensive to process, replacing complex dynamic skeleton analysis with static posture measurements. This disposable approach to data processing achieves identification without requiring substantial computational resources or time.
3Ease of operation
If skeleton data is captured at a distance, then the identification is unobtrusive and does not require cooperation, but the measurement precision may be reduced
Solution Approach 1:
The patent transitions from analyzing dynamic temporal patterns to analyzing static spatial configurations of the skeleton. By focusing on the spatial arrangement of body parts in static postures rather than dynamic movements, the system maintains measurement precision even when capturing data at a distance without subject cooperation.
Data Source
AI summary
A system and method for identifying an unknown person based on a static posture of the unknown person is described. The method includes receiving data of N skeleton joints of the unknown person from a skeleton recording device. The method further includes identifying the static posture of the unknown person. The method includes dividing a skeleton structure of the unknown person in a plurality of body parts based on joint types of the skeleton structure. In addition, the method includes extracting feature vectors for each of the joint type from each of the plurality of body parts. The method further includes identifying the unknown person based on comparison of the feature vectors for the unknown person with one of a constrained feature dataset and an unconstrained feature dataset for a plurality of known persons.