Abnormality Judgment Device Motion Procedure Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for detecting abnormal motion in videos primarily focus on individual motions rather than procedures, making it difficult to determine the correctness of motion sequences and simultaneously detect abnormalities within procedures.
Innovation Solution
An abnormality determination device and method that utilize a clustering database for motion clusters and a procedure tree database to classify video data into motion clusters and procedures, enabling the simultaneous detection of motion and procedure abnormalities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional motion detection methods are used, then individual motion abnormalities can be detected, but procedure-level abnormalities cannot be detected
Solution Approach 1:
The system segments the detection task into two levels: motion-level detection (individual actions) and procedure-level detection (sequences of actions). Motion clusters represent individual motion patterns, while procedure trees organize these motions into hierarchical procedures. This segmentation allows the system to detect abnormalities at both granularities simultaneously.
Solution Approach 2:
The system adds a temporal/procedural dimension to the detection framework by organizing motion clusters into procedure trees that represent sequences and hierarchies of actions. This transforms the detection from a single-dimension (individual motion) to multi-dimension (motion + procedure sequence), enabling detection of procedural abnormalities.
2Measurement precision
If manual detection is used, then accurate abnormal motion detection is possible, but it is time- and labor-intensive
Solution Approach 1:
The system enables automatic detection by training motion clusters and procedure trees on video data, allowing the algorithm to self-learn normal motion patterns and procedural sequences. Once trained, the system autonomously detects abnormalities without requiring manual observation, achieving both high accuracy and efficiency.
Solution Approach 2:
The system transforms the detection approach by changing parameters from manual feature extraction to automated cluster-based representation. Motion clusters capture essential motion characteristics, and procedure trees encode temporal relationships, enabling efficient automatic analysis while maintaining accuracy comparable to manual detection.
3Ease of operation
If motion clustering is performed, then individual motion classification is achieved, but procedural context is lost
Solution Approach 1:
The system implements a nested structure where motion clusters (individual motions) are nested within procedure trees (sequences of motions). Each procedure node contains references to motion clusters, creating a hierarchical organization that preserves procedural context while maintaining detailed motion classification capabilities.
Solution Approach 2:
The system merges motion-level classification results with procedure-level contextual information by integrating motion cluster assignments into the procedure tree structure. This combination allows the system to simultaneously utilize detailed motion features and broader procedural context for comprehensive abnormality detection.
Data Source
AI summary
A motion abnormality determination unit 62 classifies video data representing a motion of a person into motion clusters and determines whether the motion of the person is abnormal. A procedure classification unit 66 classifies the motion of the person into procedures based on classification results of the motion clusters and a procedure tree. A procedure abnormality determination unit 68 determines whether the procedure including the motion of the person is abnormal based on the classification result of the procedure.