Video Scene Retrieval Using Skeleton Behavior and Face IDs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing video processing systems struggle to efficiently search for scenes showing specific behaviors of specific persons using simple keyword searches, as they lack the ability to associate behavior information with person identification.
Innovation Solution
A video processing system that generates skeleton information from body regions, converts it into behavior IDs, specifies person IDs based on facial regions, and registers these IDs and scene-related information in a database for easy retrieval.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If facial image recognition is used to identify persons, then person identification capability is improved, but the system cannot search for specific behaviors performed by persons
Solution Approach 1:
The system segments the video analysis into two independent components: facial region analysis for person identification and body region analysis for behavior recognition. This segmentation allows each component to specialize in its function while working together through the database integration mechanism.
Solution Approach 2:
The system merges facial recognition results and body behavior recognition results into a unified database structure where person IDs and behavior IDs are associated with scene information, enabling combined search capabilities for both person and behavior.
2Measurement precision
If detailed behavior information is stored in the database, then search accuracy is improved, but system complexity and data storage requirements increase
Solution Approach 1:
The system extracts only the essential behavior characteristics needed for search purposes and stores them as behavior IDs in the database, rather than storing complete video segments or detailed motion analysis data, thereby reducing storage requirements while maintaining search accuracy.
Solution Approach 2:
The system transforms complex behavior information into simplified parameter representations (behavior IDs) that capture the essential characteristics needed for keyword-based searching, reducing data complexity while preserving search functionality.
Data Source
AI summary
A video processing system (10) includes: an image acquisition unit (11) that acquires at least one frame image included in video data; a skeleton information generation unit (13) that generates skeleton information based on a body region of a person included in the at least one frame image; a behavior conversion unit (14) that converts the skeleton information into a behavior ID; a person specifying unit (18) that specifies, based on a facial region of the person included in the at least one frame image, a person ID for identifying features of a person estimated to be an identical person; and a registration unit (20) that registers the behavior ID, the person ID, and scene-related information related to the at least one frame image in a database in association with each other.