Event Detection Apparatus Using Object Relationship Information
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing video monitoring techniques primarily focus on detecting the center of mass of objects, which limits the ability to monitor complex events involving multiple objects and their relationships.
Innovation Solution
An event detecting apparatus and method that acquire video data, generate object relationship information indicating action-related relationships between objects, and determine the occurrence of specific events by matching sequences of action-related situations within the video data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If video monitoring focuses on detecting center of mass of objects, then detection simplicity is maintained, but the ability to monitor complex events involving multiple objects and their relationships deteriorates
Solution Approach 1:
The patent segments the monitoring task into multiple components: detecting individual objects, tracking their movements, identifying relationships between objects, and recognizing event patterns. This segmentation allows the system to handle complex events by breaking them down into manageable detection steps while maintaining overall simplicity.
Solution Approach 2:
The patent transitions from single-object center-of-mass detection to multi-object relationship detection by adding dimensional layers: spatial relationships between objects, temporal sequences of actions, and semantic relationships. This dimensional expansion enables complex event monitoring while building upon the foundation of simple center-of-mass detection.
2Use of energy by moving object
If traditional center of mass detection is used, then computational resources are conserved, but detection accuracy for intricate actions deteriorates
Solution Approach 1:
The system performs preliminary detection of object centers of mass and basic movements first, then selectively applies more complex relationship analysis only when needed for event recognition. This preliminary action approach conserves computational resources by avoiding unnecessary complex calculations while maintaining high detection accuracy for intricate actions when required.
Solution Approach 2:
The patent applies partial action by focusing computational resources on detecting specific action-related relationships that are relevant to event recognition, rather than analyzing all possible object interactions. This selective approach balances computational efficiency with detection accuracy for intricate actions.
Data Source
AI summary
An event detecting apparatus acquires one or more video data, and generates, from the one or more video data, object relationship information that indicates two or more action-related relationships between objects. The event detecting apparatus acquires an event information that indicates an event of interest by a sequence of action-related situations at least one of which represents a situation in which a specific action is taken by a specific subject. The event detecting apparatus determines whether or not the event of interest occurs based on the object relationship information and the event information.