Video Surveillance Knowledge Graph for Resource Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current video surveillance systems face challenges in optimizing the use of computer resources and human resources, leading to inefficiencies in tracking and monitoring objects and events, particularly when dealing with multiple video cameras and complex surveillance scenarios.
Innovation Solution
A computer-implemented method that queries a knowledge graph representing surveillance devices and sensors to identify relevant video cameras and application programs for object and event tracking, optimizing the use of computational and human resources by activating only necessary cameras and application programs based on analytics data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all analytics application programs are run in parallel on all video cameras, then comprehensive monitoring coverage is achieved, but computational resources are excessively consumed
Solution Approach 1:
The system segments the analytics workload by dividing application programs into different categories (e.g., event detection, object tracking, people counting) and assigning them to specific video cameras based on their monitoring zones. This segmentation allows comprehensive monitoring coverage while reducing computational resources by not running all programs on all cameras simultaneously.
Solution Approach 2:
The patent applies local quality by tailoring the analytics programs to be executed on each video camera to its specific monitoring zone and operational requirements. Each camera runs only the relevant analytics programs for its designated area, optimizing computational resource usage while maintaining overall system reliability.
2Use of energy by moving object
If analytics application programs are delayed or deactivated to conserve resources, then computational resources are saved, but response time for detecting and tracking events increases
Solution Approach 1:
The system performs preliminary actions by pre-configuring analytics programs and their execution priorities before events occur. When events are detected, the system already has the necessary programs ready to execute immediately, eliminating delays while conserving resources during normal operation.
Solution Approach 2:
The patent implements dynamics by making the analytics program execution flexible and adaptive. The system can dynamically adjust which programs run on which cameras based on current operational needs, event detection, and resource availability, ensuring fast response times when needed while optimizing resource usage during steady-state operation.
3Adaptability or versatility
If multiple analytics application programs are executed simultaneously on each video camera, then comprehensive analysis is achieved, but system complexity increases
Solution Approach 1:
The system segments analytics programs into distinct functional categories and assigns them to specific video cameras based on their monitoring zones. This segmentation reduces system complexity by preventing all programs from running on all cameras simultaneously, while still achieving comprehensive analysis through coordinated execution across the distributed camera network.
Solution Approach 2:
The patent applies universality by designing a centralized management system that coordinates analytics execution across all video cameras. This universal coordinator handles the complexity of managing multiple programs across distributed devices, allowing comprehensive analysis capability while keeping individual camera complexity low.
Data Source
AI summary
A computer-implemented method of video surveillance comprising the steps of: querying a knowledge graph representing a plurality of video cameras as ontology entities connected by edges, in order to identify, based on a first video camera providing a first video stream that can be fed to at least one first application program to obtain first analytics data, one or more second video cameras which can each provide a respective second video stream; and identifying, based on the first application program and/or based on the first analytics data, at least one second application program that can be fed with at least one second video stream to obtain second analytics data.