Video Identification System Using Mobile Device Data Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current surveillance systems lack the capability to analyze video streams in real-time and post-time for security and investigative purposes, failing to effectively identify and address underlying user behaviors that contribute to inventory shrinkage and other security concerns.
Innovation Solution
An analytical recognition system that combines video camera data with mobile communication device data, using a data analytics module to analyze physical and movement attributes, perform facial recognition, and generate combined certainty match values to identify subjects and track their behavior in real-time and post-time analyses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If video streams are continuously stored in buffer for later review, then investigative analysis capability is improved, but storage requirements and data management complexity increase
Solution Approach 1:
The patent extracts only the essential information from continuous video streams by using event detection algorithms to identify and flag specific incidents (thefts, accidents, suspicious behaviors). Instead of retaining all video data, the system extracts and stores only relevant event segments, significantly reducing storage requirements while maintaining investigative capability.
Solution Approach 2:
The system performs preliminary analysis of video streams in real-time using automated event detection algorithms. Events are pre-identified and flagged before review, allowing investigators to quickly locate and analyze only relevant segments without manually searching through hours of continuous footage, thus simplifying buffer management.
2Measurement precision
If multiple data sources (video, mobile device data, facial recognition) are integrated for subject identification, then identification accuracy is improved, but system complexity and processing requirements increase
Solution Approach 1:
The patent merges multiple independent identification systems (video analysis, mobile device data detection, facial recognition) into a unified subject identification framework. Each data source operates semi-independently but contributes to a combined confidence score, allowing the system to achieve high identification accuracy while maintaining modular architecture that manages complexity.
Solution Approach 2:
The system employs a universal data analytics module that handles multiple types of data (video streams, mobile communication device data, facial recognition data) through a single integrated processing framework. This multi-functional module reduces overall system complexity by providing a unified interface and consistent processing logic across different data sources.
3Speed
If real-time video analysis is performed to identify user behaviors, then security response time is improved, but processing power and energy consumption increase
Solution Approach 1:
The system performs partial real-time analysis by continuously monitoring only key behavioral indicators and event triggers rather than analyzing every frame of video data in full detail. Low-complexity detection algorithms run continuously at low power, while more intensive analysis is activated only when events are detected, reducing overall energy consumption while maintaining fast response times.
Solution Approach 2:
The video analysis operates in periodic cycles with alternating phases of low-power monitoring and high-power analysis. The system continuously scans for event triggers at low computational intensity, then performs detailed real-time analysis only when triggers are detected, creating a periodic pattern that balances speed and energy consumption.
Data Source
AI summary
An analytical recognition system includes a video camera configured to capture video data of a subject and an antenna configured to capture mobile communication device data relating to the subject's mobile device. The system further includes a data analytics module configured to: analyze the video data to determine one of a physical attribute or a movement attribute of the subject and generate a first certainty match value based on this attribute perform facial recognition analysis of the subject to obtain facial recognition data and generate a second certainty match value based on the facial recognition data; generate a third certainty match value based on the mobile device data; and combine the first, second, and third certainty match values to produce a combined certainty match value, which enhances the accuracy of identifying the subject by integrating multiple data sources, including physical attributes, facial features, and mobile device information.