Multi-Sensor Object Tracking via Data Fusion and Penalty Costs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated object tracking systems fail to effectively combine data from multiple sensor types in real-time, leading to inaccurate object location and association due to sensor errors and lack of integration across different sensor modalities.
Innovation Solution
A system and method that combines data from various sensors, such as video cameras and RFID tag readers, using processor-based calculations to determine tentative associations between objects and actors, incorporating penalty cost parameters to refine tracking accuracy and reduce errors, enabling real-time or near-real-time data fusion and analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If data from multiple sensor types are combined in real-time, then tracking accuracy and association probability are improved, but device complexity and data processing requirements increase
Solution Approach 1:
The system segments the tracking problem into distinct components: video data processing, RFID data processing, and data fusion. Each sensor type is processed independently through dedicated modules before being combined, allowing complex multi-sensor integration to be managed as separate, manageable tasks that reduce overall system complexity
Solution Approach 2:
The patent introduces an intermediary data fusion module that acts as a mediator between video sensors and RFID sensors. This intermediary component receives data from both sensor types, performs correlation analysis, and produces integrated tracking results, thereby managing the complexity of direct multi-sensor integration
2Reliability
If multiple sensor types are integrated for real-time tracking, then object-actor association accuracy is improved, but information processing time and computational resources increase
Solution Approach 1:
The system performs preliminary actions by pre-processing video data to extract actor paths and pre-processing RFID data to identify object locations before the actual data fusion occurs. This preliminary organization of data from multiple sensors reduces the computational burden during real-time association, thereby reducing processing time while maintaining high association accuracy
Solution Approach 2:
The patent changes parameters by transforming raw sensor data into standardized formats with specific parameters (e.g., actor paths with position and time, object locations with coordinates). This parameter standardization enables efficient comparison and correlation between different sensor data types, reducing processing time while improving association reliability
Data Source
AI summary
Method of tracking moveable objects (typically tagged objects that are moved by actors e.g. people, vehicles) by combining and analyzing data obtained from multiple types of sensors, such as video cameras, RFID tag readers, GPS sensors, and WiFi transceivers. Objects may be tagged by RFID tags, NFC tags, bar codes, or even tagged by visual appearance. The system operates in near real-time, and compensates for errors in sensor readings and missing sensor data by modeling object and actor movement according to a plurality of possible paths, weighting data from some sensors higher than others according to estimates of sensor accuracy, and weighing the probability of certain paths according to various other rules and penalty cost parameters. The system can maintain a comprehensive database which can be queried as to which actors associate with which objects, and vice versa. Other data pertaining to object location and association can also be obtained.