Video Tracking for Person-of-Interest Identifier Association
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In video surveillance combined with communication monitoring, identifying a specific individual's mobile communication terminal identifier amidst a large number of overlapping identifiers from multiple interrogation devices and video cameras is challenging, especially in crowded areas where many people enter or exit simultaneously, making it difficult to accurately associate the correct identifier with the person-of-interest.
Innovation Solution
A system comprising multiple pairs of video cameras and interrogation devices provides continuous coverage, allowing a processor to track a person-of-interest by correlating identifiers from paired devices with video tracking techniques, extracting features, and predicting movement to accurately locate and associate the correct identifier with the person-of-interest across multiple images and devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If multiple interrogation devices are deployed to cover large areas, then the coverage area increases, but the number of overlapping identifiers increases making identification difficult
Solution Approach 1:
The system divides the surveillance area into multiple zones, each covered by a specific video camera. Each interrogation device is paired with a specific video camera to cover a particular zone. This segmentation allows the system to process and correlate identifiers from different zones independently, reducing the complexity of handling overlapping identifiers from multiple devices.
Solution Approach 2:
The video camera acts as an intermediary between the interrogation device and the identifier correlation process. The processor uses video tracking information from the camera to determine which person-of-interest is present in the coverage area at a given time, and this video-based information serves as the basis for correlating identifiers from the paired interrogation device with the correct individual.
2Measurement precision
If video tracking is used to track person-of-interest across multiple cameras, then tracking accuracy improves, but processing complexity increases
Solution Approach 1:
The system merges the video tracking function with the identifier correlation function by pairing specific interrogation devices with specific video cameras. This combination allows the processor to use video tracking results directly for identifier correlation without requiring separate, complex processing systems for each function.
Solution Approach 2:
The system performs video tracking and identifies the person-of-interest in advance before correlating identifiers. The processor first determines which individual is the person-of-interest based on video tracking across multiple cameras, then uses this pre-established information to correlate identifiers from interrogation devices, simplifying the overall processing sequence.
Data Source
AI summary
A plurality of pairs of video cameras and interrogation devices may be placed in a public place along various paths that a person-of-interest might be expected to move. The person-of-interest is then located in multiple images acquired, collectively, by multiple video cameras. From each of the interrogation devices that are paired with these video cameras, a subset of the captured identifiers is obtained. Candidate identifiers are then restricted to those identifiers that are included in each of the subsets. A given identifier may be rejected as a candidate identifier. To automatically locate the person-of-interest in the images acquired by the “paired” video cameras, a processor may utilize video-tracking techniques to automatically track the person-of-interest, such that the person-of-interest is not “lost.” By virtue of utilizing such tracking techniques, the person-of-interest may be repeatedly located automatically, and with minimal chance of a false detection.