Object Tracking System Profile Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing object tracking systems in camera monitoring systems require significant processing power and time due to the need to compare identification characteristics with a large number of potential profiles, leading to inefficiencies and reduced reliability in identifying individuals within a defined area.
Innovation Solution
A method that reduces processing time by maintaining a list of pre-registered identification profiles for individuals within the area, using confidence scores to focus comparisons on the most likely candidates, and updating profiles based on new image data to improve matching efficiency and accuracy, while removing profiles of individuals who have left the area or not recently detected.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If identification characteristics are compared with all stored profiles, then comprehensive identification is achieved, but processing time and computational resources increase significantly
Solution Approach 1:
The system performs preliminary actions by pre-registering identification profiles and maintaining an active list of persons in the monitored area before tracking begins. When a person is detected, the system only compares their identification characteristics against the pre-prepared list of active profiles rather than searching through all stored profiles, significantly reducing processing time while maintaining identification reliability
Solution Approach 2:
The system segments the identification process into two distinct phases: (1) pre-registration phase where profiles are stored and organized, and (2) active tracking phase where only currently relevant profiles are compared. This segmentation allows the system to maintain comprehensive profile databases while performing rapid comparisons only against relevant subsets during active monitoring
2Reliability
If all stored profiles are compared for each detected object, then no identification is missed, but processing power requirements increase
Solution Approach 1:
The system dynamically maintains an active list of profiles that changes based on the current state of the monitored area. As persons enter or leave the area, their profiles are added or removed from the active list, ensuring that only currently relevant profiles are compared during tracking, thereby optimizing processing power usage while maintaining identification accuracy
Solution Approach 2:
The system changes the parameter of profile relevance by maintaining different states for profiles (registered but not yet in area, currently in area, left the area). This parameter change allows the system to optimize processing power by comparing detection characteristics only against profiles with 'currently in area' status rather than all registered profiles
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The present invention relates to a method and system for tracking objects in a defined area. The invention compares image data of a detected object to profiles of persons that have entered the defined area to find the best match and connect the profile of the best match to the detected object. Identification profiles of persons that have been identified, by presenting their credentials, when entering the defined area are registered as candidates and are later matched with objects detected in the defined area. The invention hence uses the physical access control system of the defined area to reduce the number of candidates for the detected objects to the most likely candidates. The processing time and need for resources of the object tracking in the defined area are thereby reduced.