Occupant Tracking via Unique Identity Assignment

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current tracking and monitoring methods, such as GPS and image-based people detecting algorithms, face challenges in continuously tracking specific individuals in complex environments with multiple people, occlusions, and cluttered backgrounds, and often compromise privacy by transmitting images of monitored spaces.

Innovation Solution

A system and method that identifies and tags a specific occupant in an image, allowing for continuous tracking across multiple cameras without re-identifying the individual, using unique descriptors and dynamic metrics to ensure accurate object recognition and location within a space, while maintaining privacy by not transmitting images.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If GPS tracking devices are used to monitor people, then tracking capability is improved, but privacy is compromised and device dependency increases

Engineering Contradiction:

Improvetracking capabilityVSAvoidprivacy compromise

Core Design Contradiction:

ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The patent extracts the identification function from continuous image transmission by using people detecting algorithms to identify persons and then tracking them through their detected positions across multiple images, thereby eliminating the need to transmit actual images while maintaining tracking capability

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system introduces an intermediary tracking mechanism that uses detected person positions and people detecting algorithms as mediators between the cameras and the tracking output, allowing tracking without direct image transmission

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If people detecting algorithms are used to identify persons in images, then identification capability is improved, but continuous tracking in complex scenes deteriorates due to occlusions and multiple people

Engineering Contradiction:

Improveperson identification accuracyVSAvoidcontinuous tracking capability

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The system performs preliminary identification of persons in each image using people detecting algorithms before tracking, establishing initial person detections that serve as the foundation for subsequent tracking across the image sequence

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent maintains continuous tracking by repeatedly applying people detecting algorithms across multiple images and using the detected person positions to continuously update and maintain track of identified persons throughout the image sequence

Inventive Principle:

Principle #20Continuity of useful action

3Reliability

If cameras are positioned to optimize tracking coverage, then tracking reliability is improved, but installation complexity and aesthetic considerations worsen

Engineering Contradiction:

Improvetracking coverageVSAvoidcamera installation flexibility

Core Design Contradiction:

ReliabilityVSEase of manufacture

Solution Approach 1:

The system changes the parameter being optimized from camera positioning to algorithmic tracking parameters, allowing standard camera installations to achieve effective tracking through software-based person detection and position tracking rather than requiring optimized camera geometry

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS11256910B2Method and system for locating an occupant

Publication Date: 2022.02.22 POINTGRAB

AI summary

An object is tracked in images of the space. A unique identification is assigned to the object and the uniquely identified object may then be located within the space based on the tracking of the object, without having to again uniquely identify the object.