Scalable Position Tracking via Time-Windowed Sensor Fusion

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Position tracking systems face limitations in larger spaces due to synchronization issues and computing power constraints, which hinder accurate tracking of people and objects across extensive areas.

Innovation Solution

A distributed tracking system utilizing an array of cameras, multiple camera clients, a camera server, weight sensors, a weight server, and a central server, with a camera server assigning coordinates to time windows to mitigate desynchronization and a unique wiring arrangement of cameras for improved resiliency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Area of stationary object

If additional sensors are installed throughout the space to track positions in larger areas, then the coverage area of the tracking system is improved, but the computing power requirements increase and synchronization issues arise

Engineering Contradiction:

Improvecoverage areaVSAvoidcomputing power requirements

Core Design Contradiction:

Area of stationary objectVSDevice complexity

Solution Approach 1:

The tracking system is divided into multiple distributed computing nodes, each responsible for processing data from specific sensors. This segmentation allows the system to scale to larger coverage areas without requiring a single powerful computer, as each node handles only its local portion of the tracking task.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces a temporal dimension by organizing sensor data into time windows and using timestamp-based sorting. This allows the system to handle desynchronization between sensors by processing data in temporal sequences rather than requiring simultaneous processing, effectively adding a time dimension to the spatial tracking problem.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

2Area of stationary object

If sensors are divided amongst multiple computers to scale the system, then the coverage area is improved, but synchronization issues and desynchronization between sensors and computers occur

Engineering Contradiction:

Improvecoverage areaVSAvoidsynchronization accuracy

Core Design Contradiction:

Area of stationary objectVSReliability

Solution Approach 1:

The system assigns time windows to each sensor in advance and timestamps sensor readings with these pre-assigned time windows. This preliminary temporal organization allows data from multiple sensors to be systematically sorted and correlated by time, resolving synchronization issues before processing occurs.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system uses timestamp feedback from each sensor to sort and correlate data across multiple computing nodes. By continuously monitoring and sorting data based on timestamps, the system can identify and correct desynchronization issues, ensuring reliable position tracking across the distributed network.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11580748B2Tracking positions using a scalable position tracking system

Publication Date: 2023.02.14 7-ELEVEN INC

AI summary

A scalable tracking system processes video of a space to track the positions of objects within a space. The tracking system determines local coordinates for the objects within frames of the video and then assigns these coordinates to time windows based on when the frames were received. The tracking system then combines or clusters certain local coordinates that have been assigned to the same time window to determine a combined coordinate for an object during that time window.