View source for 17454786. MACHINE-VISION PERSON TRACKING IN SERVICE ENVIRONMENT simplified abstract (MICROSOFT TECHNOLOGY LICENSING, LLC)

=MACHINE-VISION PERSON TRACKING IN SERVICE ENVIRONMENT=


==Organization Name==

[[:Category:MICROSOFT TECHNOLOGY LICENSING, LLC|MICROSOFT TECHNOLOGY LICENSING, LLC]]


[[Category:MICROSOFT TECHNOLOGY LICENSING, LLC]]

==Inventor(s)==

[[:Category:Chenyang Li of Bellevue WA (US)|Chenyang Li of Bellevue WA (US)]][[Category:Chenyang Li of Bellevue WA (US)]]

[[:Category:Hongli Deng of Bellevue WA (US)|Hongli Deng of Bellevue WA (US)]][[Category:Hongli Deng of Bellevue WA (US)]]

[[:Category:Gabriel Blanco Saldana of Kirkland WA (US)|Gabriel Blanco Saldana of Kirkland WA (US)]][[Category:Gabriel Blanco Saldana of Kirkland WA (US)]]

[[:Category:Joseph Milan Filcik of Redmond WA (US)|Joseph Milan Filcik of Redmond WA (US)]][[Category:Joseph Milan Filcik of Redmond WA (US)]]

[[:Category:Ryan Savio Menezes of Bellevue WA (US)|Ryan Savio Menezes of Bellevue WA (US)]][[Category:Ryan Savio Menezes of Bellevue WA (US)]]

==MACHINE-VISION PERSON TRACKING IN SERVICE ENVIRONMENT - A simplified explanation of the abstract==


This abstract first appeared for US patent application 17454786 titled 'MACHINE-VISION PERSON TRACKING IN SERVICE ENVIRONMENT

==Simplified Explanation==

The abstract describes a method for predicting the time it takes for people to move through a service queue by analyzing video footage. The method uses machine vision to identify people in the queue and estimate the average time it takes for them to cross a specific point in the queue. Based on this estimation and the number of people in the queue, the method provides an estimate of the total time it will take for everyone to move through the queue.

* The method uses video footage to predict the time it takes for people to move through a service queue.
* Machine vision is employed to recognize and track individuals in the queue.
* The method estimates the average time it takes for people to cross a specific point in the queue.
* The estimation is based on various features of the queue and the people in it.
* By considering the number of people in the queue and the estimated crossing time, the method provides an estimate of the total time it will take for everyone to move through the queue.

== Potential Applications ==
* This technology can be applied in various service industries such as retail, banking, and healthcare to optimize queue management and improve customer experience.
* It can help businesses make informed decisions regarding staffing, resource allocation, and customer flow management.
* The method can be integrated into existing surveillance systems or video analytics platforms to provide real-time insights into queue dynamics.

== Problems Solved ==
* The method solves the problem of accurately predicting the time it takes for people to move through a service queue.
* It eliminates the need for manual observation or customer feedback to estimate queue traversal time.
* By providing accurate predictions, it helps businesses optimize their operations and reduce customer wait times.

== Benefits ==
* The technology improves customer satisfaction by reducing wait times and improving queue management.
* It enables businesses to allocate resources more efficiently and effectively.
* The method provides real-time insights into queue dynamics, allowing businesses to make data-driven decisions.
* It eliminates the need for manual tracking and estimation, saving time and effort.


==Original Abstract Submitted==

A method to predict a traversal-time interval for traversal of a service queue comprises receiving video of a region including the service queue, recognizing in the video, via machine vision, a plurality of persons awaiting service within the region, estimating an average crossing-time interval between successive crossings, by the plurality of persons, of a fixed boundary along the service queue, wherein such estimating is based on features of the service queue and of the one or more persons awaiting service, and returning an estimate of the traversal-time interval based on a count of the persons awaiting service and on the average crossing-time interval as estimated.



[[Category:G06K9/00]]