Carnegie Mellon AI Startup Zensors Profile

By Sean Patton, Published Jun 11, 2019, 11:40am EDT (Info+)

Zensors is a startup formed by Carnegie Mellon graduates from a Carnegie Mellon research project, offering customized models per camera that they claim delivers significantly higher accuracy.

We spoke with Zensors to better understand their approach, how they plan to scale their system and their go-to-market.

In this note examine:

  • Who is Zensors
  • What Customers is Zensors Targeting
  • How Much Does It Cost
  • What is Zensors' Go-To-Market
  • What Type of Analytics
  • How Do They Generate Custom Datasets
  • What VMS Integrations

Zensors ********

******* ** ****, ******* *** ********** a ******** ******* ** **-************* ****************** ****. ******* ******* ** ********* ** Pittsburgh *** *** *********, ********* ******* development ******, *** * ** ****** contracting **** ** ***** *** ******* labeling. ******** ** ** ********* ********* of *****-******** *********** ** ******** ****** University, ********* ***** ****** ********** *****, while **** ****** * ******* ****** in *****-******** *********** ** ******** ******, as **** ** ********** ******* *********** and ** ** ******** ** ********.

******* ******* $*.* ******* ** *******. They *** *** ******** *********, *** they *** ******* *************, *** *** * *********** **** DHS, *** * ****** *********** ****, ******* ** ***** **** ********** investments.

***** ********* **** ******* **** *******

******* ** ******** ***** **-***** ***** analytics **** **** ******-********* ****** ******** that *** ********* ******* ** ****** people *** ********, *** ***** **** 500 ****** ** ******* ********* *** available.

******* **** **** ***** ***** ****** to *** ********'* ******** ******* ** generate ************ ****** ***** ** ****-***** video (*.*. ****-**** **** ********, ******* tracking, **** *********). ****, **** ***** they *** ********** ****** ******** ** analytics, ***** ** ****** ***** ****** verticals (*.*. ***** **** *******, ************** Terminals).

**** *-****** ********* ***** ***** ******* people-counting *** ***** ********** ** ****:

One ***** *** ******

******* **** ******** ****** *** ******* and ********* *** ******. **** ** atypical **** **** ***** *********, **** AI-based ******, ***** *** ******* ** public ** ****** ******* **** ** images ** ****** *** ******** ******* (for **** ******** *******, **** ******** ******** ******** *** ***** ************). ******* ****** **** *********** ** models **** *** **-**% **** ******** and ******** ******** **** **** ********, night ****, *** ****** *********. **** noted ***** ** * ******** "********" neural ******* ***** *** ***** ******** per ****** ** *** * "**********", and ******* ** **** *** ******* as **** ********* ** ******** *** entire ****** *******.

******* **** ******** *** ******** *** created ***** ******** ********* ***** *******, customer ****** ***** *** ****** ****** from ******* ******** ** ***** ******** sites.

****** ********* ** ****** *********

******* ****** * *** ********* *** event *******, ********* *** ****** ************. Their ****** ** ****** ** ***, and ***** ** *** ** ********* on-premise, ******* **** **** **** **** deployed ******.

******* **** ***** ********* ** ******** to ***** **** *****, **** ** digest ****** ** ***********, ** ******** the ***** ******** ****** ** ****. To ****** *** ******, * **** asks * ******** (*.*. "*** **** cars *** ** ****?", "*** **** people *** ****?"), *** *** ********* specific ***** ** *** ***** ** search:

**** ** ******* ** ************* ******* by*****'* ******* ******** ********** (**** ****). *** ******** *** ** ******** into **** ******* ***** "********* *****" Reports, ***** ******* ********** ********* ** the ****** ** ******* ******* *******:

** **** *********** ** ******* ********

******* **** **** ***** *** ** develop **** *********** ****** ** ****** classifications, *** ******* *** ***** ********. They **** **** ***** ********* *** not ******* ** ******* ******* ********* (e.g. ******* ********, ******* ** * library) ** *******, *** ******* *** customized ****** ******** ** ******** ******* behaviors.

Targeting ***** ******, *********, ***** **********

******* **** **** *** ********* ***** city ********, ************** **** (*.*. ********, train *********), *** ***** ********** **** large ******* ** ****** *** ******** (e.g. **** ******** *******, ***** ******* garages). * ************** ****** ****** ** the ******* ** ******* ******* ******** modeling, ***** **** **** ****** **** to ********** ****** ********, *** ******** the ***** ** ********. **** **** they **** ********* **** ***** ********* for ***** ******* ************, *** ****** and ******* ********.

******* ****** ** ******* **** **** mounted * ** ****** ****** **** an ********** ******** *** **********, ********* used ** **** *******, ***** ***** $1,500 - $*,***. **** **** **** are ***** ** * ***** ******** in **********, **** ***-***-***** **********.

Per ****** *** ***** *******

******* **** **** ******* ******* *** standard ******** ****** (*.*. ****** *** vehicle ********) ** $** *** ****** per *****. ************* *** *** *****, so * ****** ****** ******** ****** and ******** ***** ** $** *** month. ******* **** *** ******, ********** behavior-based ****** **** $** *** ***** per ****** *** *****. **** **** said ***** *** ******* ***** *********, which ****** ** *** ****** ** processing ********, ***** ** ***** ******** and ******** ***** **********.

3rd ***** ****** *******, ********* ***** *******

******* **** **** ******* *** ***** cameras ***** ******** ********* (*****, ****, FTP ********), *** ********** ** *******. Atypical *** **** ***** *********, ******* said **** ** *** ******* **** fps, *** ***** *** ********** (*.*. people ***** ********), * ***** ***** 10 ******* ** ******. ******* ******** and ******** ***** ********* ******* ****** frame *****.

** ******* ******* ** ******* *******, they ******* ** **-******* ******* **** 6 ****** ** ****** *********.

Direct ***** *********, **** ** *** ****

******* ***** ****** ** *** ***** but ***** **** *** ******** ** build ** ********** *******. **** **** that ************ ** *** ***** *** integrators ** ***** ******* ***** ****, but **** *** ********* ****** * sales ***********/******** *******,** ******** ** **** *********** ********* and ***********.

Only *** *********** - **********

******* ***** ***** **** *** *********** is ************** ************ **** **** ***** ** ********** more ************ ** **** ** ***** development *******. ************, **** **** ****** integrations **** ***** ********** ** ******** connect *** **** ********* ****** **** the ****** ** ****** *******.

Potential **********, ** ** ****** ***** ****

***** **** ******** ****** ** * leader ** ** ********, ** ******* that *** ********** ** ******* ****. The ********* ** *** ** **** it ** *** ***** **** ******** market **** *** ** (** **** a ****** ********? ***********? **************?). **** advanced ***** *** **** ***** ** a **** **** **** *** **** do ****** **** *** **** (******* example****** ***** **** ****** ********* ****). *******, *********** ********, **** *** benefit **** * **** ****-*** *********** specific ******** **** ** ****** ** understand *** ** ****.

Comments (1)

John Honovich

IPVM | 07/31/19 06:29pm

Update: Pittsburgh International Airport Partners with Artificial Intelligence Startup Zensors to Provide Live Accurate Wait Times for TSA Lines

From their press release, an image demonstrating it in action:

Agree
Disagree
Informative
Unhelpful
Funny
Login to read this IPVM report.
Why do I need to log in?
IPVM conducts reporting, tutorials and software funded by subscriber's payments enabling us to offer the most independent, accurate and in-depth information.
Loading Related Reports