Qognify Suspect Search Examined

By Brian Karas, Published Jul 01, 2016, 09:25am EDT

All you have is a description of a suspect? White guy, black hair, mustache, heavy, green jacket?

No problem, says Qognify, formerly NICE Security. They say they can search for any such combinations without even a picture or video clip of the suspect.

In this report we examine Qognify Suspect Search, its functionality, practicality, pricing and comparison to rival offerings including Avigilon appearance search.

Suspect ****** ********

******* ************ ******** ** ****** ************ the *******, **** ** details **** ***** *** jacket *****, *** ******** a ***** ****** **** this ****** ***********. ******* says their ***** *********, ***** analyze ***** ** **** time *** ***** ******** meta-data ** *******, *** return ******** ******* **** a ****-******* ******.  

************, ** *** **** already *** ** ****** image ** * *******, the ****** ******** *** be ******* *** *** search *** ** ********* from *** **** *****, though ******* ****** ******** the ****** ** ***** often ****** **** ******** video **** *** ******* clearly ********.

*******'* ********* ***** ***** an ******** ** *** concept:

Building ** ******

*** ********* **** ***** an ******* ** ******** an ****** ** ****** from: 

***** *** ********** *** major ***** **** ***** and ******* ** ******, as **** ** **** more ***** ***** **** shoes, *******, ******* *** bags.

Searching *** ********

*** ******** **** ****** through ******** ***** ** analytics-enabled ******* *** ****** results ****** ** ***** of ******* ***** *****.  If ** ****** ******* is *****, *** ****** representation ** *** ******* can ** ******** **** an ****** ***** ** the ******* **** *** video, *** **** *** search **-***.

Only ******* ** ******** *****

******* ****** **** ***** on ******** *****, ***** is ** *** ** setup * **** ***** for * ******* ******** being *******.  ***********, ** takes * *** ******* after *** ********** ***** has **** ******** ****** it *** ****** ** search *******.

***********

******* ****** ********* **** been ********* **** *** results, ****** ** ******* **** the ****** ** ********* using ******* ****** ** ***.

*** ****** ******** **** used ** *** **** above *** **** ** actual ****, *** *** results ******** (***** ******* would *** ***** ** to **** *** ** customer-identifiable *******) ****** ******* of * ****** ******* to *** ******, ********* a ******** ***.  *******, these ******* **** ****** the ****** ** ****** full ****, ************ ** other ****** ** *******, in ****-*** ******* ******.  It ** ******* ** the ****** ***** **** been ********* ********* ** a ******* ***** ** an ******** ****.  ************, a ****** ** ******* returned ****** ******* ******* a ***, ** ******** a ***** *******.

Technical **********

******* ******** *** ********* **** details:

  • **** ********* *****, ******* ***** and ******* ******. ***** people *** **** ******** based ** *****, ******* and ***** ********, ******** people ** ** ******** and **********.
  • *** ******* *** ***** to ** ******** ** ~10 ****** ***** ** their ******** ***** ** to **** **********.
  • *** ~*** *******, **** would ******* ** ********** server **** ** ***** (2 ****, * ***** each) *** **** ***.
  • **** *** ** **** with *** ***** *******.
  • **** ******** ***** ****'* video ********** ******** / system *** ****** ** 'added **' ** *** party *****.

Limitations With ******* ******

  • ***** *** *** ****** very ******** ****** **** shoes ** ********** *** ****** these ******* ***** ******** ****** *** search ******* **** ***-********* video ***** *****.
  • *****-***** ********* ******** **** lighting, *** ******* ******** for ****** ***** ******* to ******* ******* *******.  This **** ******* ******* any **** * ****** has ******** ** */* mode ** *** *****.
  • *** **** ******* ****** views/angles ***, *** **** likely ******* **** ** accurate.  ****** ****** **** 180/360 ******* ***** **** not ****** ******** *******.
  • ***** *** ****** * very ******** ******, *** if ***** ******* *** not ********** ******** ** the ******* ** *** negatively ****** *******.  ** the ****** ** **** to **** *** * person **** * ***** and *******, *** ******* only **** ******* ******** detail **** *** ***** the ****** ** **** or **-********* ********* ******* that **** ***** ******* on *** *********.
  • ******* ****** ** **** valuable, *** ****** ** be ***** ********, ** large ******* ****** (** there ** **** ****** activity ** * ****** a ****** ****** ****** will ****** **** **** enough). ** ***** ******* goes **, *** ******* that ***** ******* *** returned, ** *** ******* is ******** **** **** by ***** ****** ** the *****, ********* *************.

Price *** ************

********* *** ********* **** enable ******* ****** ** $900 ****, ** *** of *** **** ******* for *******'* ***. **** puts ******* ****** ** *** upper ******* ** ********* license *******.

Compared ** ***** ********* ********

****** ** *** **** we **** ****** ** supports ********* ***** ** avatar ********, * ****** of ********* **** ***** of ********** ******:

** ***** *** ****** similarity ******** ***** **** to ***** *** **** they ****. ********, ***** does *** ** ****, is **** ****** ** its **** *********** ***** synopsis / ****** *** requires **** ** ******* and **** ** ***-**.

Outlook *** ******* ******

*******'* **-**-****** ******** ******* ** large ** **** ********. ***** that, ******* **** ** bad ** **, ** do *** ***** ** will **** * ***** industry ****** ******* ** the ******* ********* ******* aims ** *****. 

** *** ******** ****, this ***** **** ******* distinguish ****** **** ****** for ***** **** *****, price *********** ********.

Comments (1)

Has anybody used this technology in the field? Can you share your impressions?

Read this IPVM report for free.

This article is part of IPVM's 6,817 reports, 914 tests and is only available to members. To get a one-time preview of our work, enter your work email to access the full article.

Already a member? Login here | Join now
Loading Related Reports