Avigilon Facial Recognition 'Appearance Alerts' Tested

By Sean Patton, Published Dec 18, 2019, 11:00am EST

Avigilon has released 'Appearance Alerts' in ACC 7.4, which adds real-time facial recognition.

To see how this performed, we tested them with our H4A and H5A cameras and ACC7.4, examining:

  • How well does Avigilon face recognition work?
  • Where does it fail?
  • What limitations exist for face watchlist management?
  • What distance/PPF is required for face recognition?
  • What is the maximum angle of incidence it recognizes faces?
  • How well does it work in low light/IR lighting?
  • How much does it cost?
  • How much additional resource on the Analytics Server is required?

Appearance Alerts adds to Appearance Search, which we tested here.

Search ** ******

***** ********** ****** ****** for ***** ******* *************** like *****, ***, ******, age, ******, *******, ***., Appearance ****** **** ****** on ******* *****. **** can ** ********* ***** they **** ******* ******.

Notice: ***** ****** **** ******

***** *** ******* **** strong, ** **** ** emphasize **** *** **** on * ***** **** of ~** *****, *** less **** *** ****** test ******** **** * short ****** ** ****. Given ******* ****** *********** issues, ** ********* ***** scale ***** ** ******* larger, ****** ***** ** verify *** ********* ******.

Detailed ********** ***** ********

*** ******* ********** ******* positives:

  • **** *********** ********** ** ~90PPF:** ***** **** **** recognition ****** ******** ** ~90PPF ** ****-*** ******. This ** ***** **** many ***** ******* **** require ****** ** ******, but ******* ** **** we ***** *************.
  • ****** **** ***** ***********:** *** *****, ******** recognizes ***** **** ****** confidence ** **** ****** and **** **** (******* from * - **' high, *° ** **° down ****, *** * - **°). **** ******* it ** **** ** recognize ***** ************ ** targets ** **°************* ** the ******, ***** ******* Anyvision (********* ****** *********** ******) *********** **** **** **** Recognition ****** (******)*****.
  • ***** ******** **** **% Mask ********:******** ********** ***** **% obscured ** * ****. This ** *** ***** face *********** **** ** found ****.
  • ******** ******** ** ********** with ****/**********:*** ****** ******* *********** (e.g. ***, **********), ******** recognized ******** ******* ********** or * *** ** high **** **** (~**°) but **** ***** ********** settings, ******* **** ** the **** **** ****** a **** ** *********** at ~**° ** ******.
  • *** ***** ********* ** the ******* ***** ** incidence, *** ***** ********:*** ***** *********** ** solid, ******* ** **** light *********** ** ***** systems. ** ********** ***** at *********** **** **** angles (~**°) ***** ******* toward *** ****** *** only ****** **********. ** recognized ***** ** ******* walking ** * **° angle ** ** **° down ****. ****** **** light ***********, ** ****** recognize ***** ***** **°*************.

*******, ***** *********** *********** was *****, **** **** management ** ******* *** has ******:

  • ** ******** ****** *********:***** *** **** ** added ** *** ***** list ***** ***** ******* by ********* ************ *******, not ******** ***** ***** (e.g. ********). ******** **** they ***** ** ****** this ********** ** *** 7.6, *******, **** ** a *********** ********** *** early ******** *** **** to ***** *** * person *** *** *** been ** *** ******** location ***.
  • ****** **** ********* ****:** *** *.* **** 1 ***** **** ** supported, ***** ******* ** all ***** ***** ****** as * ****** *****. This ******** ***** **** creating **** ******* *** specific ****** **** ******* multiple ****** ** **** person, *******, *** **** images *** ********* ** one ****. ******** **** they **** ** ****** support *** ******** ***** in *** *.*.
  • ********* ***** *** ****** Allowed:** **** **** ** create ********* ***** ******* and **** ********* ******. Avigilon **** **** ***** be ********** **** ** a ****** *******.
  • *** **** ****** ****** Supported:***** ******** ********** **-*** PPF ****** *** *** Face ***** **** ********* images, ** ***** **** the ****** ******* **** lower ********** ******. ************, reference ****** **** * significant **** **** **** contains ******* **** ****** (e.g. *****, ****, **** not *******) **** ********.
  • ****** *********** ***** **** Beards/Face *********:** ***** **** **** faces **** ****** *** any **** ********* ******** in *** ****** ********* the ***** ** * reference ***** ** *** Watch ****. ******** **** that ********** *** ***** of ********* *** ****** for ********* ** ***** but *** *** **** any ******** ******** **** beards, ****** **** **** and **** ****** ** visible.
  • ** ******** *********:** *** *****, ******* photos ** * ****** of ******** ** ****** displayed ** ****** ******* could ** **** ** trigger *********** **** ********** nearly ** **** ** the ******* ********** ******** the *****. ******** **** they *** *** ***** the ********* *** ******** detection ******* ** ** not ********* **** *** access *******.

Comparative **** *** ******

********** ****** ** ********* compared ** *** ******* number ** ***** ************ NVRs **** ******* ****** recognition *** **** *** relatively *********** ******** ** Western ******** ********* **** routinely ****** $*,***+ *** channel.

********** ****** ******** * per-channel **** *********** ******* which ** $*** **** with * ** ******* minimum.

Face ***** ********** ****** *********** *** **********

*** ********* *-****** ***** reviews **** ***** **** management *** *********** ***** from ******** *****:

*** ********* *-****** ***** reviews *** ********** ****** and **** *********** ***********, examining **** *** *** performance ******:

Face *********** ******** ***** **** ***** ***** *****

** **** *****, ******** performance *** *****, **** high ********** *********** ** subjects, ** *********** ****** of **********, **** ** this ******* ** ~**° perpendicular ** *** ******:

**** **** *** *******'* face **% ******* **** a ****, ******** *** able ** ***** **** a **** ***** ** confidence:

** ***** **** ******** was **** ** ***** subjects ******* *********** (*.*. sunglasses, ****, *****), *******, confidence ******* **** **** to ****** ** *** levels:

*** *********** *** ********** with ***** **** **** capture *** * *********** down **** ***** ** well:

**** ** * ******* result **** ** ***** in ************ ****, ***** **** ********* well **** * *********** head ****.

*******, **** ***** *********** was ***** ** *** light *** ** *********** scenes, **** * ****** decrease ** ********** **** high ** ******, *** no ****** ****** ** incorrect ***************:

Face ***** **** ************ *** ********** ******

***** *** ** ***** manually **** ******** *****, which *** *** ** the ******* *********** ** noted ** *********** ********** ****** ****. ********** ***** *** no ****** ** ******** select ***** **** *** analytics *** *** ************* detect:

*** ****** ******** ******* is ***************, *** ********* the ********* ** ****** we ***** ** *** previous ****:

*******, **** *** ** confusing *** ***** ** there ** ** *** to ******** ****** ***** faces ***/*** *** *****, there ** ** ********** of ******* * **** is ** ** *** detected, *** ***** ****** be ***** *** *****. This **** ********** ** ** ********** parameter ** *** *******'* appearance, ******* ** ******** color, ******/***** *****, ***.

************* ******** ***** *** also ** ***** ** the **** ***** **** from ********** ******, ** was ********** *******.

* ********* ***** **** could ******** *********** ***** positives, *** **** ***** list ******* ****** **** limited **** *******, **** significant **** **** ******:

************, ** ***** **** subjects **** ****** **** more ****** ** ** rejected, ************ ** ***** mouth *** *** ******* or ********, **** ** the ***** *** **** face ******* **** ***-******* subjects:

******** ***** **** *** ideal ********* ***** ****** have ~******, *** **** eyes *** **** *******, and **** ************ **** be ********* ** *** 7.8 **** ******** ******:

********* *** ********* ***** and ********** ******** **** are *** **********

  • ******* ** (******* **) pixels ****** *** **** ear-to-ear *** ****-**-*** ** the ********
  • ***** **** ****** ****** not ** ********, ****** include *********, **** ***** above *** *** ** the ****, *** ****** have **** *** **** visible
  • *** **********, ***** ** a ********** *** *******-**** score ****. ** ******** to **** **** *** weighting ** **** *****. For ****.*, ******* ***** are ***** **** ******** video *** ********* ***** criteria *** *******. ** ACC *.*, ******** ********* images **** ** ********* to * ****** ******* quality *** *** ** will ******* * ***** image ******* *****.

******* ********** **********, *** Face ***** **** ****** duplicate ***** *** ****** to ** ******* ** the ***** ****:

******** **** **** ** ACC *.* ******** ****** of *** **** **** and **** **** ** prohibited.

Duplicate ****** *** ** ****** **** ****** *******

**** *** ****** ***** List *** ********* ***** supported, ** ***** **** multiple ******* ***** ** alerted ** * ****** appearance ** * *******:

**** ***** ** ** issue ** * ****** subject *** *+ ********* images ** *** ***** List, ***** ***** **** the ****** ****** ****** list ** *** ***** of ********* ********* **** a ****** **********.

Face ***** **** ****** ******* / ** ****** *** *** **** ***********

**** ***** **** ***** filtering ** *** ******** ACC ***** ****** ***** well, ******* ********* *** matched *****:

*** ******* ********** **** is *** ******* *** not ** ******** *** a ****** **** *****, so * ****** **** 1000s ** ******** *** day/hour **** ** ****-********* to ****** *******.

************, ***** ** ** function ** *** **** Watch **** ********** ****** to ******* *** *********** of * *******. ******** said **** **** ** added ** *** *.*:

**** ******** ** * real-time ********** ******** ** this ***** ** ****. In *** *.* *** will ** **** ** launch ********** ******** **** the **** ********* *** also ****** ****** ** launch ********** ********.

Comments (19)

***** **** ** ****** the *** *.* *** don’t **** ** ***** up ******* ******.

**** ** *******, *** need ** **** ********** Search ******* **** ****** GPU, *** ******** *** Face *********** ********.

****** **********. ***/***, ****** with *** *** **** Rec *******. **** *** is *** ** ****** yet ** *** ** Appliance.

****** ****!

*** ***** ** **** those ******* ***** ** his **** :)

* ***** ***: *** system ******** ****** ************ well ** ******** ***** a ***** ***** ***** be **** ** ********* the ****** ** *** picture. * ** ******* about *** *** ***** picture ** *** ***** where ***** *** ********* no ****** ******** *******. Considering *** (************) *** reference ******** ** ***** it **** **** *********.

**'* **** **** *** bad - ******** *** low-light *********, *** ****** that ** **** ******* with * **** **** here. ** *** ****** says "**** ** ***", but *** ***'* ********** present * *****/******** **** a ***** ***** ***** presented *** (**'* **** a ****** *** ****) - *** *** *** it ** *****?

* *** **** **** it ********** ********** ****, so *** *** ****** ever****** ********* ******, ** does ** ****** ******* the **** ******** ***** when ******* ***** **? E.g. *** *** ** people ** *** ********* database, *** ** **** were ***. **** *** of *** ** ***** by, **** ** *** "Oh, ****'* ******* ** don't ****" *** ***** that **** ****** (**********) if *** ** *** 30 ***** ** ** low *****, ******** ******, new ****-*** ***. ********* how ***** **** ** miss * *********?

** ***** *** ******** option? ** *** ****** says "****'* ***" *** in ******* **'* ****. Can *** **** **** the ****** "**! *** system. **** ** *** Rob!"?

* ***** **** *********** was **** ******, ********** considering (** *** *****) how *** **** ** the ********* ****** ****, on *******. *** *********** limitation (***** ** ***** Avigilon **** **** ***** be ****** ** *** of *** **** *******) is ********* ****** *** limited ** **** ***** capture ** *** ********* cameras, ***** *** ********** impact ********* **** ******* reference ******.

* ******* *** **** around ***** ** ** print *** ** ***** of *** *******, **** it ** ** ***** of *** ** **** cameras *** ******** ***** the **** **** **** image. ** *** *** test ****, *** ******** does *** ********* ****, I **** *** ** I *** *** **** to **** *****.

********* "******" ***********, ** a ****** ******* * person, *** **** *** not ******* ** * face ** *** **** Watch ****, *** **** the ****** ******** ***** is *********. ** * person ** ******** *** matched ** * **** in *** ***** ****, only *** **** ***** list ***** ** *********. There ** ** "*******" or "*********" **** *****.

******* ** *** ***** it ****** * *********, that ******* ** * couple *******. *** ******* match ********** *****, *** the ************* ** *** H5/H4 ****** ********* (****** ****), ***** ******* **** well. ** *** **** to ******* * **** or ****** ********** *****, to ***** **** ******** false *********, ***** ** our ******* *** ***** not ******* * **** match ***** *** ******* wearing * ****. *******, the ****** ** ***** detecting * ****** ** those **********, ** * "Person ********" ***** ** still ********* ** *** system. **** ** *** case *** *** **** capture ***** *** ******* confidence ***** ** *** met.

***** ** *** *** training *** ******** *****.

* *** ** * reference ***** ** *** holding *** ******* ***** as ** *** ** the ******* **** ** capture * *****, *****-****** image ** *** ** the ******. **** ** not * *********** ******** work-around, * **** ****** to *** *** *** system ***** ****** **.

** ******, ******** *** at * ****** ********** level:

*******, ** ******* ** a **** ********** ***** with * "****" ******** image:

*** *** ** ***** in *** ******* ********* image, *** ***** *** the ******* ** *** had ** ***** * reference ***** ** *** Watch **** *** ******* that *** *** **** captured ** **** *******.

*** *********** **** ***** now ** ** *** roadmap **** *.*? ** have ****** ** ********* as ** *** **, but ** *** ******** Avigilon *** ** *** same ***** ** ***** be ****** *****.

**** *** *** ******* to ** **** *** integration **** *****? ****, any ******** ** ******* Lenel **** *** ** get *** *** *********** your ******* ***.

********* ***** **** **** as **** **********. "**** at *** ****** ** unlock *** ****" **** of ****.

***** ** *** ****** standard ** **** ******** (at **** *****) **** looking ** ******** ****.

**** **** **** ** your ***** **** *** to ****** * **** that *** ******** *** use *** ******** *********. Other **** ****** *** grab *** **** **** your ******** ******* *** load *** *** ** an **** *** *** your ***** ****...

* ******* ********* *** that ******* ** * recall *********, *** **** point *** *******! *********, Avigilon ******* ** *** as ****.

*** **** ****** ******** only ******.

* *** **** *** my ****** **** * photo ** **** ***** turnstile ** ***.

* ******* ******** ***** this *** **** **** their ********.

******** *********, **** *** summary ** ***** ***********:

Video ******* **** ***** *******

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

  • **** ** * *** integration ******* ******** ******* Center * (***) *** later, *** ***** ******* 7.2, *.*, *.* *** 7.5.
  • ** ********* *** ******** functionality, ******** ****** **** the ***** ******* ****** to ** ********* *** recorded ******* *** ******, as **** ** *** ability ** *********** ******* individual ****** ** ***** control ****** **** ** the ***-****.

Video *********** **** ***** *******

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

  • **** ** * *** integration ******* *** *** system *** ***** ******* 7.2, *.*, *.* *** 7.5.
  • ** ********* *** ************* provided ** ******** ************, allowing ***** ** ****** ACC ******** ****** *** OnGuard *********. ***** *** view **** *** ******** video *** ******, ****** video, *** ******* *** devices *** ******* ********* events ********* ******** ***** through *** ******* ********.

*** ** **** ** you **** ***** ******** integration ******* *********.

****, ****** *** ******* that ** ****! **** replied ** ******* ***** that **** * ** really ***** ** ** there **** ** *********** with ***** **** ****** Avigilon **** *********** ** unlock ***** ****** *****.

******* ****** *** **** that's * ***** ******* is *********:********* ********* *** - Lenel.com

** **** **** **** with ***** ***** ******* or **** ******** *******?

Read this IPVM report for free.

This article is part of IPVM's 6,651 reports, 895 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