Verkada People And Face Analytics Tested

By: Ethan Ace, Rob Kilpatrick, and Sean Patton, Published on Aug 16, 2019

This week, Verkada released "People Analytics", including face analytics that they describe is a "game-changing feature" that "pushes the boundaries of enterprise video security".

To see how these new analytics perform, we tested them with our Verkada D40 Minidome, examining:

  • How well does it detect people?
  • How well does it analyze clothing color?
  • How well does it identify male and female appearance?
  • How well does it detect and analyze faces?
  • What distance/PPF level is required for detection?
  • Does it incorrectly identify vehicles/animals as people?
  • How well does it perform in low-light and IR illuminated conditions?
  • What Verkada cameras support this feature?
  • How are people analytics enabled and configured?

**** ****, *************** "****** *********", ********* face ************* **** ******** ** a "****-******** *******" **** "pushes *** ********** ** enterprise ***** ********".

** *** *** ***** new ********* *******, ** tested **** **** ********** *** ********, *********:

  • *** **** **** ** detect ******?
  • *** **** **** ** analyze ******** *****?
  • *** **** **** ** identify **** *** ****** appearance?
  • *** **** **** ** detect *** ******* *****?
  • **** ********/*** ***** ** required *** *********?
  • **** ** *********** ******** vehicles/animals ** ******?
  • *** **** **** ** perform ** ***-***** *** IR *********** **********?
  • **** ******* ******* ******* this *******?
  • *** *** ****** ********* enabled *** **********?

[***************]

Strengths *******

*** ********* **** *** strengths:

  • ****** ********* ****** ******** in *** ******** ********** tested, ******* ****** ***** alerts ** ************ ******* such ** ***** *******, shadows, *******, ***. ****** detection ****** ** ** ~25' **** **** *** camera ** ~** ***, which ** ************* *******.
  • **** ********* ****** ******** in *** ******** **********, including ********** **** / sharp ****** ** ** ~8-9' **** *** ****** or ~*** - *** PPF, ***** ** ************* limited.

** ******* *** ***** analysis, ***** ********* ****** well ** **** *****, though ******* ********* *** clothing, ***, **** ** on, ************** ***** *** lack ** ***** ********, identified *** ******* ** white ** ****.

Weaknesses *******

*** ********* **** *** most ******* **********:

  • ****** ********* ****** ******: males **** ********** ******* as "******* ******"
  • ****** ****** *** **********, recognizing *** ******* ** multiple ****** ****** *** falsely *********** ******** ******.
  • ******** **** ********* ******* categorized ** ****** ** People ****** *******, **** though *** ****** ********* identifying *** ****** ** a *******.
  • ***** **** ** * single ****** ** * time. *** ****** **** not ******* ******* ****** or ***** ****** ******** cameras.
  • ******* ** ********* / identifying: ***** ** * significant *** ** ********* processing, *-******* *** ****** detection/search *** **-** ******* for **** ***********.
  • ***** **** ***** *********, when ***** ********, *** broken. ******* ******* ***** body ***** ******, ** is *** ********** **********.

No ********** *********

***** ** ** ********** charge ** ******** ** license ****** *********. *** the * ****** **** currently ******* ****, ******* have **** ***** ** enable ****** ******* *** Face ****** *** ******.

*******, *** ******* ***** these ************ (******* ***** or ************) *** ***** that ** ********* ****** a ******* *** ****.

Competitive ***********

**** ************* ******** *******'* competitive ***********. ***** ***** are ********** ******** *** some ************ ******* **** that ****** **, ******* is *** ****** **** accurate ****** *** **** detection *********, ***** ********** into ***** '***', ********* that **** *** ******* offer *** ****** ****** at * ******* *****.

***** *** **** ** tempted ** **** ******** or ******** *** ****, this **** ******* ****** selling ****** ******* '*******' NVRs ** **** ** mid-market ***** **** ***** and ********* **** ****** do *** ***** **** features ** ******* *********** cost *** ********** ** add.

*******, **** ** * good ************* ** *** advantage **** ***** ******* bring. *** ******* ******** immediately *** **** ******* by ****** ******** * button **** ** **** to ******** *** ******** or ********, ******** *******, etc. ********, **** *******, Verkada *** **** ******* analytic ************ ** *** customers *********, ****** ********* fixing ***** **** **** were *** ****** ** QA.

People ********* ***** *** **** ********

*** ********* *-****** ***** reviews *** ***** ***** for ****** ********* *** Face ******:

*** ********* *-****** ***** overview ******** ****** *** Face ****** *********, ********* good *** *** *********** of ****:

Upper **** ***** ****** ******** *******

****** ********* ****** ****** filters *** ******** *****, with ******* *** ***** and ***** ****, ** found **** ***** **** color ****** ********* *******. There *** * ***** options ** ******.

** ********* ****** ****, though, **** **** ******* for ***** *** ****** wearing * ***** ******** were ***** ** ********* black, *** *** ***** of *** ***** **** were *******.

Lower **** ***** ****** ********* ****** / ******* ****

******* ********* ***** *** an ***** **** ***** body ***** ******, *** it *** ***** ****** 24-hours ** **** ********* them. ** ********* ***** that *** ***** **** search *** *** ****** any *******:

*** ** ** ********** accurately, **** ******* ***** limitations ** ***** **** color ******:

Ignores *******, ******** *******, *******

******* ****** ********* *** not ******** ******* ** people, ** ***** ** have ***** ** ***** analytics ***** (*.*.***** *********+ ******):

** **** *** *** find ***** ****** ********* issues (*.*. ****** *****, shadows ** ***** ***** changes) **** **** **** outside ** ** ***** spaces:

Detects *** ********** ****** *******

****** ********* *** ************ accurate ** ********* *** identifying ******, **** **** running ******* *** ***** of ****:

Vehicles ********** ** ******

****** ********* ** **** supported **** * ******* indoor *******, *******, ** found **** ******** **** consistently ******** ** ****** searches. **** **** ***** significant ***** ********* ** the ****** ***** ** view ******** ******* ** doors **** ********** ** a **** ** ******* lot:

** ***** **** *******'* camera-based ****** ********* ********* do *** *********** ******** as ******, **** *** cloud-based ********* **** **** issue.

Males ********** ** ********* ******

****** ********* **** ****** a ****** ******, ***** incorrectly ********** ***** ** Appears ******:

************, **** ****** **** identified ** **** ******* Male *** ******* ****** depending ** *** ***** of ***** *******. ******* said **** **** ******** to ****** *** ***** to ******* ********.

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

***** ******* ***** ** testing, ** ***** *** issues **** *******'* **** search.

*****, ******** **** ********** added ** *** ******** as ******** ****** ***** instead ** ***** ****** into ***. *** *******, in *** ***** *****, the **** ****** ** shown ** ** ****** subjects (*********** ** ***).

**** **** ***** ********** does *** ****** *** same ***** *******. ***** clips **** ********* ***** are ***** *** ****.

Verkada Displays Same Person As 10 Different Subjects

************, **** ******** **** incorrectly **********. *** *******, clicking ** *** ****** returns ********* ******* *** 5 ********* ******:

**** *** *** ***** with **** ********, *** occurred ******* *****.

Feature ******* ** ******* *** *** **** *******

****** ********* ** ********* by *********************** ****-**** *******, *** Verkada **** ** **** a *********** *********** ** on-camera *** *****-***** ********* to ******* ****** ******* identification *** ********* ** well ** **** ******.

*** ********** ***** ********* on ******** ******* ** atypical *** * ****** or ***** ********* ************, and ** *** *******, Verkada's ********* ********* ***** average ** ** ******* environment.

Search ******* *** ******

****** ********* ****** ** per-camera, ******* ****** *** faces *** ********** ** a ******** ******, *** searching *** * ****** or **** **** **** show ******* **** **** camera. **** ** * significant ******* **********, ******** to******** ********** ******, ***** ******* ******* from **** ******* **** a ****** ******.

Comments (55)

"**** ***** **** * lady" -*********

***** **** ********** ** a **** **** ***

  • ... ***** **** ********** labeled ** "******* ******"
  • ******** **** ********* ******* categorized ** ******...

*** *** **** ******* model# *** ******? ******* :)

* ****** *** *** joking, *** *** * serious ******:

***** ** ** ******* model # ***********, ** asked ******* ** **** have ******* ******* ********* (e.g. ***/*****/***, *****, *****) on ***** *******. * will ****** **** **** we **** ***.

**** ****** ****.

****** **** ****** *** by ********** ******** ***** referred ** ** *****?

"**** ** **, ************** given *** **** ** color ********, ********** *** objects ** ***** ** gray."

***** ******** ****** **** been **** *********** **** using ** - *** they ******'** ***** * pop-up ******* ******* *** user *** **** ** idiot ***** *** *** use ** **** ** is **.

**** ** **********, *** users ***** ****-**** ****** rec. *** ***** ** find *** ** ******* later **** ***** ** someone ** *** ********* inside?

* ******* *** **** thing ** *****....

*** **** ******** ** a ******** **** (*.*. using ******** *****) ** using **** ***** *** databases ** ******* ********* via ***** **** ***/** inclusion *** ***** ****.

* ***** **** *** users ******* **** **** value ** ****** ******** rather **** ********* *** it ** **** / less ********* ** ***** searching, ** ** ** a ******* ***** ****.

* ***** ******* ******* eventually ******** ****-**** ** an ****** / ******* feature.

*** *** ** ******** a *** ***?

****** ******* ******* ******** link

*** **** ****, ** can **** ******** *** a ******

****, * **** **** test ******* ** *** way, **** ** **** to ****. *'** **** some ******** ***** *'** tried ** *****/************ ****** them.

**** ****** ******** **** gender ********* ** **** day *** *** ****** so *'** **** **** a **** ** **** one

** *** ** **********...

*** ** *** **** out ******* ***'** *** or ******** **** * photograph

*** ** **** **** it *** ** **** a ******* ***** **** a ****-******...

*** ** ****** ********* socially **********? *******’* ** be ******* *** **** as ****** *********?

***** ** ** **’* less ** ** ******* issue, ***** *** ******** of ** ***** **** your *********** ****** **** gender, *** **** ****. Nothing ***** **** ***** non-binary ** ******** *** term ***’** **** *********** with **, *** ***** we *** *** **** more ******* ** *** forms, *** ******* ****** out ** ***** ******* out ** **, ** just ** **** ** is.

***** ** ** **’* less ** ** ******* issue, ***** *** ******** of ** ***** **** your *********** ****** **** gender...

“*********** ****** ****” ********* as ****, **?

“*********** ****** ****” ********* as ****, **?"

* *** **** *****, but *'* ******* ***** the ******* ******* ****. The ******* ********* *********** the "***" **** ***'** interested ** ********* *** far ******* **** **** you're ****** ****** ** get ****/****** ************** *** various *******.

*** *******, **** ***** is ***** **** ********* to ***** ****** ******** activity ** ******* ************, but ******* ****** ** say ******* * ******* is **** ** ****** so *** ****** *** track **** **** ** not **** ***** ** being *** **** *****.

****** **** **** **** valid ****** ***** ***** this **** ** ******** in * ****** ******* in ***** ** ******** product ******** ** * specific ***********, ***** ** also * *** **** with *** ******* ******, at ***** *** ** many ** *** **** thing. ** ***** ****, you *** ****** *** shop ** ****** **** video ************. *** ****** I *****...*** ** ******, they ***** *** ** you ** ***** *** ways.

******* *** ****** ********** don't *** ****

*** ****** ********* ****, it *** * *** of ***** ** ** for ******

********* ** **** ********* Data, **?

**** *********** ** ****** and *********** ******** ** marketing *********** *** ********** controls.

"*** ****** ********* ****,it *** * *** ** ***** in BI for Retail"

* **** **** *** the **** **** *** sales **** ** *** industry... *** * ** still ****** ******* ** the****** ******* ****** *********.

**** ******* *** *** capture **** (**** *******, people ********, ***) **** not **** **** **** data ************* ********** ** actionable **.

****** ************* ** ******* (and *** **** *** a **** ****) ** actual ********** *****. *** can *** * ******* degree ** **** *****.

********* (********** *****, *****-********) do *** ***** *** position ******** ***** ** guessing. *.*. *** ** produced ** ******* **** retail ********* ** ******* already *****.

** ** ** ******** that *** '******** ****' captured ** ******* (**** analytics) ** ******** ** best - *** *** cost ** ***.

*** *** ******** ** the ******* ** *** cost *****, ****** * read ** *****

******** ** *** ******* do *** **** *****

*******, ****** ******* ** not ********* **** ** a ****** ********* ********. Of ******, **** ***** at **** *****, *** for ***, ****** ******* retail ********* *********, **** is * **** *****.

** *** **** *** cameras **** ******* ***** new ******** ********* **** buying *** ********.

***** ****? ****** *** Frame? ***** **** ****** use ******** ** ******* their ******* *** *******, it ******* * ********* block ** * ***** readership. * ******* ****** defining ** ******* ** it's ***** ******** ** any *******. **** *** you ***** * ******* audience *** **** ******* those **** ******** **** current ********.

*** *** / *** Video ************ *****

**** **** ** ** fundamental ** ***** ************ we ** ****** ** to ** ***** ** someone *** ****** *** it ** ****. *** sure, **** ****** **** not *** ******* **** is * ********** **** for ***** ************, ** tend *** ** **** to ** ******* *********** terms. ** **, ** course, **** ********* / training ******** **** *** guide *****.

** ***** * ****, e.g. ******** ** **** (and * ****** ****** what **** ****** ***, but * **** ** when * *** **) terms, **** *** *** your *********** ***** *** expect ** **** ******* so * ** *** have ** **** ******* reference/training ********? * ********* to **** **** ******* it's ** *** ******* edge *** *** ***** interests **; * ** not **** **** **** area *** ** *** day ***. ** ***** be ******* ** **** a ****** **** * can ***** ** **** acronyms *** ******** ** if *** ****** ** not ** ****** ** acronym ** *** ***** usage.

**** **** **: ****** Per **** *** * do *** ****** ******* it, ****** * *** have ***** ***.

***** * ** *** disagree **** **** *******, if *** ***'* **** what *** **, *** does *** *********** ** the ** (******** ****) make *** ***** ** all ** ***?

...** ***** (******** ****)...

***** (************* ******** *** Regressive ********** ;)

**** *** * ******* question - **************** ** ************* ****** fashion.

************* ************ ** ******** before *** *** ****** understand *********... **** *** choose **** ****** **** that *** *** ** particular ***********.

* ******* *** ******* who **** ** ***** the ************ ** *** industry - **** **. Poole ******* ** ** doing...

* ***** ******* **** anyone ** *** ******** enroll ** *** **** (IP ***** ******) ****** Course - ** ** least ***** *** ********* IPVM ************* **** ** used ** **** ******.

** **, ** ***, the **** ************* (*** up ** ****) ******** you *** **** ********.

***** **** ***, *** wonders **** **** *****. Gets ** **** ** make ****** **** **** friendly. *'* ******** **** an ********* ****** *** process *** **** *** add * ****-*** ** common ***** **** *** or *** *** ** immediately ********** ** *********.

****: ** *** ***'* know *** *** ******** don't ********** ******** ***** any ** ****, ****** enroll ** ** **** course.

* **** **** **** is * ***** *** the ********* **** ** video *****, *** ***** with * ****** ****** mere ****** ***** *** an ******** ********** ******* signing ** *** * course.

"*'* ******** **** ** automated ****** *** ******* the **** *** *** a ****-*** ** ****** terms **** *** ** may *** ** *********** recognized ** *********."

**********, * ****** **** links ** '******' ***** within ********** - ** I ********* *** ** mouse ** ****** **** I ** ******* *** these ***** **** ** hijack ** **** ******* with ***** ** ****** I ***'* ****.

*******, ***** * **** pinned ** *** *** that ***** *** ***** and ****-** ***********/******** ******** used?

"***** **** * ****** effort **** ****** ***** get ** ******** ********** without ******* ** *** a ******."

*****. **** ** *** I ********* ** *********** - ***** *** ********* documentation ** **** ***** covers *** ******** ** the ******* **** ** their *******.

*/* ******* ***** ***** some ******* **** *** best *** ** ****** this **** ** *****.

** * **** ****, some ***** *** **** to ****** ******** ** metric ********** ** ** option ** ** ** spare ******* ** **** advanced ************* **** *** unbearable ***** ** ******** exposure ** ***** ****** medieval *****.

*'* * ****** ********* at *** **** **** performed ** *** ****. I *** **** * few ** ***** ******* for ******* *** ****** ago *** ******* **** there ***** ******* *** below ******** *********. ***** inability ** ***** ** scene *******, **** ******* a *** ****, *********** disqualified ***** ******* ** many ** *** ******* we *******. ************, ******** was ** ***** ****** the *****.

**** ***** *** ****, when * ***** ** their ** ********* * thought ***** ***** ******* would **** **** **** the ********* ***********.

*** **** ********* *** articles ** *** ***** quality ******* *********? ***** I've ************* *** ********** work. * ****** ******* it *** * *** of ****** ** ****** or *** *** ***** quality.

** *** ***** ** ***** ***** quality (****)*** **** ** ***** agrees **** ***. **** were ******* ****** *** day, ***** *** ********* at *****, *** *** trails ** *** ******.

**** *********, ***** ******* impact ** **** *** is *********** ***** ** come **** ** ******* enough ********** ** ********* at **** **** ******** and ********. ** *** of ***** *** * problem, *** **** **** appear ****** *** *********** will ******.

****, ** ** *****, in *** ***** *******'* facial************ ********, *** ** short ******, **** *-*' from *** ******, ***** was ~*** ***, ***** is ****** ****. **** is *** ** *** that *********** ***** ** that *****, ** *** camera ********** *** *** catalog ***** ****, *** we *****'* ********** **** specifically.

****** *** *** **************. May * *** *** they ********* ** **** environments? **’* ** ************* that **** ***** *** cause * ******** ** PPF **** **-**%.

* ***** *’* ***** to *** **** **** product ** ** **********, I **** ****** **** in ** ********’* *******. In ** **** ** aren’t ***** *******. ** they *** ***** ****.

*****,

* ***'* ********** **** original *******:

"* ***** *’* ***** to *** **** **** product ** ** **********"

***** * **** **** pound **** ******** *** it's ********, *** ****** even ******* ** ** customer ***** ** '*******' against * * ************ playing ******* *** *********** channel?

*** *** ****** ***** your ***** **** ******** without ******* **** **** showing ** ** *****... unless ***** *** *** just**************** **** ***** **** ?

*****, * ******* *********** for **********. * ***’* expect *** ** ***** with ** *** ** any ***** **** ** the *******, ******** ** is **** *** **.

** **** ** ** all “****” ************* *** we’ve ******* ** ****** our ********* **** ***** and ****** **** ******* product ** **. ** turn- * ***’* ********** this **** ** **** comment, ** ******* ***** day *** *** *** to ****** ******** *********.

*** *****,

**, *** ******* ** a ** ********** - it **** ****'* **, but * **** ******* to ***** ** ** your ************. ****** ****** my *********** *******.

* ***** **** *** should **** ** *** any *********** ********* ***********.

*** ****** ** ***** a ******* ************* ** where ********* ********* ***** judgements ****** ** *** food ***** ** ******** (imo) ** ******** ********* wasted ******* **** ******* up ** *** '*****' hosted ** ********.

***** ** ***?

* *****? * **** don’t *** *** *** local ***** *** ******** in **** ******* ** a ******** ***** *** curtain *** ****** ****. I’m ********* *** ********* in **** ******** ****’* relative ** ** ********. No, ** *** ** going ** **** *** the ****** * ****** camera ***** **, *****? If *** **** ****** I *** *** ***** that *** ******** ** a ***** ****, ****** buying **** ** *** or ***- *’* ***.

* ** *** ****** to ** *************... ******* that ** ***.

* ***** *** **** to ** ******** ******* that *** ***** ** your *** *****:

"* ***** *’* ***** to *** **** **** product ** ** **********"

* ***** ** *** understand *** *** *** happy ***** *** *** moves ****** *** ******* - **** **'* ***** that *** *** ** industry ************ **** *********** the ******** ** **** channel.

*****,

* ********** **** **** a **** ***** **** of *********** ************ **********. Neither *** ***** ****** I ***** ** *** her ******* ********** ***** concepts **** ** *** or **** ***.

***** ******* ***** ***** relies ** ***** ******* to ***** ******* *** image *******. * ******* it *** *** ********, however **** *** ******* of ***** ****, ***** old ******** **** **** you *** * *** doing ** *** ***** way.

**** ******* ****, ** friend!!

*’** **** *** * call ***** ** *** week ** *****-**.

****

****, **** ***’* *** is ******* **** ** NI ****** *** *** Cisco *****. *’** ***** with **** *** ** years *** **** * could **** *** ***** they **. * ******’* be ********* ** * knew *** *** **********, he ******* ** ** one ** ********** ***** regional ***... ***

*** ******** ** ***** specialized ****** *** **** demand ********* ** **** us. **** * **** it ** *** *** connect ****** ******* **** 80% ** **** ** the ******** ********* ** out *****? *****. ***** out *** *** *** and ***** ***’* *** can *** ******. *** we ***’* ******* ** for ****. *** ****** else *** **** ***** DCJS ** ******* ********* to ******* ** ** a ****. ****’** ** it ** ***** ***.

*** *** *** * new ****** ** *** household, **** **** *** talk ** *** ****!

* ******** ** **** cameras, *** ** **** of *** ****** **** offer. ****'** **** ******* in ** **** *********** for ***** * ****, and *'* ****** ********* with **** ** ***.

* *** **** ****** w/ ***** ****** ** first, *** **** * worked **** ***** **** support ** **** * firmware ****** ** ******** itself ***** ****.

************ *** ************ ****, and ***** *** ********* just ********** ** ** PoE *** ******* ** do *** *****. * don't ********** ***** ********* like **** ** *** of ** **** * sites ***** **** **** to **** ** *********** over *** ******** ** Verkada, *** *'* ********* considering ***** ***** ** lower **** ********** **** aren't ********** ******** **************. I'm ******** ************** *****, customer *******, *** ******** else *** ****** ********* would ** *******.

* *** **** **** benefit ******** *** ** shows ** *********** ***** plummeting ** * ********* around ***-*** ** ***** as ************ *** *** existing ** **** ** admin *****. ** **** NVRs, ** **** *********, and ** **** ******** stressing ***** ******* ** not *** ******** * need ** ****** *** been *********** ***** *** department ****** *** ****** to *** ** ** we **** **** ******* incident ** * ****** site ** *****. *** days ** ******* ******** video, ******* *** **** of ** *** ******* taking *** ***** **** down ** * *** win.

** *** ****, *'* impressed, *** ****'* *** easy ** ** **** it ***** ** **** sort ** *****.

** **** ******* **** that *** *** ****** dies *** *** **** to *** ** **** you **** *** *** need ***** **** **** camera **** * ***** ago?

** *******, ** **** case, **'* ******** **** the *****, ******* ** any ***** ****** **** onboard ******* **** ***'* removable. ** *** ****** isn't ********** **** *** I *** ***** *********** with **, * ******* I ***** ******* *** of *** ***** ** the ******* ***** ** it's **********.

** * ** ***** like *** ** ***** for **********, * ***** likely ***** ******* ** of **** ***** ** keep ** **** *** quick *********** ***** *** broken *** ** ******* repaired/replaced. **** ** ***** is *** ** *** other ******* * ******'* use ** ** *** Tier * *****. ** go ******* * *** of ****** ** **** 1's ** ***** **********. As **** ** *'* informed ** *** ******** in ****, * **** a *** ****** * could **** ** ****. In ***** *********, ** keep **** ***** ******* the ******, ** **** at ***** ** **** on *** ***, *** we **** **** **** available ** ******** ******* using *** ******** ********* device ***** *** ***** in ********** ** ****.

*** *******, *** ** you **** *** *** cameras ** *** ***? We ***** * *** of **** ** *** utility ***** *** **** never **** *** ****** that ******* *** ***** network ** *** ******** routed *** ** *** internet. ** *** **** have ******** ******** ******** at **** ****?

** *****, ** **** separate ******** *** *** business, *****, *** ********. Tier * ********** **** their *** ******* ** well. **** **** **** though, *****’* ** ****** of ** ******* ******** that ***** ** *** internet ******** **** * tier *...

***** ******* *** ******* cameras *** *** ******* weeks, **'** ******* *** section ** ***** **** search ************ *****:

*****, ******** **** ********** added ** *** ******** as ******** ****** ***** instead ** ***** ****** into ***. *** *******, in *** ***** *****, the **** ****** ** shown ** ** ****** subjects (*********** ** ***).

**** **** ***** ********** does *** ****** *** same ***** *******. ***** clips **** ********* ***** are ***** *** ****.

Verkada Displays Same Person As 10 Different Subjects

************, **** ******** **** incorrectly **********. *** *******, clicking ** *** ****** returns ********* ******* *** 5 ********* ******. **** one ****** *** ********** as ****** ******** ** our ******.

"**** *** ****** *** recognized ** ****** ******** in *** ******."

****** *** ***** **** beards

Read this IPVM report for free.

This article is part of IPVM's 6,307 reports, 842 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

Related Reports

IronYun AI Analytics Tested on Feb 17, 2020
Taiwan / US startup IronYun has raised tens of millions for its "mission to be the leading Artificial Intelligence, big data video software as a...
Monitoreal "Completely Autonomous" Home AI Tested on Feb 12, 2020
Monitoreal claims to allow users to "see the things you want (people, vehicles, animals) and ignore the things you don’t”, using AI to distinguish...
BriefCam Video Analytics Tested on Jan 06, 2020
BriefCam, acquired by Canon in 2018, is one of the most commonly used video analytics offerings in the West. But how well does it work? We...
Avigilon Facial Recognition 'Appearance Alerts' Tested on Dec 18, 2019
Avigilon has released 'Appearance Alerts' in ACC 7.4, which adds real-time facial recognition. To see how this performed, we tested them with...
Avigilon Appearance Search Tested on Oct 30, 2019
Avigilon Appearance Search claims that it "sorts through hours of video with ease, to quickly locate a specific person or vehicle of interest...
Camect "Worlds Smartest Camera Hub" Tested on Oct 18, 2019
Camect is a Silicon Valley startup that claims the "Smartest AI Object Detection On The Market", detecting not only people and vehicles, but...
Axis Perimeter Defender Improves, Yet Worse Than Dahua and Wyze on Sep 19, 2019
While Axis Perimeter Defender analytics improved from our 2018 testing, the market has improved much faster, with much less expensive offerings...
Vivotek "Neural Network-Powered Detection Engine" Analytics Tested on Sep 17, 2019
Vivotek has released "a neural network-powered detection engine", named Smart Motion Detection, claiming that "swaying vegetation, vehicles passing...
Anyvision Facial Recognition Tested on Aug 21, 2019
Anyvision is aiming for $1 billion in revenue by 2022, backed by $74 million in funding. But does their performance live up to the hype they have...
Hikvision DeepinMind 2019 Test on Jun 06, 2019
In 2018, Hikvision's DeepinMind AI NVR performed terribly, recognizing vehicles, animals, and other objects as humans, misclassifying demographics,...

Most Recent Industry Reports

JCI / Tyco Security Products Layoffs on Jun 05, 2020
Johnson Controls / Tyco Security Products has confirmed COVID-19 related layoffs, expanding upon the April coronavirus cuts the company previously...
EyePark Presents Mobile Driver Authentication on Jun 05, 2020
EyePark presented its long-range QR code parking verification platform at the May 2020 IPVM Startups show. A 30-minute video from EyePark...
Bleenco "Under The Tongue" Temperature Detection Examined on Jun 05, 2020
"Say aah", says Bleenco, a PPE detection video analytics company, offering a different method for measuring body temperature with a thermal...
Hikvision and Uniview Entry Level Thermal Handheld Cameras Tested on Jun 05, 2020
While most screening systems cost $10,000 or more, manufacturers such as Hikvision and Uniview have now released handheld models for $1,000 or...
Sequr Presents HID based Cloud Access Control on Jun 04, 2020
Sequr presented HID based Cloud Access Control at the May 2020 IPVM Startups show. Inside this report: A 30-minute video from Sequr...
VergeSense Presents People Tracking Sensor on Jun 04, 2020
VergeSense presented its people tracking sensor and social distancing insights at the May 2020 IPVM Startups show. A 30-minute video from...
FLIR A Series Temperature Screening Cameras Tested on Jun 04, 2020
FLIR is one of the biggest names in thermal and one of the most conservative. While rivals have marketed fever detection, FLIR has stuck to EST...
"Fever Camera" Show On-Demand Watch Now on Jun 03, 2020
IPVM has successfully completed the world's first "Fever Camera" show. Recordings from both days are posted at the end of this report for on-demand...
Cobalt Robotics Presents Indoor Security and Access Robots on Jun 03, 2020
Cobalt Robotics presented indoor security robots at the May 2020 IPVM Startups show. Inside this report: A 30-minute video from Cobalt...
Dahua Sues Ex-North American President, Says Legal Typo on Jun 03, 2020
Dahua's former North American President Frank Zhang claims he is owed almost $11 million but Dahua counter claims it is just a "scrivener's error",...