Wyze AI Analytics Tested - Beats Axis and Hikvision, Now Improved, Now Being Terminated

By: Ethan Ace and Rob Kilpatrick, Published on Nov 25, 2019

When we originally tested Wyze's free person detection deep learning analytics in July 2019, they performed well, with few false alarms, but a long 5-minute cooldown period which caused missed alerts.

[UPDATE: days after releasing this updated test, XNOR.ai has terminated their agreement with Wyze and XNOR.ai's analytics will be removed from Wyze firmware in early 2020.]

Now, they have released a new paid Complete Motion Capture plan which eliminates the cooldown.

To see how Complete Motion Capture impacts performance, we tested multiple Wyze Cams examining:

  • How does this new plan improve person detection?
  • How well does person detection work? Does it miss people day or night?
  • How does walking/running speed impact detection?
  • Do nuisance sources like lights, shadows, foliage, and animals trigger person detection?
  • How difficult is analytic setup?
  • How does performance compare to Nest Cam IQ?
  • How does performance compare to Hikvision Intrusion analytics?

**** ** ********** ****** Wyze's**** ****** ********* **** learning *********** **** ****, **** performed ****, **** *** false ******, *** * long *-****** ******** ****** which ****** ****** ******.

[******: **** ***** ********* this ******* ****,****.** *** ********** ***** agreement **** ******* ****.**'* ********* **** be ******* **** **** firmware ** ***** ****.]

***, **** **** ******** a *** ************ ****** *********** ***** ********** *** cooldown.

** *** *** ******** Motion ******* ******* ***********, we ****** ************ *************:

  • *** **** **** *** plan ******* ****** *********?
  • *** **** **** ****** detection ****? **** ** miss ****** *** ** night?
  • *** **** *******/******* ***** impact *********?
  • ** ******** ******* **** lights, *******, *******, *** animals ******* ****** *********?
  • *** ********* ** ******** setup?
  • *** **** *********** ******* to **** *** **?
  • *** **** *********** ******* to ********* ********* *********?

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

*******

****'* ****** ********* ********* performed **** **** *** course ** ***** ** testing, ******** **** ***** person ****** **** ******* which ******** ********* **** commercial *******, **** ** shadows, ***** *******, ******* foliage, *** *******.

**** *********** *** ** par **** *** **** more ********* **** *** Outdoor ** *** ****** than *********'* ********* *********, which ******* ** *******, shadows, *** *******.

*******, ***** **** ***** key ********* ***** ** our *******:

  • ****** ********* ******* ** 12 ******* *** *****:****** ********* ** ******* to *** ***** ** seconds ** **** ****** clip, **** **** ***** their ************ ****** ***********. **** ***** ****** in ****** ***** ****** in ***** **** **** amounts ** ******, ** people **** *** ** detected **** ****** ** of ** ***** ***** motion ***** *** ********.
  • * ****** ******** ****** without **** ****:** *******, ****'* ********* have * **** * minute ******** ****** ******* Person ********* ****** ***** could ****** ** ****** activity ** **** ******* areas. **** *** ********** a **** **** ***** eliminates **** ******** (******** Motion *******, $*.**/*****).
  • ****** ******* ********:*** **** *** ****** to ****** ******** ******* through *** *****, ********** of ******** ** ******** conditions. ** ******** ******* at ****** ** **** speeds **** ******.

** ******* ** ********* results ** **** *****:

Versus ***** ******** / *** *********: ****** ********* *** ** ******* ******

****'* ****** ********* ********* similarly ** ** ****** than ***** ********/*** ********* in *********** ** ****** ********* Shootout, ********** ******* ** Wyze's **** ******** **** completely ** *** ****, without ***** ************, ******** by ******.

****,****, *******, *** *** ***** on ******* ** *******, either, ***** *********'************ ******* ** ****** all ****** ** *** scene. **** ****, ***** other ********* **** ****** running ******** (****** ***** did ***).

*******, **** ** **** less ********* **** ***** other *******, **** ****** ranging ** ***** **** ~$110 (*****) ** $*** (Nest *** *******). ************, Wyze **** *** ******* a ************ *** ***** analytics, ***** ****, ****, and **** ** ($*-*/***** per ******), ****** **** do ******* * ***** cost $*.**/***** *** ****** for ********** ****** *******.

*** ******* ******** ** Wyze ******** ** ***** other ******* ** *** lack ** ******* ****** models, ***** ***** ************* offer. **** **** ***** outdoor ***** ** ******* for **** ****/***** ****.

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

**** ****** ********* ** available ** ******* *** ($** ***)******* *** ********** *** ****. ***** simply **** ** ******** the ****** ******** *** turn ** ****** *********.

Person ********* ***********

**** *** *** *** limitations ** **** ******** not ****** ** ***** consumer ** ********** ****** we **** ****** (****** present ** **'***** ****** * **** AI *********):

  • ****** ********* ******* ** 12 ******* *** *****
  • * ****** ******** ******* paid ****

** ******* ***** ** more ****** *****.

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

**** ****** ********* ***** only ** *** ***** 12 ******* ** **** motion ****. **** ***** that ** * ****** enters * ***** ***** motion ** ******* ***** 12 *******, **** **** not ** ********, *** will * ****** ****** trigger ** ********** ***** if *** ** ******* in *** *****.

**** ** ***** ***** this ********** ** ***** documentation *** ***** * notice ** ****** ********* clips ** ***** ****** app:

**** *** ** ** issue ** ***** ***** constant ****** ** *******, such ** * ****** facing * ****** **** blowing *******, ** ****** detection *** ****** *** trigger. **, ** * subject ****** *** *** but **** *** ******* person ********* ****** ** seconds, ** ****** **** not *******, ***** ***** (green ******** *** ********* motion, *** ****** *********):

Five ****** ******** ****** ****** ****** ** *******

***** * ****** ********* event ** *********, ** default **** *** ** unconfigurable * ****** ******** period ****** ******* ****** detection ***** ** ****. This ***** ****** ***** missed ****** ********* ** high ******* ***** **** as ******* ** *******.

**** **** **** ** a **** ***** **********, not ** **/******** **********. We ********* **** ********** with **** **** *******, as ****.

5 Minute Cooldown Results In MIssed Alerts_2

*** ****** ****** ******, this ******** **** *** exist, **** ****** **** closer (***** * ****** apart *****):

Motion Events No Cooldown

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

** ****** **** ********, Wyze ********** * **** plan ************** ****** ************ ********** *** * minute ******** ****** ******* events. ** *** *****, this ****** ** *******, with ********** ****** ********* events ******** ******* ***** seconds *****.

**** **** ***** *** not ** ******** ******, but ****** ** **** 5 ****** ********, *.*., if ****** ***** * minutes, *** ***** *** created. *******, **** **** person ********* **** **** use *** ***** ** seconds ** **** ****, regardless ** ******.

******** ****** ******* ***** $1.50 *** *** ***** per ******.

Person ********* ***********

****'* ** ****** ********* performed **** ** *** tests, ********* ******** **** day *** ***** (**** IR **) **** ** missed ********** ** ******** walking ** ****** ** fast *****.

People-Detected-Day-And-Night-Walking-Normal_Fast-Speed

**** **** *** *** alert ** ****** ******* of ***** ****** ***** triggered **** *******, **** as ******* ** *** scene:

No False Alerts From Shadows

** ****** ******* ** and ***:

No False Alerts From Light Changes

************, ****** **** ****** are ****** ****, ** also ****** ***** ** analytics ********. ********, ****** Detection ******* ******* ******* and ******* ***** ********* other ****** ** **** tests. **** **** ******** boxes ******** ****** ****, not ****** *********.

No-False-Alerts-On-Foliage

***** *** ***** ******* were **** ******* ** Person *********.

No False Alerts On Animals

Running ******** ******

*** **** ****** ** detect ******* ******** ** our *****, ***** *****. However, ***** ***** ****** market (*********** ******), **** is **** ****** ** be * ******* **** commercial ******* ** **** residential ******* *******.

Running-Subjects-Completely-Missed

Simple *****: ****** ******** *** **** **

****** ********* ***** ** simple, ********* ***** **** to ****** ******** *** turn *** ******* ** on **** ******. ** setup *** ****, *******/******* sizes, ** ***** ************* is ********.

Simple-Setup--Switch-On-For-Each-Camera-copy

Xnor: *** ******* ******** **** **

****'* ****** ********* ********* were ********* ** *********** with****, * *******-***** *******. Xnor's ***** ** ** optimizing ****** ** *** on *** **** ******** hardware, **** ** ********** ******* ** *** **** Cam *****:

**** ** *********** ****** as ****** *****-**** ***** perform **** ********, ***** historically *** *** **** capable. **** ** ** alternative ** ***** **** expensive **** ******** ***** such *******'* ******** ******.

****'* ****** *** ********** on *** ****, ******* analyzing ** *** *****. Wyze *********** **** ** Nest ** **** ******* cloud ************ (*** *************) to ****** ***** **** Aware/Arlo ***** *********. *********** **** ****'* ********* video********* ****:

**** *** ******* ** 2016 *** *** ****** nearly$*** *** ** ***. *** **** *******, see *** **** ******:******* ****.**, ********* ** YOLO, ***** ************ ***** Examined

Vs ********* ********* *** **** ******* ** ****** *********

**** ****** ********* ********* similarly ** **** ****** detection, *** ***-********** ******** in*** ******** ********* ********, **** **** ******** false ****** **** *******, lights, *******, *******, ***., though **** ****** ******* subjects.

**** ****** ********* ************ Hikvision's ********* *********, ** Hikvision ******* ** ******* such ** ******* ******* and ****** *******.

Hikvision False Alerts On Foliage Shadows

** **** ** ***** and ***** ******* ** the **********.

Hikvision False Alerts On Animals

*******, *********'* ********* **** alerted ** *** ********** of ******* ****, ***** neither *** **** *** Nest ******* ******* **.

Hikvision False Alerts On Headlights

Vs. **** *********

****'* ****** ********* *** not ******* ** **** sources ***** ****** ***** alerts ** **** ******* analytics, ********' ****,****** *****, ************ ************ *** ********* ** shadows, *******, ** ******* in *** *****.

**** ****** ** ******** object ********* ** ***** new******-* ****, ****** *********** ** the ***** ****** ***** this *** ****,*** *****-**** **** ******* ** slightly ****** **** **** tests.

Versions ****

*** ********* ******** **** used ****** *******:

  • **** *** **: *.*.*.**
  • **** ** *******: *******
  • ********* **-**********-*: **.*.** ***** 180718

Comments (35)

* **** *** ** these **** *** ********* installed ******* *** ** front ****** ** *** sidewalk ****** ** ** my *****. *** *** most **** ** *** worked ****** **** *********** this ** **** *** traffic, **** ********* * person **** ******* *** from *** ***** ** the ********. ** *** missed **** ******. ******* for *** ***** ***** these *** **** ****** cameras. * **** *** new ******* *** ***** bulbs ** **** *** haven't **** **** **** these *** ** * had *****. *** **** reason ** ******** ****** to *** ******* *** weekends *** ** ** spare **** *** **** involved ** ****. 😊

**** ** ********* **** for *** ********, ** this **** **** ********** to *** **** **** learning ********.

*******, ** ** ********* embarrassing *** *** *** big ********* **** ***** can’t ** ****. *** example, ********* *** *** its “*** ****”, “********* R&D”, **,*** “*********”, ******.  Axis ***, ***** **** do *** *** **** about **, **** ****** should ** **** **** to ******* ***** ***** premium.

** ** **** **** person ********* *** ***** this **** ** ****** normal *** ***** ************ but **** ** * good **** ** *** now ***** *****.

*** ***** ** **** typing *** **** *******. Spot **.

*** *** **** ***** ****** *** ****. :*

**** **** **** ** Wyze *******.  * **** not *** *** ****** with *** ****** ******* out ** ***** ****** at *** ******** *** get ** ************* **** faster **** *** **** I **** ******** *** same ****.  

****: * ******* *** title ** "**** ** Analytics ****** - **** Axis *** *********"

*** ****** ** ** emphasize *** ************ ** professional ***** ************. * can *** ** ***** and *********** **** **** is *** ** **** interest (*** **** **** report, *** ******* ******* we **** **** ** Wyze).

*******, **** **** *** done **** ** **** significant *** ************ ***** surveillance. **** ** ***** to **** * ******* or *** ******* ******* this **** *** **** 'regular' ****** *** ***** to ****** ****** ********* as ******** (**** ** they ***'* ********** **** 'deep ********' ** **** or ****** ************** **). And ******** **** **** and ********* *** ***** to **** ******* **** Wyze ** ******* **** they ***.

***** ************ ********* **** catch ** ******* ****** be **** *** ** could ******* ***** **** for ******** ** **.

* **** **** *** it ** ********** ** relation ** ****.  **** drives ** ***** ** the * ****** **** down *** *********.  ******* I **** *** ****** wrong, *** * ******* inserting ** ** **** would **** ***** ****.

****, *** *** ****** Detection ** ****, ****** when * ** ** in **** ** *** camera.....

***, **** *** ****** the ** **** *** can ** ** ******** settings > ***** ********* and ****** ********** *********, the ****** ****** **** just ************ ****** ** the ** **** *** you *** ****** ******* recorded *****.

** *** ***** ****** events **** ******** ****** 5 ******* ** ********* but ****** ********* ***** triggered * * ****** cooldown.

Motion Events No Cooldown

***, * *** *** that.  *** **** ****** I ******* ** ***** the ** **** ***** allow *** ** *********** record ****** ******* * minute ********.

** *** *** ****** detection ********* ** ******, I ****** **** ** allow *** ** ** privacy ***** ********* ****.

***** **** ***** **** be ** ******* ** Anyvision's ****** *********** ****** ****.

 

**** ******* *** ***/***** little ******.  *** **** if ** *** ******* here *** **** **** have * **** ******** so *** *** **** it **** ***** *** VMS.  * **** * few ******* **** * have ********* ** ** with **** *** **** are *** *****.

** **** *** ******* Wyze's **** *******.

********* ** ******* *** **** *******, ** ** * separate ******** ******* **** will ** ******** ************, so ** * ******** / **** *********, ** could **** ***** *** not **** **** *** commercial ************.

***... **** ***...

* **** * ** these ** ** ***** and *** **** ***** that **** ** ** the *** ***** ****, but **** ** * tiny *********.  **** **** fine *** ******* ******* stuff *** ****** **** my *** ** *** eating *** *****.  

* ** ******* ***** the ******** *****.  **** Xnor ****** **** * per-unit *******?  ***?  **** sort ** *********** ***** on ****** ********?  ** Wyze **** ****** *** cost *** *** ** order ** **** ******** in ****** *** *****, maybe ************ *****, ** algorithms?

**** ******** ** ******** pricing ****** ********** **** it ** * ********* / ******** ***** *****.

** ***** ** **** it ** ** ***** somewhat ** * ***** / ****** ***** ****.**'* wordmark ** ********* *** on **** *****, ***** is ** ************** ****. It's *** **** *********** speaking **** ***** **** to **** ****'* ******** on ***** ***** ****** so ****'* *** * guess ** *** **********. If ** **, ** is ******** * **** deal *** **** ***** that **** *** **** lots ** ******** *** other ********* *********.

* **** ******* **** Wyze *** **** ********* questions ***** ***** ****** detection:

* **** *** ******* yet, ******* ***** *** others **********.

********** * ***** ****** would ****** *** **** as *** *********.  *** damn ****** ******* ** sun ******* ********** *** day.  

***, ** ****** **** and ********* *** ******** as **** *** ************ the ******* ******* *** China *************.

*** **** ***** **** Dahua, ******, ******* *** pretty **** ***** ***** mainstream ****** ************ ***** now **** *** ******** and *****. *******: ** ****** ********* ******** - ********, ****, *****, Dahua, ******, *********, *******

* ****** **** ** retract ** ******** ******* about *** ****** *********. My ****** ****’* ******** anyone *** **** **** a **** ***. * even ***** ******* *** a *** ******* ** the ****** *** ********* me. ***** ** * glitch *** **** ** be ****** *** *** back ** *** **** to **** ** ** that ***. 

* *********** ********* ******* with ** *******, ** was **** *** ************* needed ** ** ******* on/off, *** *** ****** in ** *********.

********, ******* (* ******* chip ************), ** **** a ******** *** ****** (for **** ********* *******) and, **** *************, ********* (!) *** ***** ** be ****** ****** ** the ******* **********:

*****://***.*******************.***/*******-****/*******-*******-*****-********-******-*******-***-***-***-********.****

* ****** *** **** "stitches" *** *** **** real ********** ** ****** Xnor *** **** ** the ***** "**" ***** is ****** *** ****, as *** *** ************* states **.

 

**** ******* * ****** of *****.  ***'* **** to *** **** ***!  Anybody **** ** *** AWS ***** **** ***** in ******?

**#*, * ******* **** Wyze *******, ***** ********:

***! *** ***** ******* is ********* ** ********* whose ******* *** ***** and ******* ** ****** and ***** ********* ******* of *** *.*.

****** ***. * ********* 4 **** *******, * motion ****** *** * door ******** ***** * weeks ***. *'* ** sales ** *** ************* side. **** **** ** install *** ** ************ was **** *** ** it **** ** **** for *** ** **** readers. ****** ********* *** significant ***** ********* ********* but **** *** ******** to *** ***** ** almost **** ***** *********. It ********** ****** ****** at ***** ******. ***** example: **'* ********* *** and * ** *** office. * *** *** my *******-**-*** ******** ** beer ** *** "******** camera" *** ***** *** no ****** ******** ** the ******** ** ** the ***** ** *** house. (*** **** **** to *** ** ** back ****.) **** *** not ****** ** *** 5-minute ******** ******* ** people **** **** ******** since *:****. * **** on * ****** ***** residential ****** ** *** city. ****** **** ********** walked ** ** *** sidewalk ** ***** ** my ***** ** *** past * *****.

****** **** ****; *'* pretty ********* **** ****. For ***** *********** *** they **** ****** ******* at * **** *** price *** **** **** installation. ** *** **** to **** ** ****** security ******* *** **** install *** *****-** ******* though. ********* *** *** 12 ******* ** *** burglar *********** ** *** distance *** **** * 5 ****** *****. ********* the ******* *** ** can ** ****** ****** or *********. *** **'* better **** ** ****** system.

*** ******* ******** **** work ****** **** *** alert ******** ** ** phone ** ***** ***** are **** ****. **** blogged ******** ***** ** outdoor ******; ******* ******* to ******** **** ***...

Test ****** / ****-**-**:

*** ****** *** **** up *** ******* ***** we ********* *** ****, looking ** *** ********* and ******* ****. ***** alert *********** *** **** very *****, **** **** 2 ***** ****** ** the **** ****, **** at *****, ********* ** a *** ****** **** the ******. *** **** clip:

** *** **** ******** alarms **** ***** ******* here, **** **** *** overhead ****** ******* ** and *** *** * nearby **** *******/******* ***** the ****** *** *** in **** ****.

****** -

**** *** ***** **** ***-** ******* *** 1.49/month**** ******* *** ******** period ******* ****** ******, we **** ** ******* this *** ********* ** update ** *** ******.

**** **** ******* ***...** can't ** **** **** to *********

**** ******:

"****** ******** **** ** temporarily ******* **** **** Cam ********* **** * new ******** ******* ******* for ***-******* ****, *** to *** ********** *********** of *** ********* **** our ** ********."

***** **** *** ******* is **.

** ******** **** ***** as **** *** *** in *** ******* ** getting **** ******* **** Wyze *** ****. **’** post **** **** ** have ** ******.

**** **** ************ **** they **** *** * falling *** **** ****. It *** ** ** with *** ********* **** had ** *****. ***** they *** *** ********* they ****** *** *** they **** **** *****? It ***** ** *********** to **** *** *** and ******* **** ** able ** ****** ******** comparable (**'* ********* ** the **** ***** *****) to ******* **** (***** is ** ****** ***** on *** *******).

******** ****** ********* ** cew ****** ***** ** one *****. ** ****** like **** **** ******* to ******* ******* *********! I ***'* *** *** than **** **** *** firmware *********. **** ********* the ***** **** **** sold *** **** **** person *********. ****** **** can't **** ***** "******" a *** ******* ** product **** *********...

***'* **** ******* *** scrapping ****** *** ****** on *** ** ****!

***

***,

**** ** ** ** not ******* ********?

***** **** ***** * bigger *****.

******* ****** ** **** deserves ** ** **** didn't **** * **** contract ** *****.

Login to read this IPVM report.
Why do I need to log in?
IPVM conducts unique testing and research funded by member's payments enabling us to offer the most independent, accurate and in-depth information.

Related Reports

Bosch Budget 3000i Cameras Tested on Dec 05, 2019
Bosch has long had a hole in its lineup for, as it describes, "competitively-priced cameras". Now, Bosch has released its 3000i series cameras...
Ireland National Children's Hospital Chooses Hikvision End-to-End With Facial Recognition on Dec 05, 2019
The world's most expensive hospital project ever, the New Children's Hospital in Ireland, has chosen an all-Hikvision surveillance system including...
Ultinous European Analytics Startup Company Profile on Dec 04, 2019
European analytics-startup Ultinous pitches customers to "Have your own video analysis service!" We spoke to Ultinous to better understand their...
Access Startup Multi-Mount Aims To Streamline Reader Installs on Dec 03, 2019
Startup Multi-Mount claims it makes installing access readers 'Fast', 'Secure,' and fit 'any size frame.' The company states its bracket 'fits most...
XNOR.ai Terminates Wyze on Nov 27, 2019
Wyze has shocked the industry again - this time with a major setback. Just months ago, Wyze triumphantly added AI analytics to their ~$20 cameras,...
Budget Covert Cameras Tested on Nov 26, 2019
Covert cameras under $100 are widely available online but are they any good? To see how these models really work in the real world, we bought...
Top 2020 Trend - AI Analytics on Nov 22, 2019
170+ Integrators answered: What do you think will be the top industry trend in 2020? Why? For the 4th year in a row, AI/video analytics was...
Axis "Best Of The Best" 4K Camera Tested (Q1798-LE) on Nov 21, 2019
Axis has released their "best of the best" Q1798-LE bullet camera, touting "4K without compromise" with a large Micro 4/3" image sensor, custom...
ISC East 2019 Show Report on Nov 21, 2019
IPVM has finished in New York City covering both days of the ISC East 2019 show. Here is a 6+ minute general walkthrough: Inside this report,...

Most Recent Industry Reports

Disruptor Wyze Releases Undisruptive Smartlock on Dec 06, 2019
While Wyze has disrupted the consumer IP camera market with ~$20 cameras, its entrance into smart locks is entirely undisruptive. We have...
Bosch Budget 3000i Cameras Tested on Dec 05, 2019
Bosch has long had a hole in its lineup for, as it describes, "competitively-priced cameras". Now, Bosch has released its 3000i series cameras...
Anixter Resisting Takeover From Competitor on Dec 05, 2019
Mega distributor Anixter is going to be acquired but by whom? Initially, Anixter planned to go private, being bought by a private equity firm....
Security Sales Course 2020 - Last Chance Save $50 on Dec 05, 2019
This sales course is customized for the current needs and challenges specific to professionals selling video surveillance and access control...
Ireland National Children's Hospital Chooses Hikvision End-to-End With Facial Recognition on Dec 05, 2019
The world's most expensive hospital project ever, the New Children's Hospital in Ireland, has chosen an all-Hikvision surveillance system including...
AVTech ~$70 IP Cameras Tested Vs Dahua and Hikvision on Dec 04, 2019
Taiwanese manufacturer Avtech is taking direct aim at low cost leaders Dahua and Hikvision with ~$70 starlight and white light illuminator...
Ultinous European Analytics Startup Company Profile on Dec 04, 2019
European analytics-startup Ultinous pitches customers to "Have your own video analysis service!" We spoke to Ultinous to better understand their...
Access Startup Multi-Mount Aims To Streamline Reader Installs on Dec 03, 2019
Startup Multi-Mount claims it makes installing access readers 'Fast', 'Secure,' and fit 'any size frame.' The company states its bracket 'fits most...
Resideo CEO To Step Down on Dec 03, 2019
Resideo's CEO, Mike Nefkins, is stepping down, just 18 months after being brought in to lead the now plagued spin-out. Inside this note, we...
Arcules CEO Retracts False GDPR Claim + Dahua and Milestone Claims Examined on Dec 03, 2019
Arcules CEO has retracted a false claim about his organization being a "fully compliant GDPR company" after IPVM reporting (Arcules CEO Threatens...