Hikvision Video Analytics Tested 2016

Avatar
Ethan Ace
•Published Feb 04, 2016 05:00 AM

** ****** *********'* ***** ********* ** *** Hikvision ******, ******* **** ***** ***** to **** *** ********* *******, ** this ******* **** *****:

** ****** ***************'* ******** ****************' ***** ****** ********* *** *** *** **** *******.

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

*********'* ********* *********** *** ***** ***** rejection **** ***** **** ********** *** the *****, ****** **** ***** ******* settings. *********** ** *** ***** *** high *** ******* *** ******* ** or ****** **** **** *** *, though ****** ********'* ********** ******** *******.

*** *** ******* *** *** **** offered *** ******** ******** ****** ** ******* tested, ****** ******** *** ***** ***** rates ******* ** ****** *** ******.

***** ********* *********'* ***** ********* ****** be **** ** ****** **** ********* and ****** ** ******** ******** *** their *****, ** ******* ** ** so **** ****** **** ** ******** nuisance alerts. ***** ****** ** ******* **** adjusting *********** ** ****, ** **** slight *********** *** ************* ******** ***** alerts ** ******** *****. 

***********

*** ********* ** ***** **-***** ********* at ** ****** ** **** *** cost ****** (****** ******* ** *********/*********) helps *********'* *********** ** **** **** simply * ***** ****** *****. **** brings **** ** **** **** *****, Sony, *******, *** ****** *** **** offered ***** ********* ** ***** ******* for **** ****, *** **** **** ahead ** ****, *** ****** **** VMD */*.* (******** ******/*********) *** ********* analytics (****** ** ** ********** ~$** fee *** ******).

**** ****** **** **** ********* ** spec ********** ***** ***** ********* *** included ** * ******** ****.

Key ********

**** *** *** *** ******** **** this **** ** *********'* ** ***** analytics:

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

  • ** *** *******, *********'* ********* **** prone ** ******** ***** *********** *** to ****** ******** *** **********, *** not ******* ** ****** ****** (**********, flashlights, *******, ***.)
  • ********* ********** **** *** ****** ** interest ********** ****** *** ***** *********** from ***** *******.
  • ** ***** *********** **** ********* ** the **** *** **** ******* *********, similar ** ********'* *** ******** ******, while Axis *** * ********* ***** *****.
  • **** *** **** ************ **** *********** analytics *** ** **** **** **** inclusion ***** ******* ** ********, *** the **** ** ******* *****.

********* ********

********* ******** ****** ** ******. **** chart ******** ******** *** ********* *** competitors:

** *********'* ******* ******, *** **** integrated ** **** *** *********** */*" super *** ***** ***** ********* ****, with *** ******* ******** ****, **** the **** *** ** *** *** performing ******* *******.

*******, *** **** ************ *** ***** cameras ****** ** *****, ******** ********* subjects ****** * ***' ****/***' *****, versus ***'/***' ** ********, *** **** best ******.

***********

  • ******** ****** ********** **** ******* ******** Center, *** *** ******** ******* ******, ExacqVision, ** ********* ********. ** ******** boxes *** ******** ** ***** ***** third-party *****.
  • ****** ********* ******** ** *********'* ****-**** client, **** *** *** ******** ***** overlaid ** ***** *******.

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

*** ******** ** *********'* ******* ****** and ******** **** ******** ********* ********* and ******** ********* ** ** ****. Higher *** ****** ******* ********** *********, as ****, ***** ** **** *****:

 

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

***** *** *** *********** ** ************* which **** ********* **** ***** **** difficult **** ** **** *********** ******:

  • **** ***** ******* ****:******* ******* *** **** **** **** sides/points, ****** ***-****** ******* ********* ** draw ** ********* ******** *******.
  • ** ********* *****:*** ********* ** **** *** ******* exclusion *****, **** *******, ********* ***** to *** ******** ********* ***** ** cover * **** ****** *** **** objects **** **** ** *******.

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

***** ** *** *****, ** ********* the ********* ******** ** ****:

  • *********** **:******* ******* ** * *********** ** 50 ** *** ******** *****, *** we ***** **** ** ** *** best *********** ** ***** *** ***** alarm *********. ******** *********** ******* ******* range, ***** ******* ** ********* ***** activations.
  • ********* >* ***:** *** **** ******** ** ************, objects **** ** ******* ** *** region ** ******** *** ******* **** 1-2 *******. ******* ********* ** * or ****** ********** **** ***** *********** (typically *****-***** *** ** ******* *********) while *** ********* ********. ********* ******** to *, ******* ***** *** ********* instantaneously.

** ****** ***** ****** *** **** in **** *****:

False ***** ******

***** ******* ********, *********'* ********* ******** from **** ******* ** ***** *********** from *** *******:

********/*******

*** ******* ****** ** ******** ****** by *** *** ****** ********/*******. **** even * ****** ******, ******** ********* ********* detection ***** **** **********. **** ** these ****** ***** ** ******** ** increasing ********* ** * ** ******, though *** **** *******, ***** ***** should ** ******* **** *** ****** of ********.

*******

****** *** ***, ******* **** ** branches, ******** *****, ** ****** ******* in ***** ***** ****** **** ***** alerts, ****** ** * **** ***** rate **** **********.

Detection ********

******** ******** **** ****** ********* ** the ********* ****** *****. *** **** series (**** *** **** ** *** test) ********* **** ** ******* ******, with ******** ***** ******* ** ********'* H3A ******** ******, ***** * ***' HFOV. *** *********** ****'* ******* ******** was *******, ~***' ****, ******* ** the **** ***** **** *** *.

*******, *** ****'* ********* ***** *** *** best ** *** ******* ******, ******** a ~***' ********** ***, **** ********** smaller **** *** ******* *****. ***** cameras *********** *********** ***** ** ******** in *** *****.

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

******** ***** ** *** **** ***** series *** *** ******* **** **** smaller ******** ** *** **** *** 6000 ******. ****** *** ***,

** *****, ******** ******* *************,

VMS ***********

** *** *****, *********'* ********* ********** with ******* ******** ******, *** *** Milestone ********, ******** ******* ******, ** ExacqVision ************. ******** ***** ****** ******* are *** ******** ** ***** ** any ** ***** *****.

*********** **** ******* ******** ** *************. Events *** ****** ****** **** *** camera ** *** ***, *** ******* in *** ***** ****.  

****-****

*********'* ********* ********* **** ***** *** iVMS-4200 ***, ** ****. ***** **** is *********, ** **** ** ******* of ******** *** ****** ******** *****, not ***** ** ***** ***** *****. 

Comments (7)
WL
Wayne Louw
•Feb 04, 2016

Great. Now we are going to have more bakkie brigades selling cameras with "analytic's"!!

HL
Horace Lasell
•Feb 05, 2016

Thanks, Ethan, for another great, detail-oriented article. I wonder if defocus or scene change analytics might apply to flashlight blinding incidents?

MC
Marty Calhoun
•Feb 07, 2016
IPVMU Certified

Thank you Ethan for testing and most of all thank you Hikvision for once again supplying the video industry with IP Video cameras and VMS LICENSE FREE.

(1)
U
Undisclosed #1
•Feb 07, 2016
IPVMU Certified
In reply to Marty Calhoun

...VMS LICENSE FREE.

OLD VERSION.

(1)
(1)
UI
Undisclosed Integrator #2
•Feb 07, 2016
In reply to Undisclosed #1

The discussion included iVMS 4200. Version 2.4.3.1 is not old.

iVMS 5200 is a completely different platform

U
Undisclosed #1
•Feb 08, 2016
IPVMU Certified
In reply to Undisclosed Integrator #2

iVMS 5200 is a completely different platform.

Sure they are different, 4200 is free and 5200 is far better.

As for versions, iVms 4200 is at v2.4.3.1, yet iVms 5200 is already at v3.2.010

Why? Maybe because they started 5200 at v3.0.

UI
Undisclosed Integrator #3
•Feb 09, 2016

do you know if face detection is working on people covering their head with ski mask or burka? I mean which algorithm is used for face detection, like the Bosch IVA, which recognize the shoulders and head silhouette or does it detect by eyes nose and mouth?

Avatar
Skip Cusack
•Feb 14, 2016

I would be very suspicious of a vendor claiming to do accurate FR on subjects covered in a ski mask or burka. This problem is hard enough to solve with complete subject cooperation, at least where meaningful accuracies are required.

(2)
(1)