Bosch IVA/EVA Video Analytics Tested

By Rob Kilpatrick, Published Sep 16, 2021, 09:05am EDT (Research)

***** *** ******** *** ****** ******** of ***** ***/*** *********, **** ** overhauled *********** ******* *** ******* ******** improvements. *** **** ***** ***** ****** their *********** **************, ****, ******, ** ********* ****** analytics?

IPVM Image

** *** *** **** *** ********** really ******** *** **** *** *******, we ****** *** *******'* ********* *********** ******** *** ** ************ *****, *********:

  • *** ** **** ****** ****** ****** and ******* ***** ***** ******* **** as *******, *******, *******, ****, *** lights?
  • *** ****** ********** ******** *** ********** when *******, *******, ********, ** ********* obscured?
  • **** *** ** ******** *** ******** detection?
  • *** **** **** *** *** ****-******** work?
  • *** *** ***/*** *********** ******* ** improved?
  • *** ** ***** ********* ******* ** other ****** ********* **** ********, ****, or ******?

*******

** *** *******, *** *** *** accurately ******** ***** ******** *******, ********, and **********, **** ** ***** ****** on **** *******, ********* *******, *******, lights, ** *******, ****** **** ********* alerted ** ******** ****** ** ***** rain.

*** ********** ********** ****** *** ******** (including ****, ******, *** *****), *** EVA ************ ********** ******** ** ******.

**** ********* ********** **** *****, *******, Milestone, *** ******* *****, **** ******** searchable ** ******* *** ********* ***** Bosch ******** ******** ******.

*** *** *****'* ***-***** ****-******** ********** and ******** ******* ****** *** ******** in *** ***** ** ** ** ~500' *****, ********* ** ****** ** interest **** ** ******** ***** ******* pass ** ** ********* ******* **, though ******** *** **** ** ******* fully *********** ****** ******* ** ** an ****** ******** ********** *** * few ******* ****** ****** ***** (~* seconds). *******, ***** **** ****** ******** to ****** ******* **** ** ***********, wheels, ** *** **********, ****** ***** issues **** *** ******.

IVA ** *** *********** *** ********

**** *******, *** *********** (***** ** *****'* *****-**** ******) *** ******** ****************** *** **** *****, ******** ***** ****** *** ******* sources ** ***** ****** ***** ********** triggered **, ********* ******* *** ******/*******, with ***** ************** ****** *******, *** not **********. *** *** *** *********** any ******* ** * **** ** testing, ***** *** ************* ******** ** people ** ***** **** *** ***.

Versus ********, ****, ******, ********* *********

*****'* ****** ********** ** *** **** not ************* ****** ***** *********** ****** top ****** ********* **** **********'* ***,**** ****-******** ****** *********, ********'* ******* * **, ***** ***** ***** ********* ** similar ** *** ***** *********. *******, others ** *** ******* *** *********** process ****** ** *** (****** ******** and **** **** ******* ******** ************), reducing ************ **********, ****** *****'* *** wizard-based ***** ** ****** *** **** error-prone.

***'* *********** *** ******** **********, ** it ** ****** ******* **** **** false ***** ****** **** ** **** tests, ********** *** ** ***** *** cost***** ****-********* ******, ** ** *** ******** ****** performance ************'* ******** ********* ********.

New *********** *******

*******, ***** *** ********** * *** calibration ******* **** ***** ***** ******* setup, **** ******** *** **** *********, and ******** ** *********** ******** ****** inaccurate, ****** ***** **** ********** *** less *****-***** **** ******** *****.

*******, ***** *** ******* ** ******, many ***** ***-********** ********* (*.*. ********, Axis ****** *********, *** ****** ******* P **) ** *** ******* *** manual ***********, *********** *****.

People ********** *******, ********, **********

**** *** *** *** ********** ******** and ********** ***** ******** **** *******, running, *** ********, ***** *****.

IPVM Image

**** ******** **** **** ****** **% obscured **** ******** *** **********, **** as **** ****** ********* ******* ** a ***.

IPVM Image

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

*** **** ********** ****** ** ***** alerts ** *** *** *** *** raindrops ********** ** *** ******'* ****/** front ** *** **** ****** ***** rain. ***** ***** **** ******** *** classified ** **** ****** *** ******** in **** *********, ****** **** ******** in *** **** ***.

IPVM Image

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

** *** *******, ******* *** *** EVA ********* ***** ****** ** ******* foliage ** *** *******, ***** *****:

IPVM Image

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

************, ******* ***** *** ***** ******* (such ** *** ***, *****) ********* false ****** ** ****** *** ** EVA. *** ****** *** ******** *** ignored.

IPVM Image

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

******* ****** **/*** ** ***** *** not ******* ***** ****** ** ****** IVA ** ***. ****** **** ** issue ** *** **** ***** ** EVA.

IPVM Image

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

************, ***** ******* *** *** ******* false ****** ** ****** ********. ** with *******, *** ****** *** ******** and * ******** *** *******, *** did *** ******* ** *****.

IPVM Image

Person ********* ** ~*-* ***

****** ********* *** ******** ** **** ~5-6 ***, ********* ** *** ******** and ***** ** **** ***** ***** for * ***** ********* *********. **** is *** ******** ** **** *******, which **+ ***, *** ******** ***** than **** ***/*** *****, ***** ******** 8-9 ***.

IPVM Image

IVA *** ************

*****'* *** ************* ***-***** ****** *** ******* ************, allowing ***** ** *** ** ******** rules ***** ** ****** *********, ***** trigger ************ **** **********.

** *** *******, ******** ****** ****, quickly ********** **** * ****** *** seen ** ** ***** ****, *** smoothly ******** ** ** ****** ********** the ***** *** ** * ******** of ****** ***', *****.

****** ******** *** ******** **** **** much ** *** *******'* **** *** obscured, **** ** *** ****** ******* behind *** *** *****:

******** **** **** ********** ******* ** our ******* *** *******, ** ** ~15-20 ***. ******** *** ** *** to *** ******** ****** ********** ** the ******, *.*., **** ******, **** bikes, ***.

No ********* ******* ******* ******* *** *****.

*********** ******** **** ****** *** ***** object ***** ********* *** ****. ** does *** ***** ******** *******/****** ******* them ** ******** ***** *** ***** of ****, ********* "******" ** *** original ********** ****** ***** ** ****** the ***** ** ** ********** *** a ****** ** ****.

Stationary ******** *** *******

**** * ******* *** ********** *** too ****, ******** ****** ******* ** started ******** ******* ****** ** *** scene. **** ***** ** ********* ***** by ********** *** ******** **** **** so *** *** ***** ** *** area *** ****** ** **** ***. Below *** ****** ****** * **** stops *** ******* ****** ****** ****** and ** *******.

Swaying ******* ********* *******

******* ******* ** *** ***** **** as * **** ********* ****** *** PTZ ** ***** ** *** * long ******* ** ****.

IPVM Image

***** ******** ** **** *** **** can **** * **** ******** ***** areas ** *** ***** ** ***** processing ******* *** ******* ***** ******.

Some ******** ****** ****** ***** ****

*** ******** *** ********* ******** ****** heavy ****, ***** *** ********* ******* numerous ***** ****** ** ***** ************ PTZs.

*** *******, *** ******* *** ******* are ********** ******* ** *** ***** below, ******* ******** ** ***** ** the ******'* ****.

*******, **** **** *** ********* *****, tracking *** ********* ** *********** ** cars, ******, *** **********. ** *** clip *****, ***** ********** ******** * subject ** * *******, *** ****** locks ** *** ****** ** ***** a ********** *****'* ********* ** *** rain ******* ** ***** ******** ** front ** **.

Solid ******** *** ***********

******** ****** ********** **** *****, *******, Network *****, *** *********, ***** ******* and ******* ***** **** ********** ****** classifications ** ***** ****** (*******, ******, bike, ***.)

IPVM Image

************, ******* *** ********* ***** ******** search ***********, ***** ****** ***** ** search *** ******** *******/***** ** ******** video, ******* ** ****** ******* / ********* ******** ****** ******.

**** ***** (**** **** ******) ********* forensic ****** ** *********:

Versions ****

*** ********* ******** **** **** ****** testing.

  • *** ** ********* *****: *.**.****
  • ********* ** ********* *****: *.**.****
  • ********* ***** *****: *.**.****

Comments (3)

**** *********** *******, ***** ***.

Agree: 5
Disagree
Informative
Unhelpful
Funny

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

Agree: 3
Disagree
Informative
Unhelpful
Funny

****** *** *** ***** *** ****** article; * *** **** **** ***** "test-driving" **** **** *** *** **** similar ********. *'* *** **** ****** Portal ************ ** **** *** ** least ******** *********. ** * **** more **** *** ****** ****** ******, I'll **** **** **** *** **** a ******* ** ***.

Agree
Disagree
Informative
Unhelpful
Funny
Subscribe to IPVM Research to read the full report.
Why do I need to subscribe?
The IPVM Research Service includes products tests and shootouts plus competitive and financial analysis, helping decision-makers better evaluate purchasing, partnering, developing, and/or competing against companies in physical security.
Already have an account?
Loading Related Reports