Are Camera-Side Analytics More Accurate?

After reading several instructive articles regarding video analytics detailing what the pros/cons of camera-side vs. server side placement are, I didn't notice any mention of the effect of analytics being done pre-compression vs. post-compression.

Certainly since only the camera (or encoder) could do pre-compression analytics, I would think that this could be a major factor in performance, depending how much compression was involved, of course.

Practically speaking, with no compression artifacts, wouldn't it allow settting a much lower threshold for alarms, say with motion detection?

Related, I have heard that most analytics typically reduce any MP resolution images to D1 before processing. If this is the case, given two compressed streams from the same camera, one high-res/high-comp and the other one low-res/low-comp, would the low-res be more accurate and with less FA than the high-res one, at VMD for example?

Login to read this IPVM discussion.
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.

** ** *************, ** ** ******* **** ********* ** '***-**********' images / ******.

*** *** ******* / ******* **** ** ******* *** **** confirmed ** ******** ** ***-********** *****?

... ** ** ******* **** ********* ** '***-**********' ****** /******.

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

**, ** ** *****, *** *** ****** **** ********* ******** ******* *** *** *.*** ******, ******************, *** **** ******** ********* ** *** ******* *****?

******** ** ****'* **** ***** ** ** **** **** ***** compress ****** *********. *** *** ** *** ******* *** ** SOC *************, ** ******* ** *********** ***********/******* ******** *******, *** camera ***** **** ** ******* *** ********* ** ******** **** an ******* ******. ***** ***** *** **** ****** *******. ****** for *** ******** *** ********** * ****'* **** **** * made.

****** ***** *** ** ************** ** ****** ************* *** ***** ** **** ** *** uncompressed ***** ****.

*** ************'* ****'****** **

4.2.2 ***-*********** ***** ********** ****** ****** ********

*********** ********* **** ******** ******* ***** *** ******* ***** ****** are ** ******** *********** ** ******* ******** ******* **** *********** analytic ********* ** *** ****-***. ****’* ******** ********** **** ****** issue ** ******** *** *****-*** ********** ****** *** *******. ***** analytics **** ***** ****** ***** **** ** ********** *** ******** over *** *******. ************, *** ****** **** ********* ** *** affected ** ******* ***** ********** ** *** *********** **** *** ratio **** *****.

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

******* *** ***** ********* *** ****-*****, **** ****** *** *** of ****** ********* *** ****** *** ********* ****** ***********, ***** increases ***** *******. *** ****** **** ** ********* ********* ********** and ***** ***** ****** ***** ******* ***** **********.

******* ****** ********* **** *** **** **** ** ********** ****** is ******, *** ******* **** ***'* ***** *** ******* **** are *** ******** ***** **...

"** *******".

***** *** **** ** ********* ************ *** ********* *** * lot ** **** ** ** ***** ********* *****. **** ** simple ***** ********/***************, **** ** ******* ********, **** *** ******** calibrated, **** *** ****-********. ***** *** ***** **** ********* **** downsample ***** ** *** **********, *** * *** **** *** process ****** *********** (** ** **** ** *****).

*'* *** ***** ** *** ******-**** ********* **** ******* ** a **** ************ ****** (***** ** *** *** *** "*****" is ******* ** *** ******, **** ***** ** **** ** do). *** ******-**** ********** ***** **** *** ********* ** **** control **** *** ******. **, *** *******, *** ****** *** built **** ********* ** ****, *** ********* ****** ***** ************* have ****** ** * ********* ******** "******", ***** *** ** adjusted ***** ** *** ***** (***** ********** ** ** ****, change *********** *******, *** ** *****) ** **** *** ********* are *** ********* ** *** ********** ** ****** ********* *** bandwidth ** ******* ** ********.

********* **** ***** ** ****** ******* ** ******** *** ** somewhat *************** *********. ***** "*****'* ***", **'* ********* ** **** a ********* ******** ** *** ****** **** *** ****** **** process ** *** ****. *** ********* ******* ******, *** ******* contentions ** * ** (** ******, ******** ***********) ** ******* the ********* ****** *** ******.

***** *** **** ****** **********, ***** ******* *** ******** **-******, and **** ****-**** ** ******** **** ** * ****** ** handle *** "*****" **** ** *** *******.

****** ********* ** *** ****** **** *** **** **** "**** accurate", *** ** **** *********** ******** * ******** **** ******* or ******** ******. *** *** ** ********** ******* ** ***** of ****** *******, *** *** ******** ** ******** ******** **** optimized ** *** ********. *****, ***** *** **** **-***** ********* that **** **** ******-***** *********, ** **** ** **** ** an ********.

**** ** * ****** *** **** ****** "** *** ***** drive ****** **** * ***** *****", *** ******* ** **** there *** ** * *** ** ***** ************ **** ****** what ***** "****" ** ***. ****'* ****** ********* ** "** you *** *** ******* ******* ****** **** ******?".

** ***'** ********** ********* *******, * ***** ********* *** ** look ** **** *****. *** ********* ** *****/*********** **** (********* and *******), **** ** ********/****** *** ****** **** ****, *** coverage ****/******** *** ****** (**** *** ** * *** ***, I've **** **** $** ********* **** ***** */**** *** ***** of * $*** ********, *** **** ***** ** *****)

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

*'* *** ***** ** *** ******-**** ********* **** ******* ** a **** ************ ****** (***** ** *** *** *** "*****" is ******* ** *** ******, **** ***** ** **** ** do).

* ********** *** ** ***** *** ** ******** ** **** on *** **** ******, ** **** *** **** ** '****' is **** **********. *** *'* ****** * ****** **** ************* why *** ******** ******** ***'* ******* ****-**** **** *** ***** before *** ***** *********** *** ******* *********.

**** ** *** **** ******* ** '***** ** *** *** the "*****' ** *******'? *** *** ********* ** * ******** CMOS ******* ******* ***** *******? *** *.*** ******** ********* *'** played **** **** ** ***** **** ** *** ***** *****, you ******** **** **** *** *********** *****/********* **** ****** *** luminance ****** *** *** ***encodeFrame(_frameData), or some such construct. So someone as naive as me might conclude **** *** ***** *** **** ********* ***** ** *** ***** to *** ******** ****** ****** ** ** ******** ** *** compression.

***** ******-**** ********* *** *** ***** ** **** ********** **** with *** ***** **** ***** ***** ***** **********? **'* **** to **** ******* ***** *** ******** ***** ***'* ****. ** far, ** ******** ** **** *** *****, ************ ******* ************ ***** **** ** ******** ****-***:

******* *******, ******* ******* ** **** **************, ******** *******: “** are *** *** ****** ********* *******, *** ** *** ******* in ********** *** **** **** ** *** *******’ ********** ***** and ****** ** ************ ***** ** *** ***** ********* ********...

****** **********:** *** ****** *****, **** ********* ** ********* **** ** one ** *** *** **** **** *** *********** **** ** able ** ************* ********** **** *** **** ** *** ****, and ******* ******* * ******* *******.

*** *** ***** **** ** ** ******* ** *** ********** in ******* ******* * '***-***********' ***** *** * ****-*********** *****?

****** *****'* * *** ********** ******* * ***, *** *** 1080p *****. **** ** * *** *******, *** *******, **** camera *********, ***:******* ***** *********** **** *** ******.

******** * *****'* ** ********** ******* ** ****, *** *** system ****** ***** ******* *********** *********, **** ******** ********** ******* small ********** ****** *** *****. * ******** **** ***** *********** pixel ****** *** ********** **** *** *.*** *********** *********. * also ******** **** **** ******* ***** **** ***** **** *** would ** ******** **** ***** ***** ** ***********-***** *********.

**, ****'* **** * ******* ****** ** *** *********** **** the ****** ******. ;)

*****, **** ** *** ******* ********** ******* *** ***. **** we *** ****** ******** ******* ** *** *** ****** ** analytic ***********.

** ******* **** ******* *** ***** **-******-*** ********* *** ******* cameras, * *** **** **** ***** ********* *** *** ** the "***" ***** ****** ****** ***********. * ***'* **** *** documentation, ***. ** **** **** **, **** **** * *** told...

**. * ** ******* **** * ***** ***** * ** using ********* ****** ** ************** **** *** ******* **** * single **** ***** **** *** **** ***, *** ********* *********** levels, *** ****, *** *** ***. ******* *** ****** ********* sensitivity *** **** ** **** *******, ** ***** *** **** compression ******* **** **** ***********, ***** *** *** *********** *** is **********.

** *** ** *****, ************** ********** *** ** ** ***** ******** **** ** *****, ** * ******* *** *** **********. As * *** ** ******** *** ****** *** **** ** more ********, * ***** ***,is **** * ***** *****/****? If not, tell me what to add/change so I don't waste time by make something non-instructive, otherwise I'll have something shortly.

*'* ********* ******* *********** ** ****** ***********, ***** ******* ** what **** ****** ***. ***, ** ******* *** **** ****:********** ** *********** ******.

*** ***/*** **, ** *** ***** *** *********** ** **** as *** *** *** ***** ***** ******** ****** *** *** increase *** '**********' *****, ** * ****** ********** **** ***** may **** **** * ******* ***** *****. *** **'* *** as ** ******* *** **** ** ********* *** *** *********** eliminates ****. **** *** ****** *****.

*** **** ** ******* ********* *********. *********** **** ** ** *** '***' / '************' ***** but ** ***** *** **** ** ******, **** ** **** Axis ******* ********* ** ** ******** ****** (***** ********** *****). The ***** ***** ** **** ******** ** ********* ************** *** much ***** / **** *********** **** *********** / ********** ***********.