Video Analytics Measuring Accuracy / Accuracy Issues Guide

By IPVM Team, Published Apr 01, 2021, 09:36am EDT (Info+)

Video surveillance manufacturers often tout "high accuracy" analytics as a key marketing focus, typically with 90%+ values. But how do they reach those figures?

IPVM Image

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

  • ****** ***** *** ***** ************
  • ********** ******** ********
  • ********* *** ******
  • **** ******** **** ** ***** ******** Rate
  • *** ***** / **** ***** *****
  • **-***** - ******** *******
  • **** ******* *********
  • *********** ******** ******
  • *** **** ***** *********
  • ***** ****** *********** ********* **********
  • ************ *********** ****
  • ************* **** **** ******** *****
  • ************* *** *********
  • ******* *******

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

Ground *****

IPVM Image

****** ***** ** **** ** ******** information ******** ******* ****** ***********, ****** than ********/*********. * ****** ******* ** how **** ******* *** ** * glass ***.

** ********* ***** ******** *** **** marbles **** ** *** *** (*.*., by ********** *** **** ** *** marbles *** *** ****** ** *** jar, ***.).

*******, ****** ***** *** **** ** determined ** * ****** ******** *** marbles *** ******** *** *****.

** ***** ************, ****** ***** ** obtained ** * ***** ******** ********** results ** *** ********* **** ******** video. ******* ** *** ******* ** a *** *******, **** ** *** only *** ** ********* ** ********* are ********* **** **** ******, ******* objects, ** ****** ********.

****** ***** ***** ********* ********** ** providing ****-***** ******** ** ********, ** that ********* *** ** ******** ******* training ***/** ***********.

Ground ***** ********** ******

*********** ****** ***** *** ****** ** easy *******, ** **********, *** ****** is ********** ** *****/*** ***** ** reviewed. ***** ****** *** ** ********** as ******** ** **********.

*******, *********** ****** ***** *** **** objects *** *** ******** ** ****, because *** ****** **** *** ****** an *****/***** ** ******. **** ***** all ***** ***** **** ** ** reviewed, ********* *** ******* ** ***** analytics. ********, ** **** ************, ****** detections *** * ******* *******, **** serious **** *****************.

*** *******, **** ***** **********/***** ************ systems ********* **** ****** ******/******, *** continuously ********** ***** *** ****** **********.

IPVM Image

**** ** * *********** **** *** these ***** ** *******.

******* ******* ***** ****** ***** ** difficult ** ********* ** ***** ******* since ** ***** ******* ****** *** temperatures ** *** ****** ********.

Fundamental ******** ********

*** ********* **** * ******** **** impact *** ******** * ****** ** performing:

  • **** ********* - **: * ****** is ******** ** * ******
  • **** ********* - **: * **** is *** ******** ** * ******
  • ***** ********* - **: * **** is ******** ** * ******
  • ***** ********* - **: * ****** was *** ******** ** * ******

IPVM Image

Simplistic ***********

* ********** ****** *** *********** ******** accuracy ** ******* *** ***** **** it *** *******, *** ****** ***** false ******, ******** ** *** ******:

IPVM Image

*******, **** ********** ******** ** ******* in *** ***** ** *********** *** total *********** ** ** *********. *** example, ** * *** ********* ********* processed *** ****** *** ******** ** guns, *** * ****** *** ****, it ** **% ******** ** **** method, *** ****** ** ****** **** 100% ** *** ****.

** ****, ********* ********** ****** ** many ********* ************** **** ******** ***** algorithms. *** *******, ** *** ******** not ******* *** ****** **** ******** than ****** ****** ** ***** ****** misidentifying * **** ** * ******?

IPVM Image

******* ** ***** **************, ***** *** additional ******* ** ***** ******** ********.

Precision *** ******

******* ***** ********** ******** ************ *** its ************, ***** *** * *********** metrics **** ** ********** *** **** an ********* *****; ********* *** ******.

*********

********* ******** *** ***** * ********** object ** ******* (*.*. * ****** is * ******) ** *** ***** of **** ********* ** *** *********. Precision ******* ** ***** ********* ********.

****** ** *** ******* ** *** correct *** ******** ** ** ********* all ****** ******* (*.*. *** ******, all *****, *** ********) ** *** ratio ** **** ********* ** **** Positives **** ***** *********. ****** ******* as ***** ********* ********.

*******, ** ********* ***** **** ********* and ****** ****** ** *.*, *** in ****-***** *******, ** ********* ********* Recall ********* ** **** *****.

IPVM Image

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

********* ********** *** **** *** ********* finds ******* ********* *** **** *** take **** ******* ******* **** ** misses (***** *********), ** ********* ******* (True *********). ****** *********** ****** ******* systems ******* **** *********, *** ******** access ** *** ***** ******, *******, missed ************ (***** *********) *** *********** and ************* ****** *****.

*** *******, ** * **** ** a *** ********* ********* ********* **,*** people *** ******** * ****; * person **** *** * *** *** 3 **** *** ***, *** ****** 25 ******* **** *** ****. *** precision ** **** *** ********* ** 0.25.

  • ********* ********** * - **** *********
  • *** *** ***** ** - ***** negatives (**** *** ****** **** *********)
  • *********** ********** * - ***** *********

***** ********* ** *** ***** ** true ********* ** *** *********, *** precision **** ** * / * = **%. *******, **** ** **** that *** ****** ***** *** * substantial ****** ** ***** ********* **** are *** ******** **** *********.

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

****** ********** *** **** *** ********* detects *** ****** ******* *** **** not **** **** ******* *** **** it ********* ******* ***-******* ** *********** identifies ** ******. ****** ** **** commonly **** ** ***** ********* ********, especially **** ******* ** ********* ****** true ******** ********.

*** *******, *** *** ********* ******* above *** * ****** ** ~*.** (true ********* ** * / **** positives ** * + ***** ********* of **, *.*., * / **).

****** ** **** ***** ** *********** or **** ******** **** (***) *** is ******** *** *********** ********* ***********.

Sensitivity / **** ******** **** ** ***** ******** ****

*********** ** **** ******** **** (***) identifies *** **** ********* ***** **** be, **** **** *** *****.***** ******** **** (***) ********** *** likely ** ********* **** ***** ***** (both ******** *** ********).

******** *** *** ****** *** ** used ** ******* ********* ****** ****** testing, ** **** *** **** **********.

ROC ***** / **** ***** *****

******** *** *** *** ******* * Reciever ********* ************** (***) *****, ***** is **** ** ******* *** *********** of ******** ******. ************, *** **** under *** ***** (***) *** ** used ** ** ******* *********** *** accuracy.

IPVM Image

*** ****, ****** *** ***** ***** lines ********* * ********* ****** **** curves ******** ** *** ** *** left ********** **** *********** (**** **** Positives *** ******). *******, ******* *** ROC ***** ** **** ** ** many ****** ** ********* ********** ** TPR *** ***, ********** *** * secondary ****** ***** *** **** ***** the *** *****, ** ********* ***********:

IPVM Image

*** ** *** *-*********** **** ***** the *** ***** *** ** * value ******* * *** *, **** a ***** ** * ********** *** best ******** ***********.

*** ** ******** *** ******* *********** for *** **** *******:

  • ** ********* *** ******** ** *********/***** distinguishes ******* **** ************** (*.*. ****** vs *******)
  • ** ******** *** ******* ** *** model's ************** ************, ****** *** **** range ** *** *** *****.

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

  • ****** **** **** *** *** ************* strong *********** ** ******** ****, ************ in ***** ***** *********** ****** ** the ******** ******, *** *** *** reflect ****-***** ***********.

  • ** ***** ***** ***** *** **** disparities ** *** **** ** ***** negatives **. ***** *********, ** *** be ******** ** ******** *** **** of ************** *****. *** *******, **** doing ****** *********** ****** *******, *** likely **** ** ********** ********** ***** positives (**** ** **** ******* ** a *********** ******** ** ***** *********). AUC ***'* * ****** ****** *** this **** ** ************.

F1 ***** - ******** *******

******* ****** *** ********* ******** *********** is * *****'* * *****, ***** finds *** ******** ********* ******* ** Precision *** ******:

IPVM Image

* **** ** ***** ** ******** cited ** ******** ****** *********** ******** for ****** *********** ******* *********** *** correct ******* *** *** ******* ********/********* persons *** ********* ******* *********.

Mean ******* *********

******* ********* ****** *** ********* *********** is ***** **** ******* ********* ** determine *** ****** *** ***** ******* and ********** **** ****** **********, ******** to *** ******** ****** *****.

** ******* * ********* *** *** minimum ******** ************ **** *****, ******* will ********* ******** **** *** ********* a ****** *** **** *** ****** of *** ****** ** ********:

IPVM Image

**** ******* ********* ** *** ********** by ********* ********* ****** (*** *****), but ** ********* *** ******* **** of *** ******** ****** (********* ***) compared ** *** ****** *****:

IPVM Image

**** ******* ********* ** **** ** a ******* *** ****** ** ******* detection, ** **** ************ ***** *** likely *** ********* ***** *** **** of *** ****** *** ******** *** covered, **** **** **** ******* ** alert.

*******, ** ** ******** ** ***** related ** ******* ******* ********, ** incomplete ** ********** ******** *** **** to ****** ***********:

Fundamental ******** ******

************ ************ ****** *********** ********** ** analytics *********** **** ***** ******** ******; too **** ***** ********* *** ***** watchlists.

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

** ******* ************, *** ******* ** the ********* ** *** *** *** is ******** *** *********** *** ***** concerns, *** ********* **** ******* * non-trivial ****** ** ***** ********* **** create *********** ********.

*** **** ** ***** ****** ********* as *** ****** ** ******** *** analyzed, *** ***** ** * ***** differential ******* *** ****** ** ******** that ****** ** ******** ** **** negatives (*.*. ***-********* *********) *** **** positives (*.*. ****** *********).

IPVM Image

*** **** ****** **** ** ***** alert *******, ***** ***** ****** ** disable ****** **********. **** ** **** common **** ****** *** ** *********-***** analytics ***** ****** **** **** *** due ** ******** *** *******.

***** **** ******, *** *********** **** higher ****, ********* * ****** ***** on *****-******** ****** *********** ** * major ********* *** *** ***********, *** has **** ************* ****** ********** *** **.

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

**** * ****** *********** ********* ******** thousands, **** ** *********, **** ******* ***** (**** ****** ************ Test), ****** *********** ********* *********** ** important ** *****-******** ****.

*** *******, **** * ***,*** **** watch **** * **** ********** ********* will ****** ********* ** ***** ************, while *** ********** **** **** ****** false ************, *** ** * ************* lower **** ** ****** ** ****.

******* ************ *** *****, ****** * large ****** *********, ***** ** ***** to ** * ****** **** *** similar ****** ****** ******** ** **** the ********, *** **** ***** *********. This ** * ****** ***** *****, as *** ****** ** ***** *** known:

IPVM Image

**** ** ******** ***** ***********, **** known "*************" ****** ******** ** ******:

IPVM Image

*******, ********* ****** ******* ** ****** in ****** ***********, ***** ** ******* for ********* ******** ****** ********, ***** can ** ******-******* **** ***** ************.

Manufacturer *********** ****

** *** ******* ** ******* **** products, ************* **** *** *** ****** for ******** *** *********** **** ********** their ******** ****, ***** ** ***** misleading. **** **** ***** ******* **** by ****** * ****** *** **** with ******* *********.

IPVM Image

********, ************* **** ***** ****** ******** against ****-****** ******** (*.*.******* ***** ** *** **** - LFW), ***** *** *** ***********, *** commonly ******* ** **%+ ********.

******* *** **** ******* ************* *** is ********* *** ********** *** *** matter, ** ******* ** ********** ************ with ***** ******** *** ****** **** results. **** ****-***** ******** *** **** be ********** ******* **-******** *******.

Manufacturers **** **** ******** *****

**** ************* **** ************ **** **** ******** Rate *** ********, ***** ** *********** because ** ******* *** ******* **** it ******.

IPVM Image

*** *******, ** ***/**** ************ **** claim **% ******** *********** *** ************ characters ** * ******* *****, *** this ** ********* *** ****** **** were ****/********. **** ****** **** **** read *********** ***** ******* **** ******** metric, *** ****** **** **** *** seen ** ***, ***** ** ****** in *** ****-*****.

****** ****** **** ***** ****** ****** (vehicle *****, **** ******, *** *******, damaged ******, ******** ******) *** *** counted ******* *** ********, ***** **** not ******* *** ****-***** *********** ** the ******** ******.

Manufacturers *** *********

*** **** *********, ***** *** ** measurable ********* ******* ** ******* (*.*. WDR, ******* ** ***** ******) **** can ** ******** *** ***** **** they ****.

********, ************* **** ********* ******** ******, only ***** ******* ***** ********** **** accuracy:

IPVM Image

****'* ****-***** ******* ***** **** ********* often ******** ** **** "****" ** exceed **% ********, *** ** ************* and ********** **********, ********** ** ****** lights *** ***** *******.

****** ***** ************ ** ********** ************ (e.g. ****** *********** ****** *******, *** tolling) *** ****** ** ******** ***/*** than **** ****** ****** ** ******* detection.

Ranking *******

********* ********** ****** ** *******/******** ******* by ******** ** * ****** ****** analytic ********* ***** ** **** ****** search ********:

IPVM Image

******* ******* ****** * ***** ** verify *** *** *******, ****** **** by *********** ******* ***** * ************* accuracy/confidence *********.

*** ******* **** ******* ** ********* confidence ****** ** ********* ******* **** provide ********* ****** ** ** ******, making ** ********* ** ******* *******. It ** ****** *** ******* ** offer ******* (*.*. ****, ******, *** Low) ********** *******, *** *** ******* calculated ******.

****** *********** ******* *** ********* ** exception ** ****, ** **** ******* provide ********** *****:

IPVM Image

**** ********, ********* ******** ***** *** not ******* ** *** **** *********, making ****** ** **** ******* ********* impossible.

Comments (5)

***** *** ** **** *** **** class *****, *****. * ***** *** easy *** **** **** ** **********! I ** **** * ***** ********, you **** ****** ***** ******* ****** truth *** *** ****** ******* ********. What *** *** ******** ** ****** truth *** **** ******** ************, ** you ***** **** **** ** ** the ********* (*** ** *** ***)? Thank ***!

Agree
Disagree
Informative
Unhelpful
Funny

****** ***** (*** ***********/******) ******* ** machine *** **** ********, ********* ****** the *********** *** ******** ** *** algorithm.

Agree
Disagree
Informative: 3
Unhelpful
Funny

** ******** ** *** ****'* *****, ground ***** ** **** ******* **** model ** ******** **** *** ********** to ***** *********** ** *** ***** in ****-**** ********.

***** ** ******* ** */* ******* in *******/**** ******** ***** **** ****** truth *** ***** **********.

Agree
Disagree
Informative
Unhelpful
Funny

******** ** *** *** **** ******* when **** **** ** *********.

***********/***********, *********/****** ****** ** **** *** unbalanced ********.

***** **** ***********/***********, *********/****** ** **** it ******* ** ********* *****(******* *.*). In **** **** ***/*** ** ****** option.

***** ** ** ****** **** *** selecting ******** ****** *** *** ***** its *** ******* ** ***-**** ** are ******* ** *** ***** ***** we **** ** ******.

Agree
Disagree
Informative
Unhelpful
Funny

***** *****...**** ** **** ** ******...** is ** *********** ** ******* *** tricky ******* *** ** ******* **+% accuracy ******* ******* ***** ****** *** liar ** *** **** ****...***** ****** although ** **** ** **** * bit

Agree
Disagree
Informative
Unhelpful
Funny
Login to read this IPVM report.
Why do I need to log in?
IPVM conducts reporting, tutorials and software funded by subscriber's payments enabling us to offer the most independent, accurate and in-depth information.
Loading Related Reports