How to Select Video Analytics

Author: John Honovich, Published on Dec 01, 2012

Selecting video analytics can be difficult because many factors impact the choice. In this report, we examine 8 important questions that should be addressed when evaluating video analytics.

The easy part is usually determining the type of video analytic you want (perimeter violation, abandoned object, etc.). The hard part is assessing how it works with your existing system, facility and operations.

Here are the 8 recommended questions:

  • How does your existing equipment impact choice of video analytics?
  • How will camera positioning impact the cost of video analytics?
  • How tolerant are you to false alerts?
  • How tolerant are you to missing a real event?
  • How many cameras will use video analytics?
  • How will you monitor the video analytic results?
  • How can you determine the performance of a video analytic system?
  • What is the total cost of the video analytic solution?

********* ***** ********* *** ** ********* ******* **** ******* ****** the ******. ** **** ******, ** ******* * ********* ********* that ****** ** ********* **** ********** ***** *********.

*** **** **** ** ******* *********** *** **** ** ***** analytic *** **** (********* *********, ********* ******, ***.). *** **** part ** ********* *** ** ***** **** **** ******** ******, facility *** **********.

**** *** *** * *********** *********:

  • *** **** **** ******** ********* ****** ****** ** ***** *********?
  • *** **** ****** *********** ****** *** **** ** ***** *********?
  • *** ******** *** *** ** ***** ******?
  • *** ******** *** *** ** ******* * **** *****?
  • *** **** ******* **** *** ***** *********?
  • *** **** *** ******* *** ***** ******** *******?
  • *** *** *** ********* *** *********** ** * ***** ******** system?
  • **** ** *** ***** **** ** *** ***** ******** ********?

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

How **** ******** ********* ****** ****** ** ***** *********?

**** *** ***** **** ******** ******* *** ***** ********** ******* (DVRs, ****, ** ***** ********, ***.) ********* ********. ****** *** can ******** **** ****** ** ******** ***** ********* ****, *** must ********** *** ********* *** *********** ** **** ******** ******* and ***** ********** ******.

**** ******** ******* **** ******* ********* *** ********* *** ***** analytics ******** **** ** *** *** **** ** **** *******. Only * ******** ********* ******* ***** *** ******* *** ***** this ********.

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

***** **** ***** ******** ************ **** ******** ******* *****. ** analog ****** ******** **-***** ***** *********. ******* *** ********* *********, only * **** ***** ********** ** ******* ** ******* ******* real ***** *********.

** *** *** ***** ****** *******, *** *** ******* *** camera ** ** ******* **** **** ***** ********* **** ** the ****** ** *** *** ****** * ****** **** ******* many ******** **** ****** ***** ** *** *******. ** *** are ***** **, **** ***** ******** ******* *** ***** *** to ******** *******/******* *** ***** *** **** ******* ***** ***** own *******.

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

**** * *** ***** ********** ******* ******* *****-** ***** *********. This *** ** ******** ** * ******** ******* ** ** a ******** ******. **** ** ***** *** ***** ********* **** and ******** ***** *********** **** *** ******** ********'* ********** ******. The ******** ** **** *** *** ***** ******* ** *** type ** ***** ********* *** *** *********** **** **** ******** manufacturer ********. **********, *****-** ***** ********* ******* ****** *** ********* applications.

** *** *** ******* ** *** * ********* ******'* ***** analytic, *** **** ****** ** *** ****** ** ***** ******** events *** ** ********* ** **** ***** ********** ******'* ********** client. *************, *** *** ***** ** *** ***** ********* *** be ********* ** **** ****** ******* ** ******* ******* ******** (depending ** **** **** ************ ****).

******* ** ***** ********* ** ******** ********** ******* ** *******. Since **** ******** ******** **** (** ******) ********** **** * single ****** **** *** ** ** ********* *********** *****.

**** ** ****

* ********** ******* ***** ** *** ***** ************ ******** ** whether ***** ********* ****** ** *** ** *** ****** (****) or *** ****** **** (****). *** *********** ******* ** **** for *** ***** **************, *** ******* ****** ** ********* ** analytic **** ** **** ***** **** **** ******** *******. **** you ********* **** **** ****** **** ***** *** ** **, you *** ********* *******. *********, *** *** **** **** ****** that ***** **** *********** ************ **** ******** **** ** ****** based ***** *********.

** **** ********, ** ******* ******* *** **** ** ********* ***** ******** ************* ********* **** vs ****.

How **** ****** *********** ****** *** **** ** ***** *********?

* ********* ********** *** *** ****** ** ***** ***** ********* is ****** ***********. *** ****** ** ************** *****, ****** *********** requirements *** **** * *********** ****** ** *** **** *** design ** ***** ******** *******. **** ** **** ******* *** are ********* ******* ******, ******, ***** ** *********.

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

** *** ****'* ****** ** ****** *** ***** ********* ******* are ********** *** ************ ***** *** ******* **** ** ** positioned. **** ****** ****** ******* ****** ***** ******* ******** *******, avoiding ****** ******** ** ******** *** ********** *** ****** ** incident **** *** ****** ** *** ****** (********** ************ ** *** ******** ********). ** *** ****** ***** **********, *********** *** ****** ************.

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

*** **** ** ****** **** ** ****** *** ****** *****. If *** **** ***** **********, ** *** ****** * **** significant *******. *** *** ******* **** *** **** **:

  • **** ** ******** ******
  • *** * *** ****** ** *** **** ****
  • *** * ***, **** *********, ******

** **** *****, *** **** **** ** **, ***** ************. Worse, *** *** ******* **** ********** ******** ***** (**** ** not ***** ******* ** *** ******* ** ****** *** ***** analytic ****** ********).

** *** ** **** ****** *** *******, ********* ** **** stop *** ******* **** ***** ********. *******, ** *** ** this ****** *** ******* *** *** * *******, *** **** may *** ******* **** *** *** *** **** *** **** bad *** *** ********** *** **** * *** ** *****.

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

******** * ******* ** ******** ********** ** ********* ****** *** dramatically ******** *** ********* ********* ****** ** ******* *****. **** if *********** ******** ** ******* **** ***********, **'* ***** *** feasible ** ********* **** ** ********** ******** ******* ** *** increased ******** **** **** ********.

***** **** ** ********* ********* **** ********* ******** ** **** and ******* **** **** ************, ***** ******** **** ******** ** be ** ********* ********** ** ***** ********* *** ***** ** come.

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

***** ********* ***** ** ***** ********* **** ******** ************, *** can ********* *** *** **** ******* ******* ** ************ *** lighting *** ******. **** *** ********* *** * ********* ***** analytics:

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

** ******* ***** *** ******** ** **** **** ** *** tests *** ** ********* **** ****** *********** **** ** *********** for **** ***** ***********. *** ********, *** **** ***** ******* from*-****:

sterile zone

**'* **** ******** **** * ****** ***** **** ** ******** in **** ********. ***, ******* * ****** ** *** ******** of * ******** ***** *** ***** ** *********** ** *** camera. ***, ******* * **** **** * ***** ** * security ****. *****, ***** **'* *** **** ******** ** ***** a ****** ** **** * ******** ******* *****'* * **** on *** *******.

**** ******** ** ********** ******* ** ******** * *******, ************ direct **** ** *** ******. **** **** ****** ** ****** performance **** *** **** ** *********** **** **** ***** *********** require.

** ****, **** **** ** *********** *********** ***** ** ** evaluated ** *** ******* ** *** *********** **** *** ** achieved.

*** **** ***** ** ** ****** ********** ** *** *******:

*** ****** *********** ** *** ************* ***** *** ***** *** layout ******** *** **** **** *** ** ****.

**** *** ********* *** *********** ** ****** *********** *** **** site, *** **** *** *********** ****** ******** ****** ****** **** clearer.

How ******** *** *** ** ***** ******?

***** ****** *** ***** ***** ********* ***** ********* ******* **** ********* *** ********** ** *** use ** ***** ******** *******.

*** ***** ******** ******* **** ***** ******. ***** ********* ****** differ ** *** **** ***** ****** **** ******** *** ***** what **********.

***** ***** ******** **** **** ******** **** ***** ** ***** alerts. *** *** ******** ** *** **** ***** ****** *** a **** ******** ****** *** ****** ******* ********? ** ** 5 * ***, *** *** ****? **** ** ****** ** the **** ** ***? ** *** *** ** ********** ** a ***** ******** ******, *** ********** **** ** **** **** and *** *** *********** ** ***** **** *** *** **** because ***** ****** *** **** ***** ******** ********. ** ** experience, **** *** *** #* ******.

****** *** ******* **** *********** ** **** ***** ********* ***** obscure *** ***** ****** ** ***** ****** *** *** ****** per ***. *** ***** *** ********** **** *** *** ****** is **% ******** *** **** **** *** ******* *** **** times *** *** *** ***** ********* ******** * ***** *****. A **% ******** ****** **** ******** * ***** ***** ***** hour ** ******** ***** ** ** * *********** ******** *** most *****. ** *** ***** ****, **** ******* *** *** being **** **** **** ************ ********* ********* ******* *** ****** is ** ********* ** *********** *** ***** **********.

***********, *** ***** ** *** ****** **** *** **** ***** alerts **** *** ********. ** ** ******* ** * ***** question, **** ** ***** * ******** ** *** *** **** to ******* ***** ******** ******.

*********, ***** ****** ******** *** **** ***** ****** **** *** willing ** **** **** *** *** *** *** ***** ****** would ****** ***** ******* **********.

How ******** *** *** ** ******* ** ****** *****?

***** ******** ******* *** **** ****** ****** **** **** *** supposed ** ***** ** (****** ***** ********* ******* *** ****** falsely ******* **** ******* ********).

**** ********** ****** ******* ***** ** ****** ***** **** ** actual *****. **** ** ******* ** *** *** ** * war **** ** ***** ******** ******** ***** * ****** ***** can ****** ** ******* ********** ** *** *********** ** * critical *****.

** **** *********** *** ********* ***** **** ** *****, *** will **** ** ****** **** ** ****** ********* *** ************* modifications ** ****** ******* *** *********** ** *** ******. *** common ******** ** **** *** ******** ********** ** *** *** of ******* ******* ***/** *********** ******* ** ***** ********* (**** if ** ****** ********** *******). ** ** **** ****** *** these ********* *** **** ******** ******* ** ****** ************* ********** to ** **** ** ********* ***** ***** ******** ******* *** the ***** ****** ** **** **** ******. *******, **** ***** deploy ***** ****** ******* ***** **** *** ***** ********* ** minimize *** ********** **** ** ****** ***** ** ******. ** this *************, ***** ****** **** ******** *** *** ** ********** since ** ******* ***** *********.

*******, **** ***** ******** ***** **** ** ** ****** ******** to ***** *********. ** ** ****** *** ***** ********* ** be **** ** ********** ** *** ******** ** ********** **** previously ****** ********** ** ***. ** ***** *********, ***** ****** will ** *** ******* *******.

** ************ ** ***** ********* *** ****** ** **********, ******* a ***** ********** ** ****** ****** *** *** ** *********. In ***** ************, ***** ***** **** ****** ***** *** ******* trends (******, *******, ***.) *** *** ********* ******.

How **** ******* **** *** ***** *********?

*** **** ******* *** ****, *** **** ******** **** (*) false ****** ****** *** (*) **** *** ***** ********* ********* with **** ********** *******.

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

***'* *** * ****** **** ***** ********* ********* * ***** alerts *** ***. **** *** ** ********** *** * ***** to ****** ********** *** *** **** ***** ***** ****************.

*** ***'* *** *** **** *** *******. ****'* *** ***** alerts *** *** ** * ***** * *******. ** **** point, **'* ******** **** ****** ***** ******* **** ****** **** were ********* ****** ** **** ****.

****** **** * *** ******* *** *** *********** *** ****** of **** ******. ***** ********* ***** ******** ******* ******** *** generate *** ********* ****** ** ***** ****** (**** ********* ** the ***********), *** ***** *** ****** **** *** **** **** becomes ** *****.

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

** *** **** * ***** **** ** **** * ***** number ** *******, *** *** ** **** ** ******* **** video ******** ****** ********** **** **** ***** ********** ** **** access *******. *******, ****** ********** ****** ****** ****** ***** *********** between ******* ********** *** * ****** **** *********. **** ************ us *** ****** ******* ******, **** *** ***** ********** *** other *** ****.

******** ** ** **** ******** ****, *** **** ******* ***** analytics *** ***** *** **, *** **** ******** ** ******* to ********* *** ******** ****** **** **** ********. *** ** we ********* ** *** ***** ********, **** *** ** ********* to ********** ******* ** ***************** *** **** ** ******* ******* systems.

How **** *** ******* *** ***** ******** *******?

********** ***** ********* ** * *********** ** ********** *** ******. The ****** ******* ** ***** ********** ** ** ** *** last **** ** *** ********** *******, **** ********* ***** *** system ** ********* *** *********.

***********, ******* ********** ** ******** ** ******** **** ***** ******** alerts *** ********* ** *** ****** ** ******** *****.

*** ********* ******* ** **** ****** *** ****** **** *** video ******** ****** *** ***** ** ** ***** ******. **** is *** ** ****** ** ***** ********* *** **** **** stating **** ****** *** ******* ****** *** ***** ******. ** is ****** * **** ** ****.

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

***** ***** ********* *** ******* ******* ** ******* ********, **** are ******* **** ** ********* ** *********** ******* ******. ************, any ***** ******** ****** **** **** ** ********* ** * small ****** ** ******* ********, ** *** ** ********** ** complex ** ******* **** *** *** ********** **** *** ** substantial. *******, **** ************* ****** ****** ****** **** ********** ** numerous ***** ******** ****** ***** *** ***. ** ****, ********* into****** ************ ********** ********* ******** *********** ** *** **** ********* *** ****** ****** them ** **** ***.

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

*******, *****, ****** ***** ******** ***** **** ** ** **-***** monitoring ** ***** ******** ******. ***** *** * ****** ******* for ****:

  • **** ****** ** * ***** ****** **** * ***/*****: ** the ****** *** ********** ****** *** *** ****** ***** ******, you *** ****** *** ** ** ***** ** ** ********** to ** ******** **********. **** *** **** **** **** *** procedures **** *** ***** ********** ********** ** ******* ******. ** course, ** ******* **** *** **** *********** *****. ** *** have **** **** * *** ***** *******, **** ** ****** to ********* *** ********* *** ********.
  • **** * ******** ******** ***** *** ****** ** ***** ****: This ** *** **** ****** ******** *** ***-**** ************* **** campus ** ***** ** ********* *****. *** *** ****** ** that *** ****** ** ***** ****** ********** *** ***** *** the ***** ***** ****** *********.
  • *** ** **** *** ******** ********* *******: **** ** *** most ********* *** ** ** **** ** *** **** ******** or ********* ** ***** ********* ** ******** *********. ******, ** this *****, *** *** *********** ******* **** *** ******** ********** station. **** ***** ************ ** **** **** ************** ** *****.

How *** *** ********* ***** ******** ****** ***********?

************* ** *********** ***** ** ***** ********* *********** *** ******** available. **** ** **** ****, *** **** ******* *** *** represent *** *********** *** ****** ****** ** **** ********** (** the ************* ** ****** ***** *** ****** **** *****).

***********, * ***** *** ****** *** ********** **** *** ******. There's ****** *** **** ********* *** ** ************ **** * vendor *** ********* ** ***** **********.

*** *** **** ***** *** *** **** ** ********* *********** is:

  • Ask * *********: While references are always a good idea, you should target two key questions when asking a reference: (1) How many false alerts do they have per day per camera? This is usually pretty easy for the other party to know and something they are likely to share accurately. (2) What is their camera setup? Do they have new cameras or old cameras? Where are the cameras mounted? Given that this reference, their results are probably going to be good (or else the vendor would not have shared it with you). Asking about operational details can help identify some logistical or equipment advantages they have, that you may not.
  • Do **** *** ****: The reality is everyone who deploys video analytics has to do their own test. It's not ideal and it is time consuming but it really must be done. This is a good idea not simply because of the products available but because their performance can differ significantly based on your environment and existing infrastructure. Also, tests will help you learn about the types of nuisances you will face in production, helping you to better set expectations on the system.

What ** *** ***** **** ** *** ***** ********* ********?

** *******, *************** ***** ********** ***** **** **** ** ******** favor **** ********* ******** ** **** *** ** ******* *** justifying ****** ********. **** ** ********** **** ** ****** ******* segments ***** *** ************* ** ******** *** **** ******* *** the ******** **** ****** ** ** **** *******.

******* ***** ********* ** *** * ****** ******, *** ***** cost ** **** *********, **** ** **** *** ********** ******* cost. ***** ******** *********** *** **** ************. ****, *** ***** analytics ***** **** ***** ******* *** *** ** ********* *** differ ******* ** ******.

*** **** ** *** ***** ******** ******** ********** ***** **** free ** ***** $*,*** *** (**** ***** ********* *** ******* into ******* ** * ** ********** *** ******* *** *** analytics).

** ******** ** *** ****** ******* ****, *** ****** ****** in:

  • *** **** ** *** *** *******
  • *** **** ** ********* ******** *******
  • *** **** ** *********** **** ***** ********* ****** **** ***** security ** *********** *******
  • *** ******* *********** **** ** ********** *** ***** ********* *******

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

**********

***** ********* ****** **** *** ******* ******* ******** ******* *** to ******** *** ********* **** ****** **** **********.

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

Automatic Door Operators For Access Tutorial on Sep 20, 2017
Opening and closing doors might sound simple, but it takes a high-tech piece of door hardware to pull it off. Integrating automatic door operators...
Master Keying Tutorial on Sep 14, 2017
Mechanical keys are the most fundamental, albeit unsophisticated, form of access control. Like access control, Master Keying allows large scale use...
Startup Turing Video Segway-Based Security Robot Profile on Sep 13, 2017
If security robots can not replace guards, perhaps the next best thing is a robot the guard can actually ride.  Turing Video has raised $5...
Fail Safe vs. Fail Secure Tutorial on Sep 13, 2017
Few terms carry greater importance in access control than 'fail safe' and 'fail secure'. Access control professionals must know how these concepts...
BBC Featured Deep Learning Face Recognition Analyzed (Digital Barriers) on Aug 30, 2017
The UK's largest broadcaster, BBC, recently featured Digital Barriers (also based in the UK) on a segment highlighting face recognition technology....
Nvidia For Video Surveillance Examined on Aug 23, 2017
Nvidia is making a big push into the security market, claiming more than 50 partners, investing heavily in industry events, positioning their GPUs...
Super Low Light Surveillance Guide on Aug 01, 2017
At the beginning of this decade, low light performance of megapixel cameras was generally terrible. This was the era of super slow shutter where...
Healthy Skepticism for Deep Learning Is Prudent on Jul 26, 2017
The hype for deep learning in video surveillance is accelerating. Between the race to the bottom and dearth of a 'next big thing', certainly pent...
Hikvision Launching Deep Learning Recorders on Jul 20, 2017
Hikvision has become a common choice for super low cost NVRs. Now, Hikvision is aiming to move up market, with deep learning NVRs that claim far...
Microsoft Video AI Cloud Services Examined on Jul 18, 2017
Microsoft has released one of the most amazing video analytics marketing videos ever. In it, they detect oil spills, track individual people giving...

Most Recent Industry Reports

Reseting IP Cameras - 30 Manufacturer Directory on Sep 22, 2017
Every camera has a reset button (well, almost) but it is not always clear what these buttons do, how long they need to be held, what settings they...
80+ OEMs Verified Vulnerable To Hikvision Backdoor on Sep 22, 2017
Over 80 Hikvision OEM partners, including ADI, Interlogix, LTS, and Northern Video, have been verified as having products vulnerable to the...
Genetec Launches Cloud Access Control (Synergis SaaS) on Sep 21, 2017
Genetec's cloud everything expansion continues, with their announcement of Synergis SaaS edition, joining their cloud video offering Stratocast,...
Genetec CEO Warns Against Insider Threats on Sep 21, 2017
With Dahua and Hikvision cybersecurity issues becoming indisputable, a new counter has emerged. Just put them behind a firewall, buy cheap...
New IPVM Calculator V3 Released on Sep 20, 2017
The New IPVM Calculator V3 is released. An entirely new architecture delivers the following benefits: Turbo The calculator is now ~50% faster in...
Automatic Door Operators For Access Tutorial on Sep 20, 2017
Opening and closing doors might sound simple, but it takes a high-tech piece of door hardware to pull it off. Integrating automatic door operators...
'Clowns' Allege Ubiquiti 'Completely Fraudulent' on Sep 20, 2017
A short seller has alleged Ubiquiti is 'completely fraudulent'. Ubiquiti's CEO has responded calling them 'clowns'. Here is the short...
Avigilon 'Blue' Cloud Entry Examined on Sep 19, 2017
Avigilon is moving to the cloud. The company announced their Avigilon Blue platform, designed to be a web-managed surveillance system, utilizing...
HID Buys Mercury Security on Sep 19, 2017
One of the biggest access control deals in years. Mercury Security, the most widely used access hardware OEM, and partner to 20+ manufacturers,...
Hikvision Backdoor Exploit on Sep 18, 2017
Full disclosure to the Hikvision backdoor has been released, allowing easy exploit of vulnerable Hikvision IP cameras. As the researcher, Monte...

The world's leading video surveillance information source, IPVM provides the best reporting, testing and training for 10,000+ members globally. Dedicated to independent and objective information, we uniquely refuse any and all advertisements, sponsorship and consulting from manufacturers.

About | FAQ | Contact