Axis Guard Suite Video Analytics Tested

By: Rob Kilpatrick, Published on Jun 25, 2018

In 2015, we declared Axis' Guard Suite analytics "weak", with missed detections and false alerts common. But after nearly 3 years and a 2.0 version release, has this improved?

We tested Motion Guard, Fence Guard, and Loitering Guard to find out, using two cameras:

And in multiple scenes outdoors and indoors, examining:

  • Configuration and calibration
  • False alert performance
  • Detection range
  • Comparison to Axis VMD4
  • Camera compatibility

Readers should also see our other updated camera analytics tests, including Axis VMD4Bosch IVA Video Analytics And Motion+ VMDHanwha Wisenet X AnalyticsHikvision Intrusion Analytics, and Dahua Intrusion Analytics.

** ****, ** ************' ***** ***** ********* "weak", **** ****** ********** and ***** ****** ******. But ***** ****** * years *** * *.* version *******, *** **** improved?

** ****** ****** *****, ***** Guard, *** ********* ***** to **** ***, ***** two *******:

*** ** ******** ****** outdoors *** *******, *********:

  • ************* *** ***********
  • ***** ***** ***********
  • ********* *****
  • ********** ****** ****
  • ****** *************

******* ****** **** *** our ***** ******* ****** analytics *****, ********* **** ********* *** ***** ********* And ******+ ********* ******* * ****************** ********* *********, *** ***** ********* *********.

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

Guard ***** *********** *******

*** ***** ***** ************ (Motion, *****, *********) ******** from ***** ****** ****** by *****, *******, *** rain ********, **** ******* *********** to **** ** ***** issues.

************, ********* ******** ** all ************ *** *********** reduced **** ********** ******* object ******** *** ** such ** ********* ********* these ***** **** *** FOV ******* ** ********** to *********** **** *** settings *******.

*******, ** *** **** side, ********* ** ****** from ***** ******* *** solid due ** *** ******** perspective ***********, **** **** few ****** (* *** *-* days) ****** ** ******* in * **** ** testing.

Detection *********** *********

** ******** ** ***** overall ********, ** ***** these *** ******** ******** to **** ***** ***** application ** *** *****:

****** *****

****** ***** ******** ******** subjects ** ~**-** ***, ~150' ********/***' **** ** the ***** *** **' distance/~185' **** ** *** P3225, **** ** ***** negatives/missed ********** ** *** tests. 

***** ***** 

********* ** *******/******** ******** *** much **************** ** *** ******** tests, ***** ***** ******* were *** ******** ** did *** *****. ********* range *** ******* ** Motion ***** (~**-** ***), regardless ** ********* ** travel/virtual ******** *********. ** with ***** ******* ******** analytics, ***** ********* ****** be ********* **********, ** shadows *** ***** ** at ******** ***** ** day, ******* ******.

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

********* ***** ********* *********** like ****** ***** **** a **** ****** ******* detection **** (******* ** 120 *******), **** ** missed *********** ** *** testing. ********* ***** *** ******** less ***** ** ***** alerts **** ***** ******** to ******, *** ** its ********* ***** ****, though ***** ******** **** regular ****** *** ** blowing ***** *** *******.

Motion ***** **. **** 

******** ** ****, ****** Guard ******** **** ***** false ****** ** ***** animals *** ** ***** Suite's *********** ***********. **** could ** ******** ** reject ***** ****** ** increasing ******* ****** ****, but ** *** ******* of ********* *****, ***** Motion ***** **** *** require.

******* ** ****, *** Axis ***** ******* *** the **** ********** ****** analytic, ****** ***** ** recommended, ********** ** * series ******* ***** *** install ** *** ****.

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

**** ***** ***** ** compatible **** *** **** cameras ******* ******** *.* or ******, ***** ****** most ****** (*-* ***** old) *, *, *** Q ********.

*** ************ *** **** for * ****** *******, and ~$** *** *** others, *** ***********, *.*., running **** ****** *** Fence ***** ** * single ****** ***** **** $120.

Configuration *** ***********

*** ***** ***** ***** applications ***** **** ****** configuration *******, **** ** small ******, ******* ******, and *****-***** ****** *******, though ***** **** ******** depending ** *** ******** (loitering **** *** ******* short *****, *** *******, as ***** ***** ******* would *** ****** ** nature).

*** **** ******* ************* change **** **** ** the ********* ** *********** in ***** ****** *******. Users ***** *** ** more *****/**** ** ******* of ***** ****** (********* people) ** *** ***** of ****, *** ***** the ******'* ******, ***** here:

***** *** **** ******** define ***** ****** ******** manually, ** ** ******** versions *** ****/*. ** review **** ******* *** the ********* ** **** analytic ** **** *****:

Beware: ******* ****** ******* ********* *****

********* ******** *** ********* by **** **% **** swaying ****** ******** **** increased **** ******* (*%) to *** (**%) ** ignore ******* *****. ******** decreased ** ~**' **** 150' ** *** ***** (shown *****) *** ~**' from ~**' ** *** P3225-LVE ** **.

Common ******: *****/*******/****

********** *******, ******* ***** was * ****** ***** among *** ***** ***** applications, ******* ******** ***** alerts. **** **** ********* these *****, ***** ****** be ******* ** ***** space ******* ***** *** detection *****, ** ******** boxes *** ****** ****** further **** ********, ******* false ******.

********* ***** **** ******** **** false ****** ****** ** swaying ***** ** ***** "Time ** ****" ******** of **-** *******, **** foliage/brush ********** **** ****** to *****.

******* **** **** ********** caused ******, ***** ********** Motion ***** *** ***** Guard, ***** *****.

*******, *** ***** ************ had issues **** ******** ******* false ******, ******* ** **** other ****** ********* ** have ******.

Motion ***** ***********

********, ****** ***** *** not ***** ** ***** animals, * ****** ***** during **** *******, ** well ** ***** *********.

*******, ****** ***** *** not ***** ** ****** false ***** ******* **** as ******* ***** ******* in *** ***** ** view.

 

****** ***** ************ ******** ******** at ~**-** *** **** day *** *****. **** results ** *** ********* outdoor ******/*** ****** ** cameras ******:

  • *****-*** (*** **:*): ~***' **** *****/~***' ********
  • *****-*** **** (*** **:*) ~196' **** *****/~***' ********

Improved ***** ***** ***********

****** *******, ***** ***** consistently ******* ** ******** crossing *** **** ** ~90'/10PPF. ***** ***** **** captured ******** ***** ********** ** *** ******* tests, ********* ******** ******* across *** ***, **** during *** ***:

** **** ** ** night, ****** *** ******* *** difficult ** **** ********.

*******, ** *** ** issues ********* ****** ******* very ****** ** ********, shown *****:

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

********* ***** *** *** fail ** ****** *** loitering ********, *** ** night, ** *** *****. Objects *** *********** ********* to ****** *****, *** with *** ******** ** a *****/*** ***** ***** as *** ****** *******, alarming **** ****:

**** **** **** ********* Guard **** *** ***** for * ******* ****** of ******* *******, *** instance **** ******** ** a ***** ** ***** or ****. *** "*****" setting ** ********* ***** refers ******* ** ******* loitering ** ********** ***** on * ****** ****** individually, ** ** *** objects ** *** ***** (e.g., ** **** ** any ******* ******* *** 120 *******, *** ******* is **********), *********** **** of * ******* ****** than *********** **********.

Versions ****

*** ********* ******** *** software ******** **** **** during *******:

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

Comments (12)

This is the latest in our series of updated analytics testing. Next up are Avigilon's H4 analytics (camera based, with Appearance Search and UMD later) and Axis Perimeter Defender.

Readers should also see our others in this series:

When you get to perimeter defender, could you also include an axis thermal camera? 

That is usualy what's recomended for such application, and it would be interesting to see how they perform compared to eo cameras. (given that you mount them side by side during your test) 

It would be really nice to see comparison side by side Avigilon, Axis and Bosch analytics. I mean same scene same situations and compare the results from 1 week testing.

Finally, we saw no issues detecting people walking very slowly or crawling, shown below

If it cannot eliminate the false alarms from other motion, this really is not that impressive.

It's all impressive and far better than not using analytics. 

"Analytics", to me, infers the ability for the system to make intelligent decisions with repeatable or predictable results. Intelligent decisions would mean ignoring general motion and only alerting on specific objects of interest.  Based on the test results here, the Axis system failed to show significant intelligence, as it had several false alarms.  There is nothing to indicate it detected a "person" crawling, just that it saw the crawling as the same kind of random motion it picked up elsewhere and was unable to classify or filter out.

Such a system is, to me, nowhere near "far better than not using analytics", as it just generates random alarms and can't be trusted.

I think that it all depends on your application and reason of using analytics rule.  If you want to go through all activity the next day to see what went on, then this analytics could help you accomplish this faster. It would at least reduce drastically the number of events compared to if you would have simply relied on motion detection.

I think that as one of the leading manufacturer of IP cameras, Axis needs to be more competitive in this aspect of their products. As per many who I have talked to that attended the Axis Summit in Jamaica, they mention that they are focusing and investing on improving their analytics. They also mentioned that most partners where not even using analytics yet so I guess some of us are just a little ahead in that sense.

Let's wait and see what this gives in the next couple of months!

To be clear, we are not saying that it's impressive that it detects people running or crawling. It should detect those people. 

It was specifically called out only because in our original test of Fence Guard, it failed to detect in these cases. I clarified that in the text.

Analytics are not and will never (for a long time, anyway) be 100%. Users should expect false alarms regardless of the vendor. What noise would you receive without analytics? This is my point. If this does not make sense, please explain. 

Where does it say that they analytics failed to classify the crawling person vs. 'random motion' as you say? The crawling person displayed a green box that turned red upon crossing the line. This suggests the person was detected and triggered the line. Again, not sure what I'm misunderstanding but I'd genuinely like to know. 

 

The shadows crossing the line showed the exact same response:

Given that it failed to properly suppress the shadows and false motion, there is no reason to believe the alarm on the crawling person was anything more than accidental. Going on the results of this test as shown here, the system did not exhibit signs of being able to actually be used to detect crawling people in a manner that would not generate excessive false alarms.

The thing is that if you have used solid analytics like Avigilon, although they are not 100% they are VERY high up there. Avigilon has AI which over time increases efficiency or the analytic rules and eliminates some detections that at the time of install would have generated a false alarm.

At our monitoring central we monitor several hundreds of Avigilon cameras and sometimes we can go many minutes without one single event. A lot has to do with the the way these rules are configured by our integrators and the understanding of how they work.

One thing that I find amazing is that on all analytic solutions that I have tested or used,  Avigilon is way ahead as the best solution but what amazes me is that it is also by far the simplest to configure.

Excellent performance! Feet planted, both hands thrust into front pockets, sporadic movement, furtive glances throughout; capturing the very essence of loitering.  

 

Login to read this IPVM report.

Related Reports

Uniview Deep Learning Camera Tested on Jul 14, 2020
Uniview's intrusion analytics have performed poorly in our shootouts. Now,...
Video Analytics 101 on Mar 16, 2020
This guide teaches the fundamentals of video surveillance...
Dahua Smart Motion Detection Camera Tested on Mar 03, 2020
Dahua has introduced Smart Motion Detection, AI-based VMD, claiming to use an...
Sunell Panda Cam Body Temperature Measurement Camera Tested on May 14, 2020
Sunell is far less well known than its gargantuan domestic competitors Dahua...
Dahua, Hikvision, ZKTeco Face Mask Detection Shootout on Jun 19, 2020
Temperature tablets with face mask detection are one of the hottest trends in...
Vivotek LPR Camera Tested on Apr 15, 2020
Vivotek has historically sold license plate capture cameras but not LPR. Now,...
Tiandy Super Starlight Cameras Tested on Apr 30, 2020
Tiandy is taking aim at China competitors Dahua and Hikvision, with a new...
Dahua Critical Cloud Vulnerabilities on May 12, 2020
Dahua has acknowledged a series of cloud vulnerabilities that researcher...
Video Surveillance Cameras 101 on Feb 25, 2020
Cameras come in many shapes, sizes and specifications. This 101 examines the...
Don't Deceive. Lessons From Scott Schafer on Mar 20, 2020
Deception is bad. We can learn some important lessons from Scott Schafer, a...
K7 Wall Mounted IR Temp Gun Tested on Jun 26, 2020
The original K3 model was missing a number of important features but the...
Dynamic vs Static IP Addresses Tutorial on Apr 16, 2020
While many cameras default to DHCP out of the box, that does not mean you...
Milestone Presents XProtect On AWS on May 04, 2020
Milestone presented its XProtect on AWS offering at the April 2020 IPVM New...
World IEC Fever Screening Standards Explained on May 04, 2020
While 'fever detection' is new to most people, the technology has been...
Fever Camera Sales From Integrators Surveyed on Jun 01, 2020
Fever cameras are the hottest trend in video surveillance currently but how...

Recent Reports

Dangerous Hikvision Fever Camera Showcased by Chilean City on Aug 07, 2020
Deploying a fever camera outdoors, in the rain, with no black body, is...
"Grand Slam" For Pelco's PE Firm, A Risk For Motorola on Aug 07, 2020
The word "Pelco" and "grand slam" have not been said together for many years....
FLIR Stock Falls, Admits 'Decelerating' Demand For Temperature Screening on Aug 07, 2020
Is the boom going to bust for temperature screening? FLIR disappointed...
VSaaS Will Hurt Integrators on Aug 06, 2020
VSaaS will hurt integrators, there is no question about that. How much...
Dogs For Coronavirus Screening Examined on Aug 06, 2020
While thermal temperature screening is the surveillance industry's most...
ADT Slides Back, Disappointing Results, Poor Commercial Performance on Aug 06, 2020
While ADT had an incredible start to the week, driven by the Google...
AHJ / Authority Having Jurisdiction Tutorial on Aug 06, 2020
One of the most powerful yet often underappreciated characters in all of the...
SIA Coaches Sellers on NDAA 889B Blacklist Workarounds on Aug 05, 2020
Last month SIA demanded that NDAA 899B "must be delayed". Now that they have...
ADI Returns To Growth, Back To 'Pre-COVID Levels' on Aug 05, 2020
While ADI was hit hard in April, with revenue declining 21%, the company's...
Exposing Fever Tablet Suppliers and 40+ Relabelers on Aug 05, 2020
IPVM has found 40+ USA and EU companies relabeling fever tablets designed,...
Indian Government Restricts PRC Manufacturers From Public Projects on Aug 04, 2020
In a move that mirrors the U.S. government’s ban on Dahua and Hikvision...
Directory of 201 "Fever" Camera Suppliers on Aug 04, 2020
This directory provides a list of "Fever" scanning thermal camera providers...
Face Masks Increase Face Recognition Errors Says NIST on Aug 04, 2020
COVID-19 has led to widespread facemask use, which as IPVM testing has shown...
Dahua Loses Australian Medical Device Approval on Aug 04, 2020
Dahua has cancelled its medical device registration after "discussions" with...
Google Invests in ADT, ADT Stock Soars on Aug 03, 2020
Google has announced a $450 million investment in the Florida-based security...