Motion Detection Performance Tested

Author: Benros Emata, Published on Sep 05, 2011

Motion detection is an important element of many, if not, most surveillance systems. It plays a central role in both storage search time reduction. Storage is routinely reduced by 30% - 80% by using motion based rather than continuous recording. Likewise, an investigator can often much faster find a relevant event by simply scanning through areas of motion rather than watching through all video.

At the same time there are a number of challenges associated with using motion detection:

  • Scene Conditions: The accuracy of motion detection and the amount of times motion is detected can vary depending on what's in the scene - people, cars, trees, leaves, etc. - and the time of day - night time with lots of noise, sunrise and sunset with direct sunlight into a camera, etc.
  • Performance of Detector: Motion detetion is built into many surveillance products - from DVRs to VMS systems and now IP cameras. As such, how well each one works can vary significantly.

Our Test

In this report, we share our results from a series of tests we performed to better understand motion detection performance.

We did a series of tests in different locations:

  • Indoor well light scene to simulate the simplest scene possible
  • Indoor dark scene (<1 lux) to examine what problems low light caused
  • Outdoor parking lot to see how a complex scene with trees, cars and people would perform
  • Roadway to see how a moderately complex scene with periodic cars would perform

Three IP cameras were used with their motion detection enabled to see differences in performance:

With these tests, we answered the following questions:

  • How can one estimate motion percentage accurately?
  • Does motion estimation vary significantly by scene?
  • How accurate was motion detection in each scene?
  • Did certain cameras exhibit greater false motion detection than others? What scenes or conditions drove those problems?

****** ********* ** ** ********* ******* ** ****, ** ***, most ************ *******. ** ***** * ******* **** ** **** storage ****** **** *********. ******* ** ********* ******* ** **% - **% ** ***** ****** ***** ****** **** ********** *********. Likewise, ** ************ *** ***** **** ****** **** * ******** event ** ****** ******** ******* ***** ** ****** ****** **** watching ******* *** *****.

** *** **** **** ***** *** * ****** ** ********** associated **** ***** ****** *********:

  • ***** **********: *** ******** ** ****** ********* *** *** ****** ** times ****** ** ******** *** **** ********* ** ****'* ** the ***** - ******, ****, *****, ******, ***. - *** the **** ** *** - ***** **** **** **** ** noise, ******* *** ****** **** ****** ******** **** * ******, etc.
  • *********** ** ********: ****** ******** ** ***** **** **** ************ ******** - from **** ** *** ******* *** *** ** *******. ** such, *** **** **** *** ***** *** **** *************.

Our ****

** **** ******, ** ***** *** ******* **** * ****** of ***** ** ********* ** ****** ********** ****** ********* ***********.

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

  • ****** **** ***** ***** ** ******** *** ******** ***** ********
  • ****** **** ***** (light ******
  • ******* ******* *** ** *** *** * ******* ***** **** trees, **** *** ****** ***** *******
  • ******* ** *** *** * ********** ******* ***** **** ******** cars ***** *******

***** ** ******* **** **** **** ***** ****** ********* ******* to *** *********** ** ***********:

**** ***** *****, ** ******** *** ********* *********:

  • *** *** *** ******** ****** ********** **********?
  • **** ****** ********** **** ************* ** *****?
  • *** ******** *** ****** ********* ** **** *****?
  • *** ******* ******* ******* ******* ***** ****** ********* **** ******? What ****** ** ********** ***** ***** ********?

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

Key ******** *** ***************

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

  • ** ****** ****** (*.*. **** ******** *** ****** ***), ********** percentage ** ****** ** ********** *************** *** *** * *** margin *** *****.
  • ** ******* ****** (*.*. *******, **** ***, ********* ********, *** vegetation) ********** ********* ** ****** ** ********* *** *** **** greatly.
  • ******** ** *********** ****** ******* ********* ************* ** *** ********** of *** ***** *********.
  • *** ***** ******* ********* ******* (** ***** *********/*********) ** *** very ****** ******* ****** ****
  • ** *** ******* *** **** *** ***** ******* ****** ** record ** ****** ** **** ********* *******, *** ** ********** and ******** *******
  • *** ******* ****** ****** *** *********** ***** ********* ** ***-*****/********* scenes ****** *** ** *****/**** ** **** ** **** *** is ******* **** *** ******'* ***. **** ******** ** **** continuous *********.

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

  • ****** *** ***** ** **** ******, ****** ********* ******** (*.*. masking, ***********, *** ****** ****) **** ****** **** ** ** optimized ** ***** ** ******* ********** ********
  • *** ***-***** ******, ******** ******** ******* ****. ****, ********** **** different ****** *****/****** ** *********** *** **** ************ ** ***-*****/********* scenarios
  • ** ******* ***** ********** ****** ** ******* ****** ** ***'* estimates *** ** *** ***

Daytime ****** (********** ******)

** **** ********, ****** ********* ** ********** *** *** *** interface ** *** *******. *** ******* *** **** ** ****** record *** * ****** ** *** *******. * ******* ****** the ***** ** ********* ****** ** ***** ****** ****** ********* during *** *** ****** ****. * ******** **** *** ****** recorded ***** *** ******** ******** ** ******** *****. **** **** on *** ******** '****' ********** ****** ******** ***** *** '****' indicates ** ***** *********.

********* *** ******** ******* **** *** ******* ******** ******** ****** during **** ** *** ***** ******* ******* **** *** *****. Also, **** ** ***********, ** ***** ********* **** ********* ****** times **** *** ******* *** *** ** *** *****. *** findings *** *** ********** ***** *** ********** ** *** *********** (narrow ***, ****** *** ********** ********, ** **********, *** ***** subject/object).

Nighttime ****** (********** ******)

** **** ********, ****** ********* ** ********** *** *** *** interface ** *** *******. *** ******* *** **** ** ****** record *** * ****** ** *** *******. * ******* ****** the ***** ** ********* ****** ** ***** ****** ****** ********* during *** *** ****** ****. * ******** **** *** ****** recorded ***** *** ******** ******** ** ******** *****. **** **** on *** ******** '****' ********** ****** ******** ***** *** '****' indicates ** ***** *********.

** **** ***-***** ***********, ****** *********/****** ******** *** ****** ********** across *** ***** *******. *** ******* *** ** ***** *** lighting ******* *********** '********' ****** ** ******** *** ** **** effectively ******* ** ********** ******* (**** ***** ******** ****). ** direct ******** *** ********* ***** '********' ***** ** ****** ******* throughout *** *** ****** ******** *** ** * ****** *** produced ** ********* ** *** (**** ***** ******** ****). *** Axis ******** *** **** ** ** *** ** *** ******* indoor *********, ******* ******/***-****** *************.

Daytime ******* (******* ******)

** **** ********, ****** ********* ** ********** *** *** *** interface ** *** *******. *** ******* *** **** ** ****** record *** * ****** ** ** *******. *** ****** ** organic *** ************** ** * **** ***** ************ ********. * snapshot **** *** ****** ******** ***** *** ******** ******** ** featured *****. **** **** ** *** ******** '****' ********** ****** recorded ***** *** '****' ********* ** ***** *********.

*** ********* ** ****** *********/********* ** **** ** *** ******** is ************ **** *** *** ***** ******* (~** - **% motion). *** **** ******* *********** (*.*., *****, ******* *** ***** lighting *******) ****** ***** * ****** ** ***** ********* ****** the *****. **** **** *** ********* ****** *********** ******** ********** the ** ****** ****, *** **** *** **** *** **** slightly **** ***** *********. *** ******* *** *** ***** ********* among *** ***** *** ***** ************ **** ********* **** *********** just ************** ******** ** ********* ****** (*.*. ***** *** ******* subjects).

24 **** ******* (******* ******)

*** ********* ** * ******** ** **** ******** ********* ** two ******* (******** *** *****) ********** ** ****** ****** ********** a ** **** ******. *** ******* **** *** **** ******* scene **** *** **** ***/**** *****. ***** ********** ******** **** insights **** *********** ** ****** *********/********* ************* ****** ********* ****** makes/models. **** **** *** *** ** **** ** ********** *** motion ********* ******** **** *** ****** *** *** **** ** the *** ********** ********.

**** ********* (*:**** - *:****)

****** *** ~* ***** ** ******** ******** ** *** ******** the ******* ****** ******** ************ ******* *********** **** *** **** camera ******* **** ********* **** *** ******* (*** **********) ****** settings. ** * ******, *** ******* ******** ************ ***** *********, whereas *** **** ** ************* ** ***** * ****** ** false *********.

******* (*:**** - *:****)

*** ******** ** ****** ** ** ** **** ***** ********, as ********* ** *** ******** ** * ******* ******** *** FoV ******** ** *** ****** ********* ******* ******. **** **** how *** ******* ****** ** ****** ************ ****** ***** ****** around *:**** (*** *****), ***** *** **** ***** ** ******** the **** ********* ** ****** *********/*********.

*** **** ***** ******** **** (**** ********** ******) ********* ** the ******* ***** ****** ** ******** *********** ***** **** *** Arecont ******** ******* ******* ** *** ********* ****** ****.

********* (*:**** - **:****)

**** ** *** *** ***** ** *** *******'* ***** *********** and **** ********** ********* ******** ****** *** *********/***-***** *****. *** playback ** ****** ** ** ** ******** ***** **** *** Arecont *** **** ******** ******.

***** ******* (*:**** - *:****)

** **** ******** ********, *** ******* ****** ** ****** **** to * **** ********* ********* ******** ** ******* (*** ****). However, ** ** ***** ******* **** ********* *** ***** ******** considerable ***** ********* *** * ****** ***** **** ***** ** recording ** ***-********* (~*:* ** **%). ** ******** *** **** continues ** ****** ****** ** ******* *** **** ********* ** in ******** **** *******.

Other ******* ****** *********

*** ********* ******** ******** ******* *** ****** *********/********* ******** ** two ******: (*) ***** ******* ***, *** (*) ****** ******. Motion *** *******/******* ** *** * ***** ** *** ******** recording *********** ** **** ******* ************ ******.

***** ******* *** & ****** ****** ****/****** ***** (*:**** - 5:30pm)

*** ******* *** ****** *********/********* ********* ** ******** ** *** timeline *** ********* ******** *** ********* ** ********. **** ********* were ** ********** ***** *** ******* *******. **** **** *** FoV ** ** **** ******** ***** *** ** **** *********** to *** ******* **** ** ********.

** *** ****** ****** *****, *** ******** ** *** ********* were *** ** ********** ***** ********/******.

***********

**** *** *** ***** (*) ******* **** ** *** '****** Based *********' *****:

  • ******* ********(****** $***) - *.*** */*; */*.*" ****; ****-**; *.*/* (*****/**)
  • **** *****(****** $***) - **** */*; */*" ****; **.* ******** ; 0.05 *** (**)
  • ********* **-*****(****** $***) - *.*** */*; */*" ***; **-*****/* ****; *.*/*.** lux (*****/**)

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

  • ******* ******** - ** *****
  • **** ***** - ** *.**.*
  • ********* **-***** - ** *.**
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 on VMS

Axis Camera Vulnerabilities From Google Researcher Analyzed on Mar 23, 2017
A Google security researcher has reported 6 vulnerabilities for Axis cameras, affecting multiple models and firmware versions. In this report, we...
OpenEye Takes Aim At Exacq on Mar 23, 2017
First Milestone targeted Exacq with a takeover offer, and now OpenEye is gunning for them with an offer to swap out Exacq for their cloud-managed...
VMS Update Automation Compared on Mar 20, 2017
Updating VMS software can be a tedious and time consuming processing, which historically has required users to access each machine, download update...
Uniview NVR Tested on Mar 02, 2017
Uniview, China's self proclaimed #3 video surveillance manufacturer behind Hikvision and Dahua, is ramping up its international sales efforts. In...
Bosch Favorability Results on Feb 27, 2017
Bosch is one of the most well known brands in the industry and they have combined recently with Sony in video surveillance. But how has Bosch...
Avigilon Favorability Results on Feb 27, 2017
One of the fastest growing companies has turned into one of the rockiest, as cooling growth, management turnover and a roller coaster stock price...
Artificial Intelligence Robot Assistant (ACTi) on Feb 23, 2017
Has artificial intelligence come to the video surveillance industry? ACTi has released 'SARA' which it bills as an 'AI assistant that brings...
Cutting Costs 70% Using Milestone With HD Analog on Feb 23, 2017
HD analog and enterprise VMSes are often thought of as being on opposite sides of the spectrum, with HD analog best for small jobs due to its low...
Exacq Favorability Results on Feb 22, 2017
For years, Exacq has been one of the most frequently favored VMSes in IPVM integrator statistics (e.g., see Favorite VMS Manufacturers...
Milestone: "Easy Money Days Are Over" on Feb 17, 2017
Contrary to IPVM's criticisms, Milestone has reaffirmed that glory days remain. But they admit that they 'easy money days are over': Are the...

Most Recent Industry Reports

Axis Camera Vulnerabilities From Google Researcher Analyzed on Mar 23, 2017
A Google security researcher has reported 6 vulnerabilities for Axis cameras, affecting multiple models and firmware versions. In this report, we...
OpenEye Takes Aim At Exacq on Mar 23, 2017
First Milestone targeted Exacq with a takeover offer, and now OpenEye is gunning for them with an offer to swap out Exacq for their cloud-managed...
Lock Keyways For Access Control Guide on Mar 23, 2017
Lock keyways can be the difference between a lock working or not. Understanding keyways is important for access control. Indeed, a member recently...
Broken Browser Support for Video Surveillance on Mar 22, 2017
Modern web browsers have left the security industry behind. Current Chrome, Firefox, and Microsoft Edge browsers do not support NPAPI plugins,...
ADI Favorability Results on Mar 22, 2017
150 North American integrators provided feedback on 6 distributors, and why they do (or do not do) business with ADI. ADI is clearly a big name in...
1 Million Dahua Devices Exposed To Backdoor on Mar 22, 2017
Statistics show that 1 million Dahua devices are publicly exposed and vulnerable to the Dahua backdoor. Despite this, Dahua has downplayed the...
Hikvision Hires Crisis Communication Writer on Mar 21, 2017
Hikvision has hired a crisis communication writer as the company ramps up its efforts to deal with the 'crisis' it feels it is facing. 'Crisis...
Glass Break Sensor Tutorial on Mar 21, 2017
Burglars often break glass windows to get into a house. Using glass break detectors in conjunction with alarm contacts is a good way to protect the...
Unikey Smart Phone Access Control Platform on Mar 21, 2017
More and more people carry smart phones. Many think this could replace the conventional key or card for access control. However, using a phone...
Hikvision Attacks IPVM on Mar 20, 2017
Hikvision has attacked IPVM repeatedly over the last month, both in the international press and in its dealer communications. Attacks Listed On...

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