Milestone LPR Tested

By: Ethan Ace, Published on Mar 31, 2015

How well does Milestone's LPR work?

Milestone's LPR supports off the shelf IP cameras, integrating license plate recognition with the Milestone Smart Client for live video, playback, and alarms.

We tested Milestone's LPR with three cameras including Avigilon's H3 integrated IR bullet, Bosch's Super Low Light Starlight 5MP, and Messoa's specialty license plate capture cam, the LPR606.

The 1 minute video excerpt below, from our 15 minutes of video inside, gives an overview of Milestone's LPR:

The report answers the following key questions:

  • How accurate was Milestone's LPR?
  • What accuracy variance existed across the three cameras tested - Avigilon, Bosch and Messoa?
  • What factors most contributed to missed plates and inaccurate recognition?
  • What setup issues / factors do you need to factor in?
  • What processing load / server impact should you expect?
  • What issues caused missed plates and improper recognition?
  • How does it compare to Genetec's AutoVu LPR?
  • *** **** **** *********'* LPR ****?

    *********'* *** ******** *** the ***** ** *******, integrating ******* ***** *********** with *** ********* ***** ****** for **** *****, ********, and ******.

    ** ****** *********'* *** with ***** ******* ********* ********'* ** ********** ** bullet,*****'* ***** *** ***** Starlight ***, *** ******'* ********* license ************ ***, *** ******.

    *** * ****** ***** excerpt *****, **** *** 15 ******* ** ***** inside, ***** ** ******** of *********'* ***:

    *** ****** ******* *** following *** *********:

    • *** ******** *** *********'* ***?
    • **** ******** ******** ******* across *** ***** ******* tested - ********, ***** and ******?
    • **** ******* **** *********** to ****** ****** *** inaccurate ***********?
    • **** ***** ****** / factors ** *** **** to ****** **?
    • **** ********** **** / server ****** ****** *** expect?
    • **** ****** ****** ****** plates *** ******** ***********?
    • *** **** ** ******* to*******'* ****** ***?

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

    Key ********

    **** *** *** *** findings **** **** ****:

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

    • ********** ** ******* ********* similarly, ********** ********* *** *********** ~95% ** ****** ****** the *** *** ~**% of ****** ** ***** with ******** *** ** 1/250 ****** (****** *******).
    • ******** ********** ** ****** was ****** ** ******* plates ***** ******* */*** exposure *** ** ************ and ******* ** ******* plates.
    • ***-** ******* ********** ********** ***** 94% ** ****** ****** the ***. ** *****, non-IR ******* ******** ********** only ~**% ** ******, as ~**% ** ******* plates **** *** ****** up ** ***, **** only **% ** ***** read ********** **********.
    • *********** ******** *** ******* at ******* ******, **** ~15 ** ~** ***.
    • **** ***** *** **** using ********* *********** ********, <1 ****** ******* ******* passing *** *** ***** generation.

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

    • *** **** ****** ******* issues **** ********* ********** (0 *** *, * for *, ***.) *** failing ** **** *** or **** *********, ********* first ** **** ** the *****.
    • ****** **** ************ **** multiple ***** ** **** vehicle, **** ** ***** one ** ***** ***** being *******.
    • *** ***** ** ***-***** lettering **** ** *****, UPS, ***** *******, ***., only * ***** *** of *** *****.
    • ***-** ******* **** ***** missed ** ******* ****** due ** ***** ****** being *** *** ** gain/digital ***** ****** ***** too ****, **** ********* plate ********** ********* ** fully.

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

    • *** ***********, *** ***** rate ***** ******* *********** by ********* **************, ***** substantially **** *********/******* **** H.264.
    • ********** ** * ****** LPR ****** ***** *********** settings ********* *** **** minimally **** ** ********, but ************* **** ******** in *** *****. ********** ***** cameras ************** ******** ** further ********, ** ** ~25% **** ******** ** scene ** *** ******* (on **** **** **** I7 *.* *** *******).
    • ********* ** ***** **** from * ** ** or ****** ********** ****** as *** ********** ***** filled **** ******, ******* delay ** ***** ******** and ******** ****** ***** at *****.
    • ********* ** *.*** ********** significant ****** ** *** event ******* ** **-** seconds
    • ********** ********** **** **** to ***** *** *** introduced ****** ** ** increase ** ****** ****, nor ********** *****.
    • **** ****** **** ** recorded (** ******) ** retain ***** ******. ******** H.264 ****** *** ** recorded ** ****, *** is *** ********** ** LPR ******.

    *******

    ********* ******** *** ******** three ********, **** *** following ****:

    • ******** *** **** *******: $300 *** **** (******** one ***** *******)
    • ******** *** ******* *******: $1,295 ****
    • ******** *** ***** *******: $645 ****

    *** **** ******* ** required *** ******, **** a ******* ******* ******** for **** ******. * plate ******* **** ** purchased ** ***** **** state ** ******* ** be **** **** *** system. *** *******, ** **** United *******, ******, *** Swiss ******, ***** ********* are ******** (*** ******** in **** **** *** additional).

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

    ******** *** ******** **** accuracy **** ***** ********** are ********, **** ***** integration *** *** ********* Smart ******, ** * price ***** **** ***** than **** ********* *** systems, **** ********* ******, ****** ******* *** advanced ******* ***** ********* and ******* ****** ***** of *******.

    *******, ***** ****** ****** of ********* *********/******* ************ of *****, ***** *** stream **** *** *** processing **** **** ** retained ** ***** ****** are ** ** *****. Also, ****** ** **** PPF ************ ***** ****** preclude *** ******* **** being **** *** ******* surveillance ********.

    *******, ** **** ***** (>40 ***) *********** ** a ****, ********* ********/******** platforms *** ****** * better ******.

    XProtect ****** ***

    ** *** ****** **** be ***** ** **** client ******* ** ****** events. ****** *** ***** in * ******* *** pane, **** ***** ****** directly **** ** **** video. ******** ** ***** switches ** ******** **** in *** ********** ****. An *** *** ** also *****, ******** ***** to **** ******* ****** reads, ****** *** ******** plates (********* ******* *******), and ****** *******.

    **** ***** ******** ** overview ** *** *** in *** ******** ******:

    Server *************

    *** ******** *** ****** runs ** * ******** service, ***** **** *** XProtect ***** *** ********* servers. ********* ********** ** be *** ** * dedicated ******* *** *** the *** ******. ** *** tests, *** *** ****** increased *** **** ** about **% ** ******* (dual ****-**** ***** **, 2.4 ***), **** ****** impact ** ****** *****.

    **** ***** ******* ***** configuration ** *** *** server:

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

    ************ ** *** *** server, ** **** ** XProtect ********* *** ******** issues. ** **** *****, installation ****** ******* *** error ***********. ** ******, installation of ********* *** ****** multiple *****, *** ****** installation *** *** ********, despite ***** ********* ** per *********'* *************.

    ***** ****** *** *********** due ** *** **** and ****** ** *** Milestone ************, ***** *** easily **** **** **** an **** ****** * proper *******. ***** ****** be ******** ** **** ***** time (*****, ********) ****** installation ** ******* *** these ******.

    XProtect *** ****** *************

    ****** ** *** ****** to *** ****** ******** a ***** ************* *******, capturing ** ******* *********** of *** ***** ** view **** ******* ****** in *** *****, *** optional ********** ** * handful ** ******** **** as ********** *********, ****** of ****** ** *** scene, ***.

    *** ***** ******* ** ********** in *** ***** *****:

    ** **** ** ***** video ** ***** ******** parameters **** ** ********** frame ****, ****** ** plates ** *****, ********** time, *** ****:

    Milestone ****** ***************

    ********* ******** ********** *** following ******** *** *** cameras:

    • * ***
    • *****, ******* >**
    • ********** "*** *** ****"

    ***** ******** *** ********, to *** *** *****, since *** **** ******** of ** ******* ********* use *.***, **** ***** used **** ** ******* cases, **** ************. 

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

    *.*** *** ** **** for *** *******. *******, it ********** *********** ********** delay, **** *** **** between *** *** ******* and *** ***** ***** processed ********* **** second (***** *****) ** 10-15 *******.

    **** ***** ******** ** recognition events ******** ******* *** retrieval, ** *** ***** was ********* **** ***** the ****** ***** ********. ******* of **** *****, ******** on ** *** ***** retrieves ***** ***** *** car *** ******* ******, seen *****:

    ********* 

    ********* ********** ***** * FPS *** *** **********. Note **** **** ********* is ******** **** **** and ********* *********, ***** may ** *** ********** or *** ***** *******.

    ********** ********* **** *** recommended * *** *** processing ********** *********** ********** delay, ******* ** ***** H.264, **** *****, *** *** not ******* *********** ***********.

    **********

    ********* **** *** **** specific ****** ** ********** the ****** ** ******* of **********. *******, **** give *** ********** ** 130 *** ******* *** US ******, *** *** PPF *** ****-***** ******.

    ***** ******* *** ******** based ** * ******* recommendation ** *.* ****** per ********* "******" (**** making ** * *********), which ****** ** ***** size *** *****, *** equate ******* ** *** 130/180 *** ******* *****.

    ** ****** ****** *********** from **** ** ** *** and ***** ** *********** difference ** ********** **** or *****.

    Most ****** *********** ******

    ***** *** *** **** common ****** ***** ** our *******:

    *** *******: ********/****** **********

    *** **** ****** ***** we ***** ** *********** *** mistaken **********, **** ** B ***** ******** *** 8 ** * ******** for *. 

    ************, ********* ********** **** simply *** ****, **** commonly *** ***** ** last ********* ** * license *****:

    *** *******: ******** ***** Reads

    ******** *** ********** **** the **** ***** ******** times. ** *** *****, one ** ***** ***** was *******, ****** ****** may ** *********, ** seen *****:

    ***-** *******: ***** *** Gain ******

    *** *** ***** ***** caused ********* **** *********** ***** in ***-** ******* *** high **** ******. ** ***** to ******* ****** ** low *****, ***** ******* of **** *** *******, which ********* ******* *****, partially ** ***** ********* the ******* ** *** license *****. **** ****** complete ****** *** ******** in ***** ***** *** camera *** *******.

    ** **** (*** *** all, **** ** *** Bosch ***-***** **** *****) cameras, **** *** ** manually *******, *** **** darkens ******, *********** ****** them ******** ******* ****** visible ** ** ************.

    Versions *** ******** ****

    ********* ******** ********* **** 9.0c *** **** **** XProtect *** *.**. ******* module **** *** **, with ** ******** ***** modules ****. **** *** recognition ********** *** ***** from **** *** ***** collected **** ******** **** of *******.

    ****** ******** ******** **** as *******:

Comments (13)

We find its hit and miss. Complex and often lacks clear points in which to test and confirm the configuration. We have notice issues where we have had to remove and replace it for another solution after nine months of issues, even the "nothing is wrong its your hardware" only to find a new release fixed other issues - furthermore we have had been massive delays reading the plate up to a minute before it going in a database resulting in the gate opening too late or the system disregarding it. Milestone support is terrible. They do not understand the product enough, the logs files are poor leading to issues tracing any problems even for them.

BTW Milestone tell you that Express supports LPR, you pay your money, install it and then find out from support no it doesn't.. Their website tells a different story.

Currently we have another site which is taking Milestone over 2 days just to get the license to work!

Sorry but i'm on the fence on Milestone LPR, my gut tells me the dacollen system is too processor heavy and too poorly integrated.

Express can not support LPR, as this platform doesn't use a 'Management Server' in it's configuration - only Corporate, Expert and Enterprise use this function to 'centrally control' numerous recording servers.

In lower levels (like Express), they use a separate 'Management Application' to control each individual recording server.

They named each of these interfaces so similarly just to annoy people I think...

Can you confirm the model of processor used? We're trying to gauge the level of performance vs new i7 processors and also their Xeon equivalents.

If you can just get a generic US library, is there any advantage to paying for libraries for individual US states?

Will the generic US library work on Canadian license plates, as they are the same size and shape as US license plates?

The individual libraries are supposed to be "tuned" to specific states, to account for things like differences in character pattern, reflectance, etc. But we haven't seen much difference. We used the NJ library and tested with "Shore to Please" plate, which has stacked characters:

It did not read the stacked characters, and NY and PA plates read just as well as they did using the US generic module.

Because of that, I'd expect Canadian plates to work as well (but I won't guarantee it!), and we'll actually get one to add to the plate repertoire in the future.

it also seems the skew of the license plate is possibly greater than it should be for LPR technology with the above pictures.

The cameras were set up at an angle of incidence of about 19-20 degrees to the road, within Milestone's recommendations (<25 degrees). The vertical angle was very shallow as well, as cameras were only about 7' off the ground.

I am guessing that older analog D1 resolution license plate cameras would not work due to low resolution?

I wouldn't rule them out, but the FOV would need to be about 6' wide at most, and you would need to very carefully set it so you get multiple frames of the plate. Angle of incidence would need to be very shallow.

The up side to SD cameras, if there is one, is that the frame size is smaller, so the server should be able to process higher framerates, instead of the 4 Milestone recommends as their general rule.

Thank you for providing information on setup challenges and the impact on time frames. This is very relevant information.

We were struck with Milestone LPR, Thank you for publishing this article which indeed helped us in geeting out.

Is XProtect LPR 2.0a released as I cant find it in their website and I use 1.0c

Milestone supplied us with an advance (non-beta, but non-public as of test time) copy of 2.0a. They just put out a newsletter last week, however, claiming general availability April 15th, so check back in two days.

H.264 may be used for LPR cameras. However, it introduces significant processing delay, with the time between the car passing and the plate being processed increased from < 1 sec for MJPEG to 10-15 seconds for H.264...

Any thoughts on why decoding a 4 FPS H.264 stream would add 10 seconds of latency? Surely the VMS is capable of decoding multiple concurrent 30FPS H.264 streams in < 1 sec for live view as well as VMD, so what gives?

Makes you think that the application was written for MJPEG initially, and to make it compatible with H.264, they took the easy way out and are just decoding H.264 and re-encoding it as MJPEGs before sending it to the LPR server. Speculation? Justified because their abysmal performance invites it.

Was wondering what the camera processing time stat shows when using h.264. If it's < 1 sec even though taking ten, it's probably not the LPR server using up the time...

Read this IPVM report for free.

This article is part of IPVM's 6,379 reports, 860 tests and is only available to members. To get a one-time preview of our work, enter your work email to access the full article.

Already a member? Login here | Join now

Related Reports

2020 Video Surveillance Cameras State Of The Market on Jan 03, 2020
Each year, IPVM explains the main advances and changes for video surveillance cameras, based on our industry-leading testing and reporting. This...
Video Surveillance Cameras 101 on Feb 25, 2020
Cameras come in many shapes, sizes and specifications. This 101 examines the basics of cameras and features used in 2020. In this report, we...
Vivotek 12MP Fisheye Camera Tested (FE9391-EV) on May 08, 2018
Next in our 12MP fisheye camera evaluation, we bought and tested Vivotek's latest generation FE9391-EV, a new model claiming improved smart IR...
Hikvision 12MP Fisheye Camera Tested (DS-2CD63C2F-IV) on Jun 14, 2018
Hikvision's DS-2CD63C2F-IV is their flagship panoramic camera, with a 12MP imager, 15m integrated IR, smart codec, and more. We tested the 63C2 in...
Avigilon "Self-Learning" Analytics And VMD Tested on Jul 23, 2018
Avigilon is a popular choice for video analytics, offering "self-learning" analytics built into their cameras as well as appliances. We tested...
Camera Analytics Shootout 2020 - Avigilon, Axis, Bosch, Dahua, Hanwha, Hikvision, Uniview, Vivotek on Jan 22, 2020
Analytics are hot again, thanks to a slew of AI-powered cameras, but whose analytics really work? And how do these new smart cameras compare to top...
Axis 12MP Stereographic Camera Tested (M3058-LVE) on May 10, 2018
Axis has released the M3058-PLVE, a 12MP sensor, stereographic panoramic camera and Axis' first with integrated IR claiming images "sharp to the...
New Axis M30 Cameras Tested on Mar 26, 2020
Axis has released a new generation of, for them, relatively low cost M30 series cameras, claiming to deliver "sharp video quality even in poor...
Vivotek LPR Camera Tested on Apr 15, 2020
Vivotek has historically sold license plate capture cameras but not LPR. Now, they have released their own cameras with embedded LPR. How do they...
Hanwha 20MP Multi-Imager Tested (PNM-9081VQ) on Oct 09, 2017
Hanwhwa has introduced the latest in their multi-imager camera line, the PNM-9081VQ, a Wisenet 5 20MP model with four repositionable 5MP camera...

Most Recent Industry Reports

Avigilon ACC Cloud Tested on Jul 08, 2020
Avigilon merged Blue and ACC, adding VSaaS features to its on-premise VMS, offering remote video and health monitoring that was previously limited...
The US Fight Over Facial Recognition Explained on Jul 08, 2020
The controversy around facial recognition has grown significantly in 2020, with Congress members and activists speaking out against it while video...
Sperry West / Alibaba Tablet Temperature Measurement Tested on Jul 07, 2020
In April, we ordered a ~$500 temperature tablet from Alibaba. We set it to the side while doing 18 other temperature screening tests but, after...
Facial Recognition: Weak Sales, Anti Regulation, No Favorite, Says Security Integrators on Jul 07, 2020
While facial recognition has gained greater prominence, a new IPVM study of security systems integrators shows weak sales, opposition to...
Video Surveillance 101 Book Released on Jul 07, 2020
IPVM's unique introduction to video surveillance series is now available as a 145-page eBook. Designed for managers, salespeople, and engineers new...
Startup Duranc Presents AI VSaaS on Jul 06, 2020
Duranc presented its system at the May 2020 IPVM Startups show. A 30-minute video from Duranc including IPVM Q&amp;A Background on the...
Low Voltage Nation Wants to "Help You Carve Out A Fulfilling Career" Interviewed on Jul 06, 2020
It is difficult to make your way in this industry as there is little formal schooling. However, one person, Blake Urmos, the Founder of Low Voltage...
The Next Hot Fever Detection Trend - $100 Wall-Mounted Units on Jul 06, 2020
The first wave of the booming fever detecting market was $10,000+ cameras, now interest for ~$2,000 tablets is high and the next big thing may be...
Cisco Meraki Unlocks IP Cameras With RTSP Tested on Jul 06, 2020
Meraki opened up its cameras to 3rd party NVRs/VMSes by offering RTSP streaming because of "the need to solve a business problem". We tested...