Intel Neural Compute Stick 2 / Movidius AI Test

Author: IPVM Team, Published on Nov 21, 2018

AI is a major trend in video surveillance with manufacturers paying significant attention to Intel's Movidius Myriad chips. Indeed, Avigilon has announced that their next generation AI H5 cameras will use the Myriad X.

But how well do these Myriad X chips perform?

IPVM has done its first testing of the Myriad X chip (via the NCS2) and shares results inside this report.

Intel / Movidius / Network Compute Stick Overview

Cameras like Avigilon will use Intel / Movidius chips inside them to deep learning / Artificial intelligence. To the side is an image of a Myriad X chip. Video will be sent into to on-board chip, the chip will run deep learning models and it will output categorizations of people, objects, faces, etc.

Just a week ago, Intel announced its second generation of 'Neural Compute Sticks' (NCS). While the first NCS had the original / older Movidius Myriad 2 chip, this new one has the newer Myriad X inside, which Intel claims "delivers 10X the performance compared to previous generations".

IPVM bought the NCS2 and tested it.

Areas Analyzed

Inside this report, we share results across:

  • Face detection using Intel's face-detection-retail-0004 model
  • Testing across Intel i7, Myriad 2 and Myriad X
  • FPS, CPU and RAM consumption variances across devices
  • Accuracy comparison of detection
  • YOLO support and issues

** ** * ***** ***** ** ***** ************ **** ************* paying *********** ********* *******'* ******** ****** *****. ******,******** *** ********* **** ***** **** ********** ** ** *********** *** *** ****** *.

*** *** **** ** ***** ****** * ***** *******?

**** *** **** *** ***** ******* ** *** ****** * chip (*** *** ****) *** ****** ******* ****** **** ******.

Intel / ******** / ******* ******* ***** ********

******* **** ******** **** *** ***** / ******** ***** ****** them ** **** ******** / ********** ************. ** *** **** is ** ***** ** * ****** * ****. ***** **** be **** **** ** **-***** ****, *** **** **** *** deep ******** ****** *** ** **** ****** *************** ** ******, objects, *****, ***.

**** * **** ***,***** ************ ****** ********** ** '****** ******* ******' (***). ***** *** ***** *** *** *** ******** / older ******** ****** * ****, **** *** *** *** *** newer****** *******, ***** ***** ****** "******** *** *** *********** ******** ** previous ***********".

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

Areas ********

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

  • **** ********* ***** *****'* ****-*********-******-**** *****
  • ******* ****** ***** **, ****** * *** ****** *
  • ***, *** *** *** *********** ********* ****** *******
  • ******** ********** ** *********
  • **** ******* *** ******

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

Key ********

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

  • Myriad * ~= *.** ****** * ***: The NCS2 ran roughly 2.7x frames-per-second more than the NCS1 in their face detection model we tested. Intel says that different optimizations and measurement changes would increase this significantly (discussed in caveats below).
  • Faster **** *** (**): The NCS2 / Myriad X outperformed the i7-7700K (a top-of-the-line in 2017) chip tested here, a significant advance given the Myriad X being significantly lower cost and lower power consumption.
  • Little/no ******** ****: Our tests noted no differences in output video accuracy in line's feedback that OpenVINO's model-optimization step should be considered "lossless." They pointed out that allowing lossy model compression (when converting a model to be run on Myriad; eg FP32->FP16 data-type downsizing) would cause issues with vendors training a model with certain expectations, and having a different (lossy) model for inferring.
  • Model ************* ** ******: While Intel has mentioned YOLO support for OpenVino, the current YOLOv3 is not yet compatible on Myriad chips due to a particular network layer. ***** **************** ***** *** ******* ********** ****** ** ** *** ** CPU, *** ****** ** *** *** ********** ** ****** ******* due ** * ********** ******* *****.
    **** ** & **: ***** ******* ***** *** ** *** on ******, *** *** ***** *******.
    **********+***: *** ***** ** **** ****** **** *******, ************ ***** face-detection-retail-0004 (********** ***** **** * ******-**** ********).
    *********+***: *** ***** *******. ** **** ******* ****** ****** **** Github ** *****'* *** ******.

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

intel performance comparison2

Caveat ** *** / *****

***********, *****'* *** ******* *** **** ****** **** *** ***, for **** *******. **, *****'* ****-*********-******-**** ***** ******* *** *** on ***, **.* ** ******* (**** ***** ******** ********** ******* numbers ** **** ******).

* *** ****** ** *** ***** ***** ******* ***: (*) We *** ******, **** ******* **** ***** *++ ****; (*) our ***-******* ******** ******* **** (** ****** *******/******* ******), *** isolating ***** ****; (*) ** *** *** ***** ******* ************ handling ** ***** ***** *******, ***** ** ***** **** ********.

Video **********

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

Questions / ******** / **** ** **** ****?

** **** ******* ******* ** *** **** / ****** * along **** ***** ********* *** **** **** ****** **** *** next *** *****. **** ***** *** **** ** *** ******?

Comments (12)

*'* **** ** ********** **** **** ** * *** ****. Do *** "****" **** ***** **** * ******** *** *** a ******* *** *** ****** ** ***** *********** *******? *** these ******** **** ****** ** ******** *** *********?

*** **** ****** ** **** * *** **** **** *** other *** ******. ** * **********, ***** ****** ******* ****** aren't ****** *** ********** ************, *** *** **********/******* **** ****** network / ******* ** *** ****** **** (** *** *** it ********, ****** *** **********, ***). ***'** ** ***** ** integrated ****** **** ** *** **** *****.

**** **** ** *** *** **** ** *** **** ***** (I'll *** ***** ******* ** ****-****** ******* ** **), *** it's **** **** **** *** ***. ***'** ** ****** ****** cloning ********'* *** ****** *++ *****. *** *** **** ***** (after *** ******* ********) ** ~/*****/*******************/****************/****************/*******. ** ** "*** **** open ****** / ********", ** ******** ***** ** "***" - they **** ** *** *** *******. *** ***'** **** ** read *** ******** ******* (**** ** *******) ** ~/*****/*******************/*********.

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

******* ********, *** ** ******* $ ** $$ ** $$$?

**** *** $***. ********** **********, *** ****'** *** ****-***** *********

****** **** **** **** **** **-*****. * ******* *** * days *** *** ** ** ******** ******.

**** ******** - **** ***% *** *********** ** *** **-***** mean **** **** ********* *** ***** *** ***** **** **** of ** ** ** ** ******** ******* **** ***** ******?

****, *** *** *** *** **** *** ****** *******? ** there * *********** ****** ** ******* ** *** *****? **** wondering **** *** ****** **** ** ** *** ******* *******/****.

*** **** * ** ***, *** *'* ************* ******. * think **'* ** *** ******, ** ********* ***% **** *********** of * **** *** ** **'* * ***** (** ********** aggregate ****** ****). ** ************ *'* ******** ** **** *.**/* cores *****.

* ***** *** ***** *** *** **** **, ** ********** heat. *'** *** ** ***** ** * ****** *** ** gauging. **** ***** ** * * *** *****, *********** ******* of ****** * **** (** ***** ****** **** *****) ******** to **** ****** ****.

* ***** **'* ** *** ******, ** ********* ***% **** utilization ** * **** *** ** **'* * ***** (** comparable ********* ****** ****).

** **** ** ****** *** ****, * ***** ******* **** the ****** **** ** ** ********** ****** ********, *.*. ***%=**%.

****** **** ******** *** ***%, ***** *** * *** ** cores? ** ** **** ***** ******** **** **** *?

* *** **** ******* ******* ** *** ******* *******. ***** it ** ***** *** ***** *** ********* *** ***(******* ****** Power). **’* **** *** **** *** ****. * ** *** certain *** ** ******** ** *** *** ** * ******** chip **** ** ******* ** ** ******* *** ******** ***** to ******* **** **** ** **** ** ********... ** *** not **** ****. * *****’* **** **** **** ** **** wattage ** ******* **** ** **** ****** *****. **** ** how ****** * ******** ** ***** ****** **********:

****** * - *.* **** ***

**-***** - ** **** ***

**** ********* - *-** **** ***

****** ***** - ** ** *** **** *** is **** ** ** *** *** **** ******** **** *** server **** ********** ****** ********* *********

* *****’* **** **** ** **** *** *******/******* **** *** mobile ********** **** ********** ** *****. ***** ***** ** ******* everything **** ***. * ******* **** *** *** * **** but ******** **** ******* ***** ** ******* ***********.

***, ** *** ***** ** ** *** / ************ ******** on ** / **** ******** ** *** **** ****** ** well.

** *** **** ******* ** ** ********* ***, ********** **, some *** *** **** **** ***** / ******** ********* ****. Upcoming ********* **** ******* ****.

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

* ****** * **** ** ***** ** **** **** **** mouser ** *** ****** ****** ************ *** *** **** ** play **** **** **** *** *******. ** ******* * *** openVino **** *** ***** *** *** ** **** *** ********* the ***** ** ***(*** ******). ******* ** ********** ** *** it ****** *** *** ** **** ** ******.

(** *** ** * *** ****, *** "***" ****** ** only *** ***** ***'* *** ******, ***.)

* ** ************* ** *++, **** ******* *******, *** *** samples **** ****** ****.

* **** **** ******** *** ******* *** ******* **** ** the ******* **** ** *** **** *********** ** ****. ** is **** ** ********** *** *** *** ****** **** **** other *** *** ****** **** *** ** ***********. *** *** license ***** ***** *** ****** ** ********* **** ** *** into *** ******* ***** ********* ***** ** *** **** *** license ***** ***********. **** **** * *********** ******* ********* *** recognition.

** ***, ****** ************ **** ***********, *** ** ** ****** early ** **** ***** ***.

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

19 Facial Recognition Providers Profiled on Apr 23, 2019
IPVM interviewed 19 facial recognition providers at ISC West to understand their claimed accuracy, success and positioning. 9 from China, where...
Verint Victimized By Ransomware on Apr 18, 2019
Verint, which is best known in the physical security industry for video surveillance but has built a sizeable cybersecurity business as well, was...
ISC West 2019 Report on Apr 12, 2019
The IPVM team has finished at the Sands looking at what companies are offering and how they are changing their positioning. See below for 50+...
Bosch AI Camera Trainer Released And Tested on Apr 09, 2019
Bosch is releasing a highly unusual new AI feature - 'Camera Trainer'. Now, coming as a standard feature in Bosch IVA/EVA analytics, one can train...
Airship VMS Profile on Apr 03, 2019
Airship has been developing VMS software for over 10 years, however, with no outside investment, and minimal marketing, the company is not well...
Cambium Wireless Video Surveillance Profile on Mar 27, 2019
Cambium Networks, spun out of Motorola Solutions in 2011, says "outdoor durable radios are in their DNA" and they are targeting video surveillance...
IBM / Genetec Surveillance System Investigated Over Philippines Human Rights Abuses on Mar 22, 2019
A lengthy investigation into an IBM video surveillance project in the Philippines, raising concerns IBM helped local police conduct a bloody...
Large Hospital Security End User Interview on Mar 21, 2019
This large single-state healthcare system consists of many hospitals, and hundreds of health parks, private practices, urgent care facilities, and...
BCDVideo Expansion And Switch From HP To Dell Examined on Mar 11, 2019
BCDVideo says they have more than tripled revenue in the past 5 years and are continuing to grow, powered most recently by switching their lead...
Church Technology Director Security Interview on Mar 07, 2019
With 40+ years of experience in IT from a wide array of verticals, including US and foreign military, and large corporate and industrial settings,...

Most Recent Industry Reports

Ex-Integrator Now Growth Strategist Interviewed on Apr 24, 2019
For more than a decade, Scot MacTaggart was a security integrator (at PA-based PSX). In late 2018, he left the industry. He is now a Growth...
19 Facial Recognition Providers Profiled on Apr 23, 2019
IPVM interviewed 19 facial recognition providers at ISC West to understand their claimed accuracy, success and positioning. 9 from China, where...
Locking Down Network Connections Guide on Apr 23, 2019
Accidents and inside attacks are risks when network connections are not locked down. Security and video surveillance systems should be protected...
Hikvision Admits USA Sales Falling on Apr 22, 2019
Hikvision, in a new Chinese financial filing, has admitted that its USA sales are now falling. Less than a year after the US government passed a...
Speco Ultra Intensifier Tested on Apr 22, 2019
While ISC West 2019 named Speco's Ultra Intensifier the best new "Video Surveillance Cameras IP", IPVM testing shows the camera suffers from...
Arecont Favorability Results 2019 on Apr 22, 2019
Arecont's net negativity remained the same in IPVM's 2019 integrator study, though integrator's feeling became relatively more neutral compared to...
H.265 Usage Statistics on Apr 19, 2019
H.265 has been available in IP cameras for more than 5 years and, in the past few years, the number of manufacturers supporting this codec has...
ACRE Acquires RS2, Explains Acquisition Strategy on Apr 19, 2019
ACRE continues to buy, now acquiring RS2, just 5 months after buying Open Options. One is a small access control manufacturer from Texas, the...
Access Control Course Spring 2019 - Last Chance on Apr 19, 2019
 Register for the Spring 2019 Access Control Course----Closed IPVM offers the most comprehensive access control course in the industry. Unlike...

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