Facial Detection Tested

Published Nov 16, 2018 12:17 PM

****** ********* *** *********** *** ************ offered ** ***** ************ *************.

****** ********* ******* ***** ** ** image/video *** *** ***** **** ** is. *******, **** ****** *********** (***** the ****** ******** ** ********* *** identity ** **** ****) ******* ** facial ********* *****. **** **, *** system ****** ******* ** ********* * face ***** ** ******* **** ** object ** * ****. ** ****, facial ********* ** * ***-********* *** facial *********** *******.

facial detection test

* *********** ********** ***** ** ********** facial *********:

  • **** ********
  • ***
  • *** / **** ********

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

  • ******** ** ********* ***** - ***** it ** '****' ** ****** * face ******* ******** ** *** ****** in * ****-*** *****, *********** *** vary ************* ********* ** *** * person ***** ***** **** (****, ****, right, ***.) *** *** ******** ********** of *** ***** (*******, ********, *****, etc.).
  • ********* **** ** ****** ***** - Finding *** *********** **** ******* *** in * ***** *** ******* ***** objects *** * **** (******* ** a ****, * ***, * ***, a ******* ****, ***.) *** ** very *************** ********* ***** **** ***** surveillance ******* (*.*., ** *******, ****) have *********** *********** ** ********** *****
  • **** / ******** **** - ***** (i5/i7, ******** * & *, ****); Nvidia ****, ***.

**** ** *** ***** ** * new ****** ** ******* ******** / video ******** ******* **** **** **** be *****.

****** **** ****, ** **** ***, HAAR *** *** ********** ** ****** detection *********** ***** *********** (***) *** computing ***** ******** ** ***** **-*****. In ******* *******, ** **** **** on ******** *******, *******, *** ****** GPUs, ** **** ** *** ******** tests (******* *********). *** **** *** this ****** ** ** ****** [**** no ****** *********].

Facial ********* ********** ********

*** ***** ** *** *** ******** with ***, **** *** ***, *** 8-minute ***** ***** ********* **** *** explains *** ********* ***** ****:

Code / ******* *** ****

*** **** *** ******* **** *** the **** ** ****** ** ****'* public **** ********* **** ********** ** Github [**** ** ****** *********].

** ******:

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

** **********, *** ***** ********** ** the **************, *** *** ****** ****** used [**** ** ****** *********], ********* below *** *******:

Test ******* *** ****** *********

***** **** ************ *** *** **** computing ********* **** *** *** ****, in *** ****, ***** *** **** Intel **-***** *** *** * **********, the ******** *** ****** ********* ***** delivered ******* ****** *** ****** (~*****) as *** **** **** ******** **** classifier ***** ********** ***** *** *** of *** **** ****** ******** ** well. *** ***** ***** ********* ***** results:

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

  • ***** ******** ********** *** ********* *** ** ****** ** ***********. OpenVino ********* ***** *** ************* **** data-type ********* ********** (****->****) ******** ********* ****; (*) ********** *** ***** ** the ****** ******** (**/**/**, ********, ****). This ******** **** * ******* ************ SqueezeNet+SSD) ********* ****** **** ************ ******** results.
  • *******, ~***** *** ** ****** ***** I7-7700k **** ***** ******** ********** *** video ************ ************. **** ***** *** not *** ****** ** ******* (*** to **** *** ***** ***********) *** while **** *** ** *** ** recorders, ********* ***** **** ** ******* far **** **** ***** ** ****** 8, ** ** **** ******* ********* being ******** ** * ********. ******** IPVM ***** **** ***** *****'* ******** chips (** ********** *** ******* *** MyriadX) ***** *****'* ****** ******* ***** (NCS) *** **** (***** *** *******).

********

**** *** *** ******* ******* ********* capabilities ********** ********** **** ****** ***** as ***** ** *** **** *****:

*** ********* ******** ***** *** ******** from **** '**********' ** *** **** was *********** **** *** **** **-******** as ***** *****:

** ********, *** *** ******** ***** quite ******** ******* *** ********** ** HOG, ** ***** *****:

Questions / ******** / ***********

**** ** *** ***** **** ** this *** ****** *** ** *** presenting *********** ******* ** **** **** we *** ******* ** *** ** encourage *** ** *** ********* *** make *********** *** ********* ******, ******, hardware, ***. ** ****.

Comments (10)
JH
John Honovich
Nov 16, 2018
IPVM

I want to welcome and thank Tyler Renelle. Tyler has a popular podcast on machine learning. For those looking to learn more in this area, I'd encourage you to listen to his 30+ episodes.

Tyler started by giving us private lessons and he has expanded into doing tests on video surveillance related machine learning approaches.

Next up is a test of the brand-new Intel Neural Compute Stick 2 (which uses the MyriadX chip that, e.g., Avigilon will be using in their upcoming H5 cameras).

We are also working on training to help industry professionals better understand machine learning fundamentals as they apply to video surveillance.

Again, any questions or suggestions for testing / Tyler, please ask.

(19)
Avatar
Markus Lahtinen
Nov 19, 2018

Very much looking forward to following the results John. The police in South Wales in the UK did some tests on facial recognition in high-volume spaces, but they haven't returned my mail yet.

Avatar
Tyler Renelle
Nov 16, 2018

Note that dlib has a CNN face detector built in (you can run it in the code as `--models dlib_cnn`). The CNN is an older model, not on of the more modern SqueezeNet/MobileNet varieties. If you have CUDA installed, it will use your GPU by default. If you want it to run without GPU-support (run on your CPU), you'll need to compile dlib from source. I tried both with and without GPU:

- i7: dlib_cnn ran so slow I couldn't even finish the process. Ie, FPS much less than 1.
- 1080ti: dlib_cnn was very fast this way; faster than any of the options in the report. But again, we're talking very powerful GPU; something not likely available at the edge.

Generally I'd be less interested in using dlib_cnn since it's a model from another time, and more interested in recent models from public repositories / papers. With these you'll also get more control on how they're run (CUDA on GPU, OpenVINO on Intel, etc).

(6)
U
Undisclosed #1
Nov 19, 2018
IPVMU Certified

Any thoughts on the viability of running cnn on chips that are used in cameras and nvrs, like ARM architecture, for instance?

Avatar
Tyler Renelle
Nov 19, 2018

That's a really good question. I'll keep an eye out for an answer here as I work with OpenVINO & reply back if I find one.

SL
Steve Lewis
Nov 19, 2018

Excellent piece. Thank you.  I would like to suggest a similar comparison of these techniques with license plate detection.

(1)
PD
Paresh Desai
Nov 19, 2018

Anyway to run the tests using our own videos from security cams?

Avatar
Tyler Renelle
Nov 19, 2018

Yeah, grab the code from Github (link in the report), follow the setup instructions, and drop your own videos into the vids/in directory (instead of downloading the recommended samples). I'll keep that repo updated & try to improve on quality, to make it easy to test on custom vids.

(1)
MM
Michael Miller
Nov 19, 2018

Thanks for this report.  Looking forward to learning more. 

 

(1)
Avatar
Franky Lam
Nov 23, 2018
Zen Foods Group

I am also working on the project in Hong Kong now by using AI Deep Learning. Let me share some experience on this shortly. Good topic for discussion.