Neurala Deep Learning Platform Profile

By Brian Karas, Published Aug 31, 2017, 11:33am EDT

Find lost children? If Neurala has its way with its recent partnership with Motorola, that is the aim as shown in their video below:

Neurala has developed a deep-learning platform designed for implementation in low-power edge devices, providing analytics capabilities often found only in more expensive and powerful hardware.

Motorola is deploying Neurala's technology in an updated line of police body cameras, and Neurala hopes to find more security-based uses for their technology.

IPVM spoke with the company, and provides an analysis of their development and potential to impact the security industry.

Background *******

******* *** ******* ** 2006 ** * ****** University ***********, ************ ******* [**** no ****** *********] (***) ******* **** Versace [**** ** ****** available] (COO) *** ******* ************* [**** no ****** *********] (***). *** company ******* *** **** seed *******, *** ******, and ***** ****** * total ** ~$*** ** develop **** ****** ******* frameworks ******** *** *** in ***-***** ***'*. ***** aim *** ** ****** devices **** ******, ******** cameras, *** ******** *********** with ********-****** ************ ********** unavailable ** ***** ********** due ** ****, ****, or ***** **********.

*** ******* ******* ~** people ** *** ****** headquarters, *** ******** ** them ** ***********/*&* *********.

Edge ******** - *** **************

*******'* ********** ****** **** devices ** ** *********** trained ** ****-**** ** new ****** *******, ********* that ***** ********* ******* more ******** *********** ********** resources, *** ********** **** delays (*****). ******* ****** ** this ********** ** ** LDNN, ** ******** **** Neural *******.

 

**** *******'* **** ******** on * ***** ******, a **** *** ******* video ** *** ******, highlight ** ****** ** the *****, *** ***** the ****** ** ********* future *********** ** **** object.

**** ********** ****** **** other "**** ********" ********* which ********* **** ******* understanding ** ******* ******* objects, *** *** ****** to ***** ** ******** new ****** ***** ** appearance ******* *** *** of *********** *********.

Nvidia ************

*** ****-***** ******** *** been*********** ** ******'* ****** GPU. ******* ** **** part ********'* ********* *******, ******** ** **** foster ******* ********* **** utilize ****** ******** *** deep ******** ************.

Motorola ****

******** ** ***** *******'* investors, ********* ** *********** sum *********'* $*** ****** *** **** ** *** partnership ******* *** *** companies. ********'* ***** ******** ******* *** ******** ** **** advantage ** **/*** ************, enabling *******'* ******** ** run ****** ***** *******.

Bodycam ************ ** ******* ****

** ********* *******'* ********** in ********, *** ******* *** be *********** ******* ** recognize ******* ** ******* of ********, ******** *** officer ******** ** ********* when ** ******* ** appearance. ******** ********* ******** the ******* "*******" *** camera ****** ** *** person/object ** ** **** for ********. * ***** image *** ** ****, or * ***** **** can ** **** (**** as **** ******** ******** footage, ** **** *******), though **** ******** ******* are ******** ** ***** a ****** ** ****** (still ** *****) ******* of * ****** "*******" style *****. *** ******* then ********* *** ****** locally, ********* ** * period ** * *** minutes, ** ****** ** updated ******* ** *******, which ** *** **** recognize ** **** ***** from **** ***** *******.

*** ********* ****** *** camera *** **** ** used ** **** ********** on ******* ** ******* encountered ** ** ******* during *** ****** ** their *****. **** *** provide *********** **** ********** such ** *** ***** an ******* ****** *********** walking *****, ****** ** people, **********, ***** ********, street *******, ***. **** data *** ** **** to ******** ****** ******, or ***** ***** ****** within *** ************.

Surveillance ************ ** ******* ****

***** ************ ******* *** typically ** *** **** any **** ********* ********, and *** ********* ** a ********, ***** *** **** ********** power, *** **** *** edge-learning ****** * ****** itself ** *******. *******, embedded ********* ***** ****** low-cost ***********, *** **** far ***** *********, ***** Neurala's ********** ** ********* could ******* ************ ******* to ***** ****** ** *********'* **** ******** ********,******* ********* * ****** card **** ******. **** ** ******-***** recorders **** **** *********, the ******* ** ** dynamic ******** ** * way **** ******* ******* requirements *** ** ********** to ******** **** ***********.

***** ******* **** ****** edge-based ********* ************ *** object **************, * ****** of ************* **** ** Avigilon, ****, ******, *********, and ******, **** ******* begun ********* ******** **** edge-based *********, ****** *******'* offering ** **** ****** of ***** ******** *** the ************ ******.

Upcoming ******* ** **** ******** ****

******* ****** **** **** soon ******* * ******** update **** ****** ****** training **** ** *** device ** ** ******** and ****** ** ***** devices ****** *** **** organization. **** ***** ***** an ***** *** ******* their **** ****** ** the ********** ** * person ** ***** **** custom ******** **** **** other ********. 

Looking *** ******** ******** ********

*** ******* ****** **** would **** ** ******* with ******** ******** ************* to ******* *******'* ********** in ***** ********. **** would ****** ****** *** appropriate *** ** *** device, *** **** ********* Neurala's ********. *** *** requirement ***** **** **** manufacturers ***** **** ** create *** ******** ******* for ******** ******* ***** they ****** ** ****** the **********.

Challenges *** ******* ** ********

***** *******'* ********** *** be ********** *** ************* to ******** ******* ************, adding even ***-*** *** ************ can ******** ****** ****** by **'* ** *******, which *** ** * significant ******** ** ***** for **** ******* *** recorders. ************, ***** ************* **** been ******** ** **** on *** ******** *** core ******** **** ** analytics, ********** ******* ** create ***** *** ******** as * ***** ** differentiation. *******, ***-**** ******* may **** *******'* ********** *** offer **** * *** to ******* ***-******* ******** without ****** ** ****** heavily ** ***** *** R&D.

Comments (2)

This is really cool and really scary at the same time. Sometimes being in this industry is absolutely amazing and sometimes you have to step back and say, Did I really just do that? Referring to making big brother even more powerful!!

Agree: 4
Disagree
Informative
Unhelpful
Funny

I'm not too concerned yet. The article is very light on technical detail, and knowing Brian's inclination to nail that sort of thing, it's probably because the vendor is light on sharing it. A cop's body camera that beeps away with false alarms is not going to be accepted. And high accuracy is at odds with low cost and small form factor edge devices. It's a great idea, a good vision and deep learning holds the promise of a lightweight footprint, but there is no detail yet. What complexity can it learn? What is the impact of environmental conditions (shadow, low light, direct light, motion, etc.)? What is the accuracy in terms of false reject and false accept? It ain't real until this is all quantified, hopefully by a credible third party.

Agree
Disagree: 1
Informative
Unhelpful
Funny
Read this IPVM report for free.

This article is part of IPVM's 7,199 reports and 959 tests and is only available to subscribers. To get a one-time preview of our work, enter your work email to access the full article.

Already a subscriber? Login here | Join now
Loading Related Reports