Healthy Skepticism for Deep Learning Is Prudent

Author: John Honovich, Published on Jul 26, 2017

The hype for deep learning in video surveillance is accelerating.

Between the race to the bottom and dearth of a 'next big thing', certainly pent up demand exists.

But now is the time for a healthy skepticism about when and what deep learning can do. In this note, we examine the hype and real issues that professionals need to consider.

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

******* *** **** ** *** ****** *** ****** ** * 'next *** *****', ********* **** ** ****** ******.

*** *** ** *** **** *** * ******* ********** ***** when *** **** **** ******** *** **. ** **** ****, we ******* *** **** *** **** ****** **** ************* **** to ********.

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

'Revolution' ****

**** *****,*** ******** **** ********** ** "* ********** ** ***** *********", *********:

********************** **** ***** **** ********** ******* **.* ******* ******** ** ************, ***** ************ ******* ***** ******** ** ******* ** *******.

************* **** ***** ***** ***, **** ***** ***** ** *** even *** *** **.* ******* ** ***** ******** *** *** mentioned.

*** **.*% ****** **********.

Irony ******

*** ***** ** *** *** ***** ** *** ******* ******** of *** **** ******** *****:

*** ***** ********* ******** ** ***** ******* *** *** ************ damage ** ********* ** * ****** **previously ********* *** **** and delivering too little in the past. [emphasis added]

*** ****** "***** *** ****** ******** *** **** *** ********* to ****** **" ** ********* *********** ****.

Robots

**** ** ****** ***, '******* *******' ******** ******* *********** ************ *** ****** *** ****** *** **** *** "**** ** robots **** ****** ********** *******". ** *******:

** **** ** ** ** ******** ********* ***** **** **** a **** **** ***

** ********, ** *** **** ******** ***** *** *****. ** are ** ** '******** ********* *****' **** ****** **** ****. Unfortunately, *** *******, ************** **** ****** * ****** ****** ***** ****.

Timing ******

** ** **** ** *** **** ********** *** ************ **** become ********** ** ********* ****** **** ******. *** ******* **** eventually *** *** *** ***** ******.

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

***** *** / ***** ** ***** ****** ********. *** ********* are ****. *********** *** ******** *****.

Deep ******** **********

**** *** * *** ********* ******* *** * ******* ********** of **** ******** ** *********:

  • ******* ************: **** ******** **** ** **** ** ******* ***** ************ applications. ***** **** **** ****** **** *** ***** **** **** poorly ** ***** *******. ** ** ****** ******* **** *** performance **** **** ************* ****** ************. "**** ********" ** ****** to ** ******** ** ********* *** ***** ** **********.
  • ***** *********** ********: ***** **** ******** ************* ****** **** ********, *** *********** will ** ************* ******** ** **** ** ** *** ************ **. *** '**** *****' ** ******* *** ** ***** applications *** ******** ** ********* *******, ******* *** ***** (*.*., people **** *********, ****** ***********), ** ** ******* **** *********** problems **** ** *****. **** ** *** ******* ** *** easily, ******* ** ******* *** **** ******** ************ *** ** re-trained ** ****** ***** *********.
  • ******* ****** ***********: ****** ******* ***** **** ******** **** ******* **** * few *********, *** ******** *** *********** ** **** ******** ***** surveillance ******* ** ***** ** **** ************* ***** ** *** engineering ***** (***** ** ** ***** ****** *******), ********* ********* and **** ********* ** ****** *** ******* ****** ** ***** on. **** ** ****** ** ****** ** *********** *********** ********* across ******* **** ** *** ** **** *** '**** ********' on *** '***'.
  • ******** ***** ******: ****** ***********,*** **** ******** ******** **** *********** ******** ***** ******.

Early *******

**** *** *** *****, ** ** ********* ** ****** ********* that **** ** ***** ***** **** *** **** ******** ** video ************.

* *** ** **** ** ***** ***** ** ***** ********* demos. *** *******, ** *** ****** *** **** **** *****, one **** ******** ******** *** ******* *** *** ******** / performance ** ***** ******. ***** * ****** ** ** ** watching **, *** ***** ****** **** *** **** ****** **** on ******* **. ** ****** ***, **** **** ****** ******* in * **** ** *** *** ******. ***** ***** ****** will **** ********** **** *** *** *** * *** ** deep ******** ** **** *****.

Healthy **********

**** **** ********, ** **** **** * ****** ** ***** for **** ******** ** ****** (**** *********** *** ******** ****) for ** ** **** * *** ********** ** ***** ************. Hyping ** *****, ********** ***** *** ***-**** ******* **** ***** analytic ******** ** *** *****, ***** ********* ******** **** ********'* reputation *** *** ********** ********* ****** **** ** **.

Comments (11)

Undisclosed #1

07/26/17 03:37pm

*** ** *** *** ************ ******** ****** **** **** ********* the ****** *** ******** ** '**** ********' ** ************/******** ************??

*.*. *** ** ********* ** ********?

John Honovich

IPVM | In reply to Undisclosed #1 | 07/26/17 03:41pm

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

*** *******, * ***** ****** '********' ** *** ******* ** a '********' ***** ** ******** *** **** ****** ***** *** it.

* ** *** **** *** ****** *** ** **** *** around *** **** ********* ******* *** ******** (*.*., ** **** learning ***** ************ '*******' ** **/**'* *******?). @*****, *** **** you ****.

Avatar

Brian Karas

IPVM | In reply to Undisclosed #1 | 07/26/17 05:11pm

*.*. *** ** ********* ** ********?

***, ******** ** **** ***** ** ***** *********** ********** (*.*.:*.*** ********* **** ******** / *** *********), ******'* ******** *********, ***. ****** **** *** ********* *** defined ** "**********" ************.

**** ** *** ********* ******* ******* ****** ***** (*********, ***.) applied ** ********** *******. **** ******** ** *********, ** ***** so ***, *** **** ******* ******* ** *** ********** *******, doing * ****** *** ** *********** **** ** "*****" (*******, boat, ***, ***) ** *** *****. ***** *** ******* ********* applications ** ****, *** ***** *** *** *********** ***** ******** unique (*** ****** ****** ********* *********** ******).

*** ***** ****** * ******** **** ******** ******* **************, *** it ***** *** ** * **** ****** ******. **** ** very ******* ********** ** ********* * ***** ***** ********** ***. You ***** ** **, *** ***** *** ** **** **** to ***** * ********** *** **** ******* ***** ***** * competing *** ******* ********** **** ****** ** ***. ******** ******** used ** ***** ***'* *** *** **********, *** ***** *** some ***** ******** ** **** ***** ******** *** ********** *** (many *** ********* *** ***-**********/******** ********).

*** ***** ****** * **** ****, ****-******** ******* *** ******* to ******* **** ** ******* ********* *** ******** ******** ** a ****** ** *******, *** *** ***** *** ***** ******* to *** ** (** *** *** * ******* ***). ****, if ******* **** *** ***** **** ******, *** *** *** tagging ** ***** ***, *** ***** *** ******* * ******* fee (**** ** ******** *** ****** ********** *** *** *****/*********** by ***).

**** ******** ** ***** ******* ** ** **** ***** ** so **** ******** **** ** ** ******** **** ******** ******* will **** ***** ************ ******* ** **** ******** **** ****** the ******** ********.

***** *** ***** *** **** ****** ******** ** ******** ** in ***-*** ********/************ ***** ** *** ** ************ **** **** learning ***** ********. *** *******, *** ***** ** **** ** patent * *** *****-****** ******* ****-******** ******* ** * *** that ** ********* ******** *** ** * *** ****** ********* a ******, ** ******** * ********** ******** ******* ********.

Undisclosed #1

In reply to Brian Karas | 07/26/17 06:18pm

**** ** * ***** *******... ************:

"*** ****** ****** ********* *********** ******"

** ** ******* ************* ** '**** ********' - *** **** me ** ** * ** ***** - ** ******* ** me ** ** **** ** *** ******** ******* ***** ** pretty ****** '**/****' ********* ***** ************.

**** *** *********** *** '**** ********' ********** ** * ******** increase ** ************* ***** *** *****.

*** ****** ***** **/**** ********** *** ** ******, *** **** operational ************ **** ******* **** ***** '**** ********' ** '****' things **** **** *** ******** ******* *** ************* ***** ******** to ***** **** ****.

** * *****?

Avatar

Brian Karas

IPVM | In reply to Undisclosed #1 | 07/26/17 06:42pm

*** **/**** ******* ** *** * *** *******, *** ** is **** *** * ******* *******. * ** *** **** if *** *** ***** ******* ***** *******/************* ** ***-***** ************, which ***** ****** **** *** *** *** **** ** **** the **/**** *******.

**** ******** ** *** ** (********** ************), ** ** **** about ******* ****** **** **** *** ********, *** **** ***** pattern *********/***********, ************ ** ***** ***** ****** ***** *** ** as **** ** ***** **** **** *** ****.

*** *** ***** * *** ** ****** ***** ***** ** cancer, *** **** **** *** **** ** *** ***** ** know *** ** ********* ** ********* ****** ********* ********.

Avatar

Skip Cusack

In reply to Brian Karas | 10/10/17 02:36pm

******* - *'* *** ** ******** *** *** ********* ** not ***** ******....

***** *** * ******** ******* ***** ****** ** **** (***** vs. *** ****) **** ***** *** *** *** ****** **** an *********, ** **** ********. ** **** ** **** ** hardware. **** ** ********* * *** ****, *** **** ***** waves ******* **** ******** ***** **********.

****** ******** ** **** ******** *******, **** ********, **** ******* this ****** ** ********* *** ******** ** ******** ******* ** not ********.

*********, ** ************* ** **** *** *** *** ****** **** Learning **********, *** ****** **** **** ** **** ** ******** like ********** *** ******* ** * *** **** ** *********** to *** *********.

Undisclosed #1

07/26/17 07:03pm

*****...

"* ** *** **** ** *** *** ***** ******* ***** patents/patentability ** ***-***** ************, ***** ***** ****** **** *** *** you **** ** **** *** **/**** *******."

**, ******** * ** ** ********* - * ***'* ***** that ********* *********** ****** ** ********** ******. *** '*****-******' **** set *** ** ********/****** ** ****** *********** ******. **'* **** simple ****.

**** ***** *** ******** ** ********* (* *****) ** *** ability ** **** '*****' **** *** ******* ***** **** **** fast ****** ** ****** * ********* *** **** *** ****** that *****.

** **** ****** *** ** *** ***** *****, *** ********* in *** ******** **** ** ** ********* *** **** **** they **** **** *** ***** ******* - ******** **** **** word **** ********** **** *******.

********* ************* ***** *********** ** ******** ** *********** ***** ****** on * **** **** ********** ** **** ** ******* **** really **** ******.... *** ** **** ******** ** ****-***** (** VCA ***) ** * ******* ****** **** ***** *** *** capabilities ** ******** ******* ******** ******** ********, *** **** ******** has *** ********* ** ***** ****** ** *** **** - like *** ********* ********** *** ****** **** **** *** ************ to ******** ******** *****.

Avatar

Brian Karas

IPVM | In reply to Undisclosed #1 | 07/26/17 07:16pm

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

***** **** ***** ********* ******** ********* (** ******** ******) *** in ***** ******** ****** **************. **** ******** ***** ******* ***-****** approaches ** *** ** * ******** ****** ** ********** ***** from ***-***** (***** **** *****, **** ******** ********, ******* ****-******* coupled **** ******** ****** **** ** ********* ***** *******, ***.)

** ***-***** ********** *** ****** ******** **** ** **** ** object**, **** ***** ****** *** ** ***** ** *** ** that ** * *******/******/**** ******** ******.

** **** ****, *** ***** ** *** ******** ***** ** analytics. ****** *****, ** *** ****** ** ***** ******* **** an ******** ********* ******, ** ******* **** *******, *******, *** expensive. ***** ****** * ***** * **** ** ******* *** embedded *******, ******* ********* *********** ** *** ******/************* **** **** than *** ** (*** ** ***** ******* **** ****-****** **** of ***** ******** ** ***** ****** ******** ****** ********* ***** get *****).

******** *** ** ********* ***** *** *** ******** **** * major ******, *** *** ***** **** **** ****** ********** (*** marketing/sales) *** *** ********** ***** **** ***** ***** *** **** figured *** **** ** ****** ** ** ***** **.

Slava H

3dEYE Inc. | 07/27/17 08:25pm

* ***** ************* ************* ** ********* ** **** ** *** ** ******** *** security ********.

*** *** ****** ********* ** **** *** *** **** ** research ** *** *********.****://***.**********.**/.

Avatar

Brian Karas

IPVM | In reply to Slava H | 07/31/17 06:46pm

*********, **** ** **** ** * *********** **** **** ** actual ***, ************ *** ******** ************. **** ***** ****** ** DNN-based ********* ****** *** **** ********** *** **********, ** ********* below.

* ***'*/***'* ******* ** *** "**** * *****" ******** ******* I ** *** **** ****** ***** *** ********** ******* ********* work ** * *** *****.

*** ******** ************, *** *********** ****** ***** ********* ** **** form ** ******* **********, ** **** * ***** ****** (**** likely * ******) ***** ***** ********* ** *** ******. **** could ** ** **** *** ***** ******** ** "***", ** to ****** ***** ********* ********** (******** * ****** ******** ** be ********* **. **** ***-***********).

***** *** * *** ****** **** **** ** *********/**** ********* to ** ** *********** ****** *** ************:

  1. ******** ********* *** ********* *** **** ******/************/****** ******** *** ******* around **. ************* ******* ***** ********** **-*****, **** ****** *****. The ******* ******* ****** ********, ***** **** ** ***** ******** cannot ** ****** ****** ****** **** ***** ** ****** ** attackers ** *** ****** ** * ****** *** *&*/******* ********. Not ****** ** ** **********, *** ** **** **** ****** a ****** ****** *** *** ******* ** **** ******* **** of ***** ********.

  2. ****** ********* **** ******* ******* ** ** ****** ****** ******** giving ** * **************. ******** ******* **** *** ******* ** generally **** ****** ***** ****** *******. ****, ******** ********* ** image ** *************** *********, ** ** ***** ** ***-****** ****** out ** *** ***** *** **** ******* ******** **** **** some **** ********. **** ** ********* * ******* **: **** for **** ******->******* *** ***** ****/*****/****** ***** ********->******* *** "*********** motion"->then ******* *** *** **** ******* *** *** *** **************. This ***** *** *** **** ** ** **** **** **** inject ******** ****** ****** **** *** ****** ** ****** **.

  3. ***** ****** ******* ***********, ** ********** ** ****** *** *** would ****** *** **** ** *******, ****** **** **** ******* with *** **** ******* (********, *** ****** ** ** ******** more ****** ** *** ****** ** ***** ****** ** *******/********* labeled **** **** ********), *** ******* *** ****.

*********, ** **** * ******* ****** ********-***** *** ********* ******, you ***** **** ** ********* **** **** ** ******* **** that ******** ********** *******, **** ******** ****** *** ***** ** motion (***** ***** ******* ******** ********** ** **** ******). ** the ****** ***** ******** ******** *** ********* ****** *** **** 1 ******, ** ***** ******** ** *****.

***** ** ******** ***********, ** ** **** **** ** **** which, ** ***, ********* *** ** *** (* ***** **** is **** * ****** ********** *** ******** *** ***** ***********-******** cameras). ******** *** * ********** ****** **** **** ****** ***** require **** ****** ** ****** ********* *** * **** ****** motivated ********. ** ******* ***** *** *** ***** ** ************ for ***** ***** *********, ** *** **** ** *** ****** today, *** ******** *** *********** *** *** ***** ** ****, those ********** *** ******* *** **** **** *** *****-****** *****-*****-***-*********-***** armed ******.

Slava H

3dEYE Inc. | 08/02/17 04:34pm

*** **** ** * *********** ********, *** ********* **** ******* would ****** *** ******** ******** *** ** ** ****.

* ***** ***** ******** ** ******** ******* *** ***** ***-******* existing ****** **** ** ******** *** ******** ***** *** ****** layer *** ***** *****. ***** **** ** *** ****** ******** and ******** ***** *** ******.

** * **** ** *****: ****** **** *** **** ** optimize *** **** ** *******. ****** ****** **** *** ******** to ****** *********** ************; ****** ******* ** ***** *** ***** distribution *** *** ********* ** *********** ********. ********* *** *** resistant ** *********** ********.

******* ************** ** ***** **** ** ********* ** **** ******** and ******* ***** ******** ****'* **** ** ***** **** ** optimise *********** ******, ********* ******** ** ******** ** ********* *** working *** **** ****. (**** *** ***** ** **** *****: https://arxiv.org/pdf/1412.6572.pdf)

** **** ********* *********** **** ****** **** ***-*******, ****-***** ****** model ********** ***** ***** ********** ** * ******* **** **** some ***** ** * *****.

** ** ****, **** (********** *********** ********) ** ** ****** area ** ******** *** ** ***** * **** ******** ********* and *** ******* ** ****** ******.

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

Avigilon Favorability Results 2019 on Jan 15, 2019
Since IPVM's 2017 Avigilon favorability results, the company was acquired by Motorola and has shifted from being an aggressive startup to a more...
Gorilla Technology AI Provider, Raises $15 Million, Profiled on Jan 15, 2019
Gorilla Technology is a Taiwanese video analytics manufacturer that recently announced a $15 million investment from SBI Group, saying this...
Managed Video Services UL 827B Examined on Jan 09, 2019
Historically, UL listings for central stations have been important, with UL 827 having widespread support. However, few central stations have...
IPVM Best New Products 2019 Opened - 70+ Entrants on Jan 07, 2019
The inaugural IPVM Best New Product Awards has been opened - the industry's first and only program where the awards are not pay-to-play and the...
Axis Tailgate Detection Tested on Jan 04, 2019
Axis is aiming to tackle tailgating, one of access control's biggest issues, with the Tailgating Detector ACAP application. This camera app claims...
The Battle For The VSaaS Market Begins 2019 - Alarm.com, Arcules, Eagle Eye, OpenEye, Qumulex, Verkada, More on Jan 02, 2019
2019 will be the year that VSaaS finally becomes a real factor for professional video surveillance. While Video Surveillance as a Service (VSaaS)...
Scam Research And The $86 Billion IP Camera Market on Dec 19, 2018
Scam. The most widely cited research numbers in many, if not most, industries come from a growing number of Indian 'market research firms'. We...
Cisco Meraki New Cameras and AI Analytics on Dec 14, 2018
Meraki has released their second generation of video surveillance with 3 new cameras, AI-based video analytics, and 2 cloud-based storage...
Top 2019 Trend - AI Video Analytics on Dec 10, 2018
160+ Integrators answered: What do you think the top industry trend will be in 2019? Why? AI / video analytics was the run-away winner with...
Alarm.com "AI" Video Analytics Tested on Nov 30, 2018
Alarm.com has announced what it calls an "artificial intelligence (AI) architecture and video analytics service", touting that  Alarm.com's...

Most Recent Industry Reports

The IP Camera Lock-In Trend: Meraki and Verkada on Jan 18, 2019
Open systems and interoperability have not only been big buzzwords over the past decade, but they have also become core features of video...
NYPD Refutes False SCMP Hikvision Story on Jan 18, 2019
The NYPD has refuted the SCMP Hikvision story, the Voice of America has reported. On January 11, 2018, the SCMP alleged that the NYPD was using...
Mobile Surveillance Trailers Guide on Jan 17, 2019
Putting cameras in a place for temporary surveillance where power and communications are not readily available can be complicated and expensive....
Exacq Favorability Results 2019 on Jan 17, 2019
Exacq favorability amongst integrators has declined sharply, in new IPVM statistics, compared to 2017 IPVM statistics for Exacq. Now, over 5 since...
Testing Bandwidth Vs. Low Light on Jan 16, 2019
Nighttime bandwidth spikes are a major concern in video surveillance. Many calculate bandwidth as a single 24/7 number, but bit rates vary...
Access Control Records Maintenance Guide on Jan 16, 2019
Weeding out old entries, turning off unused credentials, and updating who carries which credentials is as important as to maintaining security as...
UK Fines Security Firms For Illegal Direct Marketing on Jan 16, 2019
Two UK security firms have paid over $200,000 in fines for illegally making hundreds of thousands of calls to people registered on a government...
Access Control Cabling Tutorial on Jan 15, 2019
Access Control is only as reliable as its cables. While this aspect lacks the sexiness of other components, it remains a vital part of every...
Avigilon Favorability Results 2019 on Jan 15, 2019
Since IPVM's 2017 Avigilon favorability results, the company was acquired by Motorola and has shifted from being an aggressive startup to a more...
Gorilla Technology AI Provider, Raises $15 Million, Profiled on Jan 15, 2019
Gorilla Technology is a Taiwanese video analytics manufacturer that recently announced a $15 million investment from SBI Group, saying this...

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