Aegis AI Gun Detection Video Analytics Startup

By: Sean Patton, Published on May 07, 2019

Gun detection analytic startups are increasing as the promise of AI and the threats of active shooters grow.

One company, Aegis AI, is being led by a Marine Corps Veteran Sonny Tai, who aims to use his experience in the military to help solve this problem.

We spoke to Aegis, to better understand their gun detection first approach, go-to-market, and how they position their video analytics in campus environments.

In this note we look at:

  • Who is Aegis
  • What Type of Video Analytics
  • What Customers is Aegis Targeting
  • How Much Does It Cost
  • What is Aegis Go-To-Market
  • Developing Image Datasets

*** ********* ******** ******** are ********** ** *** promise ** ** *** the ******* ** ****** shooters ****.

*** *******,***** **, ** ***** *** by * ****** ***** Veteran***** ***, *** **** ** use *** ********** ** the ******** ** **** solve **** *******.

** ***** ** *****, to ****** ********** ***** gun ********* ***** ********, go-to-market, *** *** **** position ***** ***** ********* in ****** ************.

** **** **** ** look **:

  • *** ** *****
  • **** **** ** ***** Analytics
  • **** ********* ** ***** Targeting
  • *** **** **** ** Cost
  • **** ** ***** **-**-******
  • ********** ***** ********

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

Aegis ********

******* ** ***** ****, Aegis ** ************* ** Chicago, **, *** ******* 4 ****-**** *********, *** technical *******. **** **** co-founded ***** ***** ****** ***** ** ***** as * ** ******, part ** ***** *** spent ** *******-********** ********** and*** ******, ** **-********* ** Program *******, *** ********* the ******* ***** *** detection *********.

***** **** ***** ********* include *** ********** ** Chicago **************(*** **** ***********). **** are ******** ** **** additional ***** *** **** a *** *********** ****** in ***.

Goal - ********** ****** ******** **** ** ****** ********

***** **** *** ***** over * **** ***** leaving ****** **** ******* speaking ** ******, **********, and ********* ******** ********* to ********** *** ** could ******* *** ********** in ****-********* *** ********** to *** ****** *** more ********* ****** ******** to ****** ******** **********.

**** **** **** ******** directors *** ****** *********** are ********* **** ********* calls ** ****** **** 5 ******* **** *** first ***** *****, *** that *** ******* ******** time ** ****** ** site ** ****** **** the ******* **** ********. Aegis **** *** **** of ***** ********* ** to ******** *** ********* time, *** ******* ******** information ** ***** ********** so **** *** ***** the ******** ******* *** safer.

**** *-****** **** ***** shows * *** *** detection ****** ******:

***** **** **** **** be ******* *** ************* videos ** ***** ******** in ********* ****** *** corporate ****** ************, ****** that *** ******* **** videos ******* ******** ********* video **** ********** ****** are *** ***** ****** market.

Gun *********, ** **** ***********

******** *** **** ** video ******** ********, ***** is *** ******** **** recognition *** ** ******* on ***** ***** ***** analytics ** ****** **** for ****** ************. **** said ***** ****** *** detect ****** *** ***** non-gun ******* (*.*. *********, packages) *** ******* **** typical ***** ******** ********* like ********* *********.

**** **** ***** ****** networks **** *** **** trained ** ********* *** face ***********, *** **** do *** **** ***** to ******* *** **** recognition, ****** *********** ******** already ** **** ***** that *** **** ****** with ***** *******.

Gun ************** *** ************** ********* ******

***** **** **** *** not ******* ***** *** neural ********, ******* ********* and "******* *********" ****-****** YOLOv3. **** **** *** primary ************* **** ** strip *** ******** *** capabilities ** ****** **** types ** *******, *** training *************** *** "******", "long ***" *** "********". They **** *** ****** network ** ******* *** contours ******* * ****** and ******** ~**-** *** required ** ****** * gun ****** * ****** of ***** ** ******.

**** ***** **** ******* test *********** *** ****** with **** ****, ******, dark ***** *******, *** polished ****** *********, *** claim **** **** ******* their ******** ** ******* these ******. ******* *** most ***** *********, **** noted **** ********** ***** density *** **** ******** are *** ******* ********** to *********.

Cloud ****** / ** **-******* *********

***** ****** ********-**** ******* that *** ******** ** Amazon ***** ******* *** there *** ** **-******* or ********* *******. **** utilize *** *** ***** existing ** ******* *** do *** **** ******* to *** *****.

**** **** **** ******* encrypted ***** ******* ***** available, *** ******** ***** unencrypted ***** ** *** customer's ******* ** *** do *** ******* **. They **** ***** ******* for ******** *** ********* on ****** ******* *** said **** *** *********** developing ***** *** ******** plugin ** ******** ******* to ***** ********.

*******

***** *** * ****** SaaS ************ ***** ** $30 *** ****** *** month, ***** ******** ** hardware ********** ** *********** on-premise *** ******** **-*** video *******.

***** **** **** *** offering * **** ***** of ***** ********* *** end-user *******, *** ******** less **** ** ****** customers ** ***** ***** year, *** *** ** track ** **** ******* goals.

Channel *********

***** **** **** *** currently ********* ****** ** large *** *****, *** have **** **** ** channel ******* ***********. **** said **** *** ********** the ******** ************* ** be * "****-*******" ******, but *** ******* ******** with *** ***** ****** deployments ** ***** *** optimize *** ****** *** each *******.

No ******* *** ************

***** **** *** ******* any ******** *** ************ but **** ***** ****** is ********* ******* **** Genetec, ********* *** ******* VMS ******* **** ***** streams *** **** *** send ******/****** ** ***** VMS. *******, **** ** not **** ******** *** overlay ****** ** *** VMSes.

***** **** ***** ** a *** *********** *** viewing **** *** ******** reference *****, **** ***** video ******* *** ************* management.

Comments (22)

... **** ********* ***** ** police **** * ******* from *** ***** ***** fired

* **** ** **** hard ** ******* **** it ***** * ******* for *** ***** *** call ** ***** ******. Police are ******* **-***** ****** 5 ******* ** *** first *****, *** **** is * ******** **** being **** **. 

*'** **** **** ****** a *** ***** ******. Some ** **** **** the ********* *****:

*** ****** ******** ** Active ******* ********* - Washington *.*. ****** ********* Research *****

*'** ****** ******* **** a *** *****, *** I *****'* ***** ******** that ******** **** ** takes * ******* ** average ****** ****** *** called.

 

* **** * *** a **** ****** ** this ********. * ***** heard ** *** "* minute" ********* **** * attended * "***, ****, Fight" ******** ****** ** a ****** ***. *'** then **** ** **** by ******** ********* *******, without ***** **** ** track **** * ******* source.

*'** **** **** **** statistic **** ******** **** LEOs ******* **** ****** officer ** ***** (* met * ***** ** Chiefs ** **** ********** last ****), *** ****** has ******* **.

** ******* *** * primary ****** **** ******** the **** ******* *** calls, **** ***** ** great. * **** ** Parkland, ** *** ** seconds ***** *** ***** round *** **********, ***** may ******* **** * minutes ** ***, *** I **** ***'* **** enough ****. 

*** (*) ****** ****** is ********** ** * number ** *** ******** response ********.  *** ***** for *** ***** ** referred ** ** “******** bias”.  ****** ****** ********* it ** *** **** Unthinkable.

**** ****** ****** ********, including ******, ** **** we ** ** ****** normalcy ****. * ******* and **** *** ****** of ******* ******** *** ******* the ***** *** *** saved *****, *** * have ** ****.

* ****** **** *** contemporary ***** **** ***** the ******* ********* ** the ***** *** **** from *** *****. ********** news ******** *** **** case ******* **** ***** coming ** ****** * minute ** *** ***** shots *****.

*'* *** ********* ** denying **** *** **** said, **** ******* *** data.

*******, *** **** * great ***** ***** ********* normalcy ****.  * ***** you *** ********* **** point **** **** *********... "you **** *** **** to *** ******** *** will **** ** **** level ** ********".  ****** inoculation ** ******** ** you **** ** ***** effectively ****** * ******** incident.  ** *** **** train ***** *** *** it ***** *** **** fail ***** ******** *** must ***** ***** *** can't *** ** *****!

*** *** ****** ** convenience *****/**** ******* ** examples ** *** ***** gun ********* ********* **** - **** ***** **** this ***'* **** **** intend **** ** ** used ***?

* **** **** *********** - ******* ** ******-*** robbery ********** (**** *** ones **** **** ** their *** *****), * think ***** ******** ***** actually ******* **** ***** - ******* *********** *** actually ** ******* ****** anyone **** ****.

*** ******* ** *** gun **** ***** ***** robbed ** ********* *** hand **** *** ****.  and **** **** ******* the ****** ***** ***** that ***, *** ****?  gun ********* ********* ***** certainly **** ** ***** scenarios.

Plus *********** *****/**** ********* *** ***** ******.

** ***** ** **** they ******* *** *** 2nd ********* ***** ***** on - *** **** videos ** **** **** they ***** **... *** then **** ** ****** involved ***** ********* ****** to ***** ** ****** shooter ********* ******* - cuz ****'* **** *** buzz ** *** ***** now - *** **** shifted ***** *** *** potential ** * ****** return.

****** ****** ******** ********* (I ** ** ******, but **** ** ** perception) ***** *** ***** blazing **** -- ********* gun ******** ********* ******** useless - ** ***** in ********** ** *** obvious ***** ******** ** strong-arm ******** *********.

  

** *****,

*'* *** ** *** founders. ***** ** ****** any ********* ** *** best ** ** *******.

*** *** ****** ** convenience *****/**** ******* ** examples ** *** ***** gun ********* ********* ****...

We **** *********** ***** ********* *** *** *******:

- ** *** *****, it ** **** **** abundant, ***** ***** **** with **** **** ********* and ******** ********, ** can ***** ** * valuable ********** ** ******* training ****.

- ** **** ****'* want ** ********** ******* with ***** ******* ** people ***** **** ** a **** *****, ** using ***** ********* *** a **** *** ** demonstrate *** ************ ***** real **** ******** ****** crime ******* ******* ** stock *******.

** ***** ** **** they ******* *** *** 2nd ********* ***** ***** on - *** **** videos ** **** **** they ***** **... *** then **** ** ****** involved ***** ********* ****** to ***** ** ****** shooter ********* *******...

Violent *** ******* *** *** ***** **** *** *. ** ***** **** ** ******** ********** *** ******* ***** *** *****, *** ***'** *****, ****** ****** **** ****** **** ***. ******* ************ ***** ** ******* ** ****** ********* ** ******** ********* ** **** ***** ****** ****** ******* **********, ****** *** ******* ******* ****** *** *** ******** ** *** * ******** **** **** ** ***** *** **** ** **********, **** **, ***** *** ******* ******* ** ***** **** *** *** *********** ***** **** *** * ******** ** *** ****. 

****** ****** ******** ********* (I ** ** ******, but **** ** ** perception) ***** *** ***** blazing ****...

You *** ********** *****. *** ***** ** ******** ****** *** ********* ** **** **** ***** **********, *** **'* ***** *** ******* ** ******** ****** **** *********** ********* ** **** ****. *** ******* - ** ********, *** *********** *** ** **** **** *** ******* **** ****** **** ***** ***** ***** *** ***** ***** *** ***** (

- ********/********* ** ********

- ********/*********

- **********

...which *** *** ******** ****** ** *********** **** ******* *** *********** ** ********** *** ****** ** **** ** ******** *** *** ******** ********* ** **** ********* **** ********* ***** ******* *** ********.

* **** ***** **** been * *** ** companies *** **** **** and **** ********* ******** vision *** *********** ************. I'm *** ****** ** have ** *** ******* out - *** **** thing ** **** ** do ** *********** *** underdeliver. *******, ** **** a **** ** * data ******* ****, ********* who **** **** **'** doing *** ****, *** we **** **** ****** distinguished ********* *** ******* in **. **'** ******** to ** *********.

****** *** *** ********! I've **** ** **** reader *** **** * year ***, *** *** of *** ********* ****!

**** *** ** *** best, **** ******** ****** I've **** **** ** my ************* *********** ********* in * **** ** IPVM.

*****, ***!  ;) 

***** ***! * ***** that ** ** *** together * ********** *** talented **** *** ******* ourselves **** *********, ** can ********** **** ** impact ** * ********** way **** ***** *****.

**** **** *** *** provocative ** *** :-) It's ******* ** ** skeptical, ** *** ****** be. ***** *** *** many ******* ** **** industry ******* ** **** a ***** **** *** massively ************.

 

* ***** ***** *** ultimately *** ***** **** to **** ** * company ** ******* ** this *****:

*. **** ***** ******** page *** *** ** they **** ****** **** data ******* ********* (**** specifically - ********** **** neural ******** *** ******** vision). ******* *** ***** an ***-***-***** ***** ** an **** ****** **** set *** *** ** to **** ****-****. ** takes * *** **** to **** ** ********.

*. **** **** ****** significant ******* *******? ** have ****** ****** $** (will ******** ****), **** of ***** ** **** VCs *** **** ***** investors ** ********* **** as ****, ********, *** ClassPass - *** **** do *** **** ****** with ***** ********* *** diligence.

*** ** ********* ** a ****** ************ ** the ****** ** *** end ****/******?

** **** * ************ with *** ******** ****** via ***/*****, ** ** can ******* ** ** the ***.

**** **** **** *** don't ********* ****** ****** directly? (**, *** ****** sends ***/***** ** * list ** *****, *** those ****** *** ******** to ****** ******)

** **** *****, ** don't, ** *** *** there *** *** **** bureaucratic ****** ** **** through ** ***** *** integrations **** ***** *** enforcement **********.

*******, ** **** ***** for ************* **** ** the ******, ****** *******:

(*. *********** **** * computer ***** ******** ****** after *** ***** *** been ********* ** * human

(* ******** *** *** monitoring ****** *** ******* 911.

** *****'* *********** **** yet, ******* ********* **** actually ***** ** *** the ****** **********. *********, the ****** ** ** 3-5 ******* ** * school ********** **** ** education ***********, *** *** Director ** ******** *** the *** (** **********) in ********* ***********. 

*** ***** ** **********/***********/****** even ** ******?  $** a ***** *** ****** is * *******. 

**** **** ******* ************ networks *** ******** ************* with *** ********* :)

** *** **** *** plans *** ******* **** OnSSI ******** (*** ***** by *******)?

** ***** ************ **** VMSs ** ** ******* customers *** *** * specific ***. ** ***** love ** **** **** Ocularis/Qognify, *** ** ***'* have * ******* ******** yet. **********, **** ** co-founder *** * *** University ** ******* ***** and **** *** *******, but ** *****'* **** able ** **** **** as * ******** *** :-P 

** *** *** ********* is ********* **** ** of ******** ** **. We ** * *** of **** ** *** K-12 ***** *** *** very ******* ** *********** of ******* ** ******, lockdown *** ********* ************* and **************. **** ** about *** *** ******* that * **** **** across *** *** *** pricing ***** ** **** reasonable. 

*** *** ***** * have ******* ** **** these ********* *** ****** to **** ***** *** and *** ** *** go ** ******. ** the ******** ** ***** to ** ***** ********, retail **** ** * different **** **** ******* with * ****** ****** that *** ******* ************ or **** **** * state ******** ** * legal *********** **** ** sell ** ***** *******.

 

* **** * ******** architecture ********* ******** ***** the ******** ** **** real-time ***** *********:

*. **** ** **** expensive ** ********* **** live ********* ***** **** customer **** ** **** cloud? 

*. **** ***** *** delay *** ******* ***** live *******?

 *. *** ** *** address ********* ******* ****** bandwidth?

*. *** ** *** address ********* ******* ********?

******: **** ******* *** been ***** ** *** own **********:********* ***** *** ******** Of **** ****-**** ***** Analytics

** *****, ****** *** your *********! ***** *** issues ** ***** ******* with *** *********:

 
*. ** **** ****** at ******** *********** *** low ****** *** ******. As **** ** *** customers' ******* *** ******* by **** *******, **** doesn't ************* ******** ***** quality, *** ************* ******* bandwidth ************. ** ******* deployment ** **-** ******* is ***** ********** ** one ****** ********* *******. Also, ** **** ***** we *** ******** *** basic ********* ****'** ******* doing, *** **** **** images **** ****** ** detected, ******* ******** ********* by **-**%. **** ***** that ********* ***'* * huge *******, *** ** definitely *** ******* **** installation ****** ******* ******** on ****.
 
 
*. ***** ** ******** very ****** ***** ****** the ********. ** *** of *** *********** ** can ******* *** ******* an ***** ****** * second ** ** ***** stored ** *** ***. The *** ** *** at ********* ** ******* their ******* *** ***** VMS, ***** ** * local ************* ******* **** we ********* ********* **** with ***** ******** ********** to *******.
 
 
*. **** ** *** customers ***'* **** ********* concerns, *** *** *** ones **** ** ** can *** **-**** ****** detection (** ** #* above), ** *******-***** *********** to ******* ***** ********* concerns. **** ** ****** counter-cyclical: **** ***** ** a *** ** ******** in ********, ******* ****** aren't ***** *** ******** as ****, ** ****'** leaving **** ** ***** to *****, ** *** system **** ****** **** existing ********* ****** ********.
 
 
*. *** ****** *** build **** ******* ** mind **** *** ****** up. *******, ** ***'* analyze ***** ** *** other ********** ************ ***********: We're **** ******* ****** without *** ******** ********. Second, ** **** *** customer **** ***** ***, so *** **** ********* time *** **** ***** un-annotated ****** ** **** short. *****, ** *** the ****-************ ********* ********* by *** ********'* ***, which ***** ** **** has ******* ******** ** part ** *** *** purchasing *******. **** ** our **** ******* *** customer's ******* ****** *** an ***** ***** **** back ** *** **** of * *********. ***** we ********** **** **** customers *** ***** **** concerns ***** *** **** being *********** ********** ** all, ** ******* *** system ** *** **** privacy-compliant ****-**** ***** ********* solution ********* *********, *** other ********* **** ******* additional *** ********, ****** data ********* *******, ** more ***-***** ******** ** hardware ******** * *******.
 
 
**** **** *****! 

***** *** *** *** fast ********:

*. ** *** ******* it *** ********* **** you **** **-** ***  , **** ***’* *** bandwidth, *** * ** sure *** ***’* ****** weapon ** *-* ***. second * ** *** sure *** *** ** the ******** ** *** cases ******** ** ** RTSP ****** *** ********* the ****** ** ****** that *** ****** *** configure ****** ** ****** or ** *** *** level. 

*. * ***’* ********** how *** *** ***** on *** ****** ********* analytics. *****, ** ** not ******** *** ******* massive ****** ** ***** alerts. ******, ** ** irrelevant ** ** *********** which *** ******** ****** which ** *** ******** of **** ***-**** ** far ** * ********** it. 

*. * ***** ***** that ***** ** ******* issue ****** *** ******** especially *** * ******** service ** *** *******. 

******** *** ***** * am *** ********* **** you ********** *** *****.

***, **** ** *** minimum ****** **** **** is ******** ** ***** to ********* **** **** is * ******? 

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

Schmode is Back, Aims To Turn Boulder AI Into Giant on Sep 16, 2019
One of the most influential and controversial executives in the past decade is back. Bryan Schmode ascended and drove the hypergrowth of Avigilon...
Panasonic 4K Camera Tested (WV-S2570L) on Sep 13, 2019
Panasonic has released their latest generation 4K dome, the WV-S2570L, claiming "Extreme image quality allows evidence to be captured even under...
ASIS GSX 2019 Final Show Report on Sep 12, 2019
IPVM went to Chicago for ASIS GSX 2019, with many exhibitors disappointed about traffic and the exhibitor schedule changing next year. However,...
Genetec Stratocast VSaaS Tested on Sep 05, 2019
The VSaaS market is rapidly expanding in 2019, with Verkada, Meraki, Eagle Eye, Avigilon and numerous startups growing their market share. When we...
AI Video Surveillance (Finally) Goes Mainstream In 2020 on Sep 03, 2019
While video surveillance analytics has been promoted, hyped and lamented for nearly 20 years, next year, 2020, will be the year that it finally...
Scylla AI Video Analytics Company Profile on Aug 29, 2019
Scylla, an AI analytics startup, says they are targeting 1 Billion dollar valuation in 5 years and it "is not rocket science" to detect weapons and...
Uniview 4K Camera Tested on Aug 29, 2019
In our 8MP / 4K Fixed Lens Camera Shootout, Uniview's low end 8MP was firmly in the middle of the pack. Does their higher end Pro Series 4K camera...
UK Facewatch GDPR Compliance Questioned on Aug 27, 2019
Even as the GDPR strictly regulates biometrics, a UK company called Facewatch is selling anti-shoplifter facial recognition systems to hundreds of...
Warning: Windows 7 Update Crashing NVRs on Aug 26, 2019
Windows 7 updates are causing VMS servers to fail to boot. After running the update, impacted systems do not boot as normal, instead display this...
Anyvision Facial Recognition Tested on Aug 21, 2019
Anyvision is aiming for $1 billion in revenue by 2022, backed by $74 million in funding. But does their performance live up to the hype they have...

Most Recent Industry Reports

US Army Base To Buy Banned Honeywell Surveillance on Sep 17, 2019
The U.S. Army's Fort Gordon, home to their Cyber Center of Excellence, has issued a solicitation to purchase Honeywell products that are US...
Vivotek "Neural Network-Powered Detection Engine" Analytics Tested on Sep 17, 2019
Vivotek has released "a neural network-powered detection engine", named Smart Motion Detection, claiming that "swaying vegetation, vehicles passing...
Schmode is Back, Aims To Turn Boulder AI Into Giant on Sep 16, 2019
One of the most influential and controversial executives in the past decade is back. Bryan Schmode ascended and drove the hypergrowth of Avigilon...
Manufacturers Unhappy With Weak ASIS GSX 2019 And 2020 Shift on Sep 16, 2019
Manufacturers were generally unhappy with ASIS GSX, both for weak 2019 booth traffic and a scheduling shift for the 2020 show, according to a new...
How Cobalt Robotics May Disrupt Security on Sep 13, 2019
While security robots have largely become a joke over the last few years, one organization, Cobalt Robotics, has raised $50+ million from top US...
Panasonic 4K Camera Tested (WV-S2570L) on Sep 13, 2019
Panasonic has released their latest generation 4K dome, the WV-S2570L, claiming "Extreme image quality allows evidence to be captured even under...
ASIS GSX 2019 Final Show Report on Sep 12, 2019
IPVM went to Chicago for ASIS GSX 2019, with many exhibitors disappointed about traffic and the exhibitor schedule changing next year. However,...
Installation Course - Last Chance - Register Now on Sep 12, 2019
Last Chance - Register Now - September 2019 Video Surveillance Install Course. Thursday, September 12th is your last chance to register for the...
Commend ID5 Intercom Tested on Sep 12, 2019
Commend touts the new ID5 intercom as 'timelessly elegant' and the slim body, glass front touchscreen indeed looks better than common, but ugly,...
US State Department: "Chinese Tech Giants" "Tools of the Chinese Communist Party" on Sep 12, 2019
The US State Department has called out "Chinese tech giants" for being "tools of the Chinese Communist Party" in a blunt new speech that makes...