Gun Detection Analytics Are Here, Says Startup

By: Brian Rhodes, Published on Jul 03, 2014

A timely innovation, or cashing in on tragedies?

A new video analytics company is touting its 'gun detection' analytics that can trigger as soon as a weapon is drawn, potentially alerting authorities in seconds and saving lives.

Are they crazy, or will this be a powerful defense against active shooters and lower the risk of gun violence? We spoke with the company and take a look at its features, pricing and positioning inside.

* ****** **********, ** cashing ** ** *********?

* *** ***** ********* company ** ******* *** 'gun *********' ********* **** can ******* ** **** as * ****** ** drawn, *********** ******** *********** in ******* *** ****** lives.

*** **** *****, ** will **** ** * powerful ******* ******* ****** shooters *** ***** *** risk ** *** ********? We ***** **** *** company *** **** * look ** *** ********, pricing *** *********** ******.

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

Overview ******

*** ***** **** ***** demonstrates ********'* ******* ********* analytic. *** *** ***** below ********* *** ******** of *** *** **** the ******, *** ******** speed ** *** *** shooter, *** *** ********** interval **** * ******* is **********:

********'* ************,*********, ****** *** ******** alarms ********** ** *** type; ********, ******, ** shotguns *****. **** ***** below ** *** **** demo ** '******* ******' compared ** *** ******** in *** ******** ****:

Key **************

*** ******* *** ******** requirements ** *** ******* combined **** ********. ** a *******, ******* **** have:

  • **** ** ****** ********** (no *** ******)
  • ***** ** *******
  • ******* ********* ******
  • ***** *** ********: *** company ********* *** *** of **** ** "*********, but **** ** ******** on ********** ****** *****"
  • *** ***** *********** ******* (but ** **** ************* given)
  • ******* *** ********* ******* at * ****** ** 10 **** ***** ****** (although '*** ********* *****, but ******* *****'.)

******** ******* ** * customized ****** (****** ********) containing '************ ****' **** can ****** ** ** 100 *** ***** **********. At ******* ********************, *** ******** *** support ** ******* ** 720p **********.

*******

******** ** ********* ******** to ******** ************. *** ******* ********** that ***** ******* ******* on ******** ***** *** site ***********, *** ****** MSRP ** ~$**** *** camera *** **** ***, and ************ $*** *** year *** ******** ***********.

******* ******** ******** *** required ******** ********, ********** services, ************* *** *********** validation.

Secret *****?

***** *** **** ******, we ******* *** ****** on **** *** ******** picks ******** *** ** a *****, *** ***** alarming ** ****** ***** 'like * **********' *** example. ******** ********* ****:

"[** ***] * ****** developed **************-***** ****** **** recognizes ***** *********, *** color ** **** ******** in. *** ****** ******* classifier *** ********* "***" the ********** ******* * broomstick *** ** **."

*** ******* **** ******* the ******** **** "******** *********** *** **** guns *** ********" *** ******** "*** **** *********** ** silver ******* ******** **** black".

Buying ********

********* ** *** ********* dealer ** ********. *** sales, *******, *************, *** support **** **** **** the *******, **** ** plans ** ****** ** outside *******. *** ******* claims **** ** ** part ******* ** *** customization *** ************* ******** for **** *****, **********:

"******** *********** *** ************ testing **** ******** ********* capability *** **** ******. Factors **** ** ******** scene ********, ********, *** optics *** ******** ** scene-specific *************** **** ******** is ******** ** ****** to."

**** **** **** ****** suitable ******* ** ************* labor ** ******, *** will **** **** * customer's ******** ************ ****** if ******. ******** **** that ********* ******* "***** **** ********** **** area ******* **** ********, allows *** *** *********** of **** ******, *** a **** ** *-**** addresses *** **** ******* numbers ** ** ******** when ******** ******* * threat."

How **** ******?

********* ** ***** ** advertised, **** **** ** gain ***? ***** *** matter ** ************ **** could ** ******** ** the ****** ********* ********** the ******* ** ** active *******, ** **** not ********* ******** **** be *** ****** ** more ********* **** ******* SafeZone.

******, ** *** ******* already *** * ******* drawn, ****** ** ******* will **** ****** ***** within ******* ** ****** verification. ** **** *****, the ***** *********** *** *** ****** of *** ***** **** likely ** * ******** indicator ** ******* **** video *********.

***** **********

** **** **********, **** schools ***** *** **** of ********* ** ****, guns *** ****** ******. The ********* **** * real *** ** ****** in ***** ** * SafeZone ******* ****** ** likely **** *** - once * ****, ******* longer.

** ********, **** ** the ****** ** ********* accurate *** **** ***** alarms **** * ****, that ***** ** ** false ****** *** ***** valid *** - * ratio **** ***** ***** many ********* ** **** faith ** *** *********.

**** ** * *********** issue *** *** ******** that ******** ** ******** extremely **** ******.

Missed ****

***** **** **** ** many****, ****** *** ****** and ****** *********** *** warp **** ******* **** like (*******, *****, *** angles, ***.), ** ** also * ******* ** the ********* **** ** identify * **** ***** gun.

Going ** **** ********

** *****, ******, *** detection ** *** ** the ***** ***** *** security ********, ** ** expect **** *** ******* will **** ******** *** perhaps *********.

Comments (11)

What about pop-tarts chewed into the shape of a gun?

Or, just pointing out a pretty bird to a class-mate? Finger-pointing constitutes an assault weapon these days.

I can only imagine the number of false alarms this will produce.

Given that trained police officers often have a hard time distinguishing a firearm, I am suspect about this system.

In the given demos, there are no other people around, giving a clear view.

I'll put on my 'companies are buying the government' tin foil hat and say that they'll advertise this, get it on the news, lobby congress to require it, and make a @#$% ton of money.

Next time anyone draws a gun and shoots up a place, we will see the media and the family's declaring that this would have saved them.

At $4,000 per camera, a college campus with 1000 cameras would need $4 million to start with. I see people taking cameras down rather than being forced to have that expense.

Even if this product works 100% as advertised, it is difficult seeing the value for the expense.

If a guy is brandishing a gun out in the open, he is most likely seconds away from using it. At best this system warns me seconds ahead of time? ...that's not much early response to be gained by this analytic.

With the substantial analysis of recent mass-shootings, I'm not sure I have heard anyone claim the problem is instant notification and awareness of the shooter.

Even if this product works 100% as advertised, it is difficult seeing the value for the expense.

If it works 100% as advertised, it is actually easy to see the value for the expense. NONE!

Can anyone explain what they are even claiming on their critical, make-or-break page, titled "How Does SafeZone Save Lives?".

This is a recreation of the page, my comments in <italics>

How Does SafeZone Save Lives?

What would happen today if an armed gunman or gunmen attacked a building where you are, or where your children are, or where your employees are? Would an effective response be launched and prevent the loss of lives?

<The implication is no. Note: the promise of an Automatic Threat Response by the title of the picture>

Here is a video of a simulated gunman attack on a public meeting space

In this video clip, the gunman is present for approximately 60 seconds. If this were a real attack with a full room of people, dozens of people would have been hurt.

<Agreed. But what can be done to save them?>

So how does this scenario change with SafeZone?

Here are the results possible with SafeZone detection and response support

The threat is detected and a response is launched in 10 seconds, before an attack can be mounted. <I see no response launched! Or if one is it's certainly not stopping the mounting of the attack, which continues in all windows unabated!> Responders would have a chance to engage the gunman, potential victims would be alerted of the gunman's presence, and automatic defensive systems (such as door locks) could be engaged.

<Were some doors locked, somewhere? What am I missing?>

Well, that's just in that there scenario! They have more analytics that regular folk might find handy:

I'm sure y'all had this one happen to you: You just finish installing a ski slalom pole in the middle of your front, corner view yard in July, and then your onry neighbor has the nerve to walk right up to it in broad daylight and graffiti all over it. But that never has to happen again...

It looks easy nuff to detect graffiti in broad day light 10 feet away from you with a straight on FOV, but have another gander, the scene is a might bit tricky. Watch how the analytical thing will not be distracted by the possible garbage digger (who doesn't seem to mind the graffitist) nor by the seasick tilt of the whole apparently "crooked" street.

Disclaimer: I am being facetious here, and am really not impressed with this at all. Are y'all?

Did the company itself give an estimated false/missed alarm percentage. If they refuse to give one, or say it's 100% accurate, you know that it's probably bunk.

Watch the rifle detection video. It appears as if the analytic will only detect an object as a rifle if it is held in a firing position (parallel to the ground). And even then, it doesn't maintain a lock on the rifle once it has been detected as such, reacquiring, then losing the target box continuously as the shooter moves down range.

Below is another video from these guys showing how their analytic can tell that a broom isn't a rifle. But it has problems telling that a rifle is a rifle too... :)

Notice the difficulty the analytic has in detecting (and reacquiring) the actual rifle unless the rifle is held (in a firing position) perpendicular to the camera... i.e. if the rifle is pointed at the camera (or in any direction except sideways to the camera) the analytic won't recognize it as a rifle.

So, some dudes got together and catalogued pictures of known firearms (from a side view perspective only apparently), built an analytic to look for these images in camera FOVs, and claim they have a firearm detector that is worth $4K/camera.

As Brian already mentioned, even if it worked flawlessly and immediately identified every firearm in a FOV, what is the 'value' of such a thing?

Keep in mind that any funds spent on these types of gimmick (imo) solutions are not being spent on other security 'things' that actually possess value. So, a case can be made that 'solutions' such as these actually come with a negative value.

...so we expect that the product will draw interest and perhaps heartache.

Why heartache, because they will deploy it and a situation will ensue where it was needed but failed to 'perform'? More likely would be deployment followed by false broom alarms leading to heartburn.

Liked the "Going to Draw Interest" bit.

Pun Score: B+

This is the Redeemed Rambo deployed by helicopter in Southeast Asia, fighting the good fight by Uzing any and every means to bring the boys back home:

And Ari and I* would appreciate his good image not be sullied by yet another association with an agressively stupid active shooter product.

*Possibly Marty also, though he might have just been messin' with us.

Now hold on just a sec, before you BRate BRhodes, you might take a lil look see at yonder rectangle. On account of it not being all red boxed, like all the other clearly contrasted guns are. That means it identifies the weapon, but has also id's the possessor!

And that new-fangled Rambolytic detector is thrilled to see Mr. Balboa give somebody a buzz cut or even help move a bullet-proofed bookshelf in front of a grammar school door.

You see the Rock ain't the disease, he's the cure...

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

Bank Security Manager Interview on May 15, 2019
Bank security contends with many significant threats - from fraudsters to robbers and more. In this interview, IPVM spoke with bank security...
10 Facial Recognition Providers Review (Secutech) on May 09, 2019
Adding to our 19 Facial Recognition Providers Profiled report from ISC West, IPVM focused on facial recognition technology for our Day 2 coverage...
Proxy Access Control Tested on May 09, 2019
Silicon Valley Access Startup Proxy raised $13.6 Million in May 2019, focusing on mobile physical access control. Beyond the fund raising, Proxy...
Hikvision DeepinView Camera Analytics Tested on May 08, 2019
Hikvision is expanding its 'deep learning' offerings with a new camera series called 'DeepinView' claiming false alarm reduction and improved...
Aegis AI Gun Detection Video Analytics Startup 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...
Verkada Cloud VMS/Cameras Tested on May 02, 2019
Verkada is arguably the most ambitious video surveillance startup in many years. The company is developing their own cameras, their own VMS, their...
IBM Shuts Down Intelligent Video Analytics on May 02, 2019
Abruptly, IBM has discontinued its Intelligent Video Analytics solution, it confirmed to IPVM. IBM's video analytics have faced recent media...
LenelS2 Launches VRx Video Platform on Apr 29, 2019
For years, S2's video management platform, the NetVR, was based on Exacq. Now, after years of internal development, S2 has launched its own...
The HIVIDEO $31 Face Detection DVR Tested on Apr 25, 2019
Face detection in a $31 DVR? That is what "HIVIDEO" (not to be confused with Hikvision, even if the company intends to do that) was promoting at...
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...

Most Recent Industry Reports

Facial Recognition Systems Fail Simple Liveness Detection Test on May 17, 2019
Facial recognition is being widely promoted as a solution to physical access control but we were able to simply spoof 3 systems because they had no...
Inside Look Into Scam Market Research on May 17, 2019
Scam market research has exploded over the last few years becoming the most commonly cited 'statistics' for most industries, despite there clearly...
Maglock Selection Guide on May 16, 2019
One of the most misunderstood yet valuable pieces of electrified hardware is the maglock. Few locks are stronger, but myths and confusion surround...
Panasonic 32MP Multi Imager Camera Tested (WV-X8570N) on May 16, 2019
Panasonic has released their first multi imager models including the 32MP (4x4K) WV-X8570N, claiming "Extreme image quality for evidence capturing...
Trump Signs 'Huawei Ban' - Executive Order Targeting Foreign Adversary Technology on May 16, 2019
US President Donald Trump has signed an executive order targeting technology provided by 'foreign adversaries', in what is widely being called a...
Bank Security Manager Interview on May 15, 2019
Bank security contends with many significant threats - from fraudsters to robbers and more. In this interview, IPVM spoke with bank security...
Milestone XProtect 2019 R1 Tested on May 15, 2019
For the past few years, Milestone has released quarterly software updates XProtect VMS platform. What is new and how much impact do the updates...
San Francisco Face Recognition Ban And Surveillance Regulation Details Examined on May 14, 2019
San Francisco passed the legislation 8-1 today. While the face recognition 'ban' has already received significant attention over the past few...
Security Fail: ASISNYC Auto Emails Passwords In Plain Text on May 14, 2019
ASIS NYC automatically emails a user with the password the user just entered, in plain text, when one registers for the site / event, as the...
Hikvision VP On Muslim Oppression on May 14, 2019
Hikvision has won tens of millions of dollars, at least, in direct contracts with the Chinese government that oppresses Muslims, including a forced...

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