Deep Science - Active Threat Cloud Monitoring Startup

By: Brian Karas, Published on Apr 03, 2017

Deep learning for $2 a day for a system that automatically detects guns and masks, alerting the police to robberies and threats?

A US startup is launching such a service, based on the work of its founder/CEO, Dr. Sean Huver [link no longer available], and previous work from projects he worked on for DARPA and the DoD. 

In this report, we share feedback from Huver and analyze the cloud-based threat detection service that his company is set to release.

**** ******** *** $* a *** *** * system **** ************* ******* guns *** *****, ******** the ****** ** ********* and *******?

* ** ******* ** ********* such * *******, ***** on *** **** ** its *******/***, **. **** Huver [**** ** ****** available], *** ******** **** from ******** ** ****** on *** ***** *** the ***. 

** **** ******, ** share ******** **** ***** and ******* *** *****-***** threat ********* ******* **** *** company ** *** ** release.

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

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

**** *******, *** ******* ******* by **. *****, *** born *** ** **** he *** ** * market ****** **** *** not ***** *** ** current ***** ******** *********. Unlike **** ***** ********* companies, ***** **** ******* to ******** ******, *** rely ** ******* ******** or ******** ********* *** monitoring, **** ******* ** also ******** *** *** monitoring ******** ** ******* and ******* ** ******.

*** ********** *** ********* to ****** ********* ********* in *********** ****** *** ******* businesses, ** **** ** after-hours ********* **** ***** into *** *****.

*** ********* ***** ***** an ******** ** ****** detection ****** **** **** Science's *********:

 

Management / *******

********* **. ***** ** the ******* ********, ***** the ******** ** *** R&D/development, ******* ****** *** President *** ****** ***, **** Snyder [**** ** ****** available], ** ****** ** an ******* ** *** company.

*** ******* ** ********* funded, *** **** **** have ****** **** ****** from *** ** *****, preferring ** ****** *********** for ***, ****** **** not ***** *** ****** funding ** *** ******.

Threat ********* ********

********* ** *** ***, his ********** ********* **** for * ****** ********** to ******* ***** ******** by ****** ****** ******** through ****, *****, ********, or ******* *******. *** system *** **** ****** a ****** ******* * weapon. ** ***** *** a ****** ** ********** frames ***** *** ** both ** ***** ******** are ***, ***** ***** an ***** ***** ** sent ** **** *******'* office, ***** ********* ***** review *** ***** *** take *********** ******. 

*** ********* ***** ** threats *** ********* ********:

  • ********* ******* / ****** concealing ******** ** ******* a ******
  • *****-***** *********
  • ***** ****** *** **** monitored

Range/Resolution ************

*** ****** ******** ******* 40x40 ****** ** * person's ****, ** ** a ******, ** *** accurate **********. **** ******* to ************* **-** ***, which *** **** **** limitations *** ****** **** have ***** ********** ******* in *****, ** *** covering **** ***** **** a ****** ****** (** a ***** ** *********, with ***** ************, ** ** camera ***** **** ***** ~13' ****, * ***** camera ** ** ~**'). 

Cloud ******** - ******** *********, **** **********

* **** ***** **** from ******* ** **** to **** *******'* ***** servers, ***** *** ***** analytics *** *********. *** company **** ** *** work **** **** *******/**** streams, ******* *** ********** requirements *** ****** ** larger ******** ********* *******, particularly ** ******** ******* are ***** ********* **************.

**** *******'* *** ** ************ ***** ****-********** be **** ** ****** remote ****** ** *** cameras. ***** **** ********** the **** *** ********** on-site ********, ** *** make *** ******* **** susceptible ** ***** ******* or ******** ****** ******.

Live **********

** ***** ***** *** employees *** **********, **** Science ****** **** *** better ******** ****** *********, as **** ** ****** any ***** ***** ****** to **** ********** ******** data **** *** ****** to ****** ****** ***** alarms. ********* ***** *** no ******* *** ********* to ****-******* ***** ******* directly, *** *** ******* does **** ** ***** this ********** ** *** future.

********, ********, *** ********* a ********** ******** ** a ******* *********, ***** is *** **** ******** and ***** ********* ** this ***** ****** ** outsource **** ******** ** dedicated **********. *******, ***** operators ******** *** *********** *** **** ***** ******** staff *** ********** ******* and ********** ** ******* events, ** ** *********** (****** *********** *** *** be *** **** ******* to **** ******** ****** from). *****, ***** ********** is ***** ********* *********** among ******, *** ******* potential ********* ** ** event ** **********, ****** the **** ********** ******* potentially * **** ** distraction, ****** **** * benefit.

Open **** **** 

********* *** ******* ** available ** * **** phase, **** ** ***** *** ~40 ******* ***** *********. This **** ***** ** being ****** ** ** a ***** ********, ***** participants *** *** *** cloud ********* *** **********, however *** ********** ****** is **** ******* **** noon ** ********, ***. 

Pricing *** ****** ****

******* ** **** *******'* site ** ****** ** *** users, ****** *** ******* says **** **** ** ******** dealer ******** ** ****. Depending ** ****** ** cameras *** **** *******, prices ***** **** $**-$** per ****** *** *****, or **** **** $*/*** in **** *****. *** prices ******* *** ***** analytics ** **** ** 24/7 **** ***** ********** of ******** ******. ***** are ** ****** ** number ** ****** *** month.

**** ************ ** *** service ** ********* ********* for **** ****.

Comments (3)

This is an interesting approach. Detecting specific articles like masks and weapons obviates the need for a nice high frame rate, which is not practical. I would expect Dr. Huver has done an actuarial analysis that ends up justifying the cost per camera. Another cost is that of false alarms. Where I live, if the cops have to roll up to repeated false alarms then they start billing the originator. 

Depending on the approach the detection it is likely to get better over time. There maybe false positives to begin with, but especially with active monitoring, those should get factored down fairly quickly. 

Another cost is that of false alarms.

True, but they are attempting to address that by manning their own monitoring operation, so police should only be called when there are actual events, not just someone in the winter time wearing a face mask.

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

Top 2020 Trend - AI Analytics on Nov 22, 2019
170+ Integrators answered: What do you think will be the top industry trend in 2020? Why? For the 4th year in a row, AI/video analytics was...
ISC East 2019 Show Report Day 2 on Nov 21, 2019
IPVM has finished in New York City covering both days of the ISC East 2019 show. Inside this report, we cover: Day 2 Traffic Centaur...
Gatekeeper Security Company Profile - Detecting Faces Inside Vehicles on Nov 14, 2019
Border security is a common discussion in mainstream US news and politics, as is the use of banned Chinese equipment by US Government agencies....
Rhombus Cameras, VMS and Analytics Tested on Nov 06, 2019
Rhombus boasts they have created "the new standard in Enterprise, cloud-managed video security" and told IPVM in January 2019 they offer twice the...
90+ Companies Profile Directory on Nov 06, 2019
While IPVM covers the largest companies in the industry regularly (like Axis, Dahua, Hikvision, etc.), IPVM strives to do a profile post on each...
Paravision AI Face Recognition Company Profile on Nov 01, 2019
Paravision (formerly EverAI) toutes being #1 in NIST testing and "America's only mission-critical face recognition" provider. We spoke to...
Avigilon Appearance Search Tested on Oct 30, 2019
Avigilon Appearance Search claims that it "sorts through hours of video with ease, to quickly locate a specific person or vehicle of interest...
Lock Status Monitoring Tutorial on Oct 28, 2019
Just because access doors are closed does not mean they are locked. Unless access systems are using lock status monitoring, the doors and areas...
nFlux AI Startup Profile on Oct 28, 2019
nFlux, an Amazon, Google, and Microsoft funded AI startup told IPVM their mission is to build the most intelligent video analytics platform in the...
Alarm Veteran "Demands A Criminal Investigation" Of UL on Oct 18, 2019
The Interceptor's Project pressure against UL continues to rise. Following Keith Jentoft's allegation that "UL Has Blood On Their Hands", Jentoft...

Most Recent Industry Reports

Axis "Best Of The Best" 4K Camera Tested (Q1798-LE) on Nov 21, 2019
Axis has released their "best of the best" Q1798-LE bullet camera, touting "4K without compromise" with a large Micro 4/3" image sensor, custom...
Glass Doors and Access Control Tutorial on Nov 21, 2019
One of the biggest access challenges are locking and securing glass doors. Unlike wood or steel doors that can be modified to work with...
Avigilon H4 Intercom Tested on Nov 20, 2019
Avigilon is well-known for video surveillance and access, but how well does the company's intercom work? We purchased and tested Avigilon's H4...
The Cowardly, Greedy "Leaders" of Video Surveillance - SIA on Nov 19, 2019
The video surveillance industry suffers from cowardly, greedy 'leaders' focused on maximizing easy money while undermining public trust. The...
Hikvision Dual Lens Face Recognition Camera Tested on Nov 19, 2019
Hikvision's Dual Lens Facial Recognition camera, claims that it "adopts advanced deep learning algorithm and powerful GPU to realize instant face...
Top Manufacturers Gaining and Losing 2019 on Nov 18, 2019
2019 has been an explosive year for video surveillance, with the world's two largest manufacturers, Dahua and Hikvision, being sanctioned for human...
Hidden Camera Detectors Tested on Nov 18, 2019
Hidden cameras are a growing problem as cameras become smaller, cheaper and easier to access. However, some companies claim to be able to detect...
Wyze Fires Back at JCI - Your Patents Are Invalid, Pay All Of Our Costs on Nov 18, 2019
Goliath JCI targeted startup Wyze this summer alleging the fast-growing consumer startup was violating a slew of JCI's patents. Now, Wyze has...
ADT Stock Surges - "Leading The Commercial Space" on Nov 15, 2019
Don't call it comeback... but maybe call it a commercial provider. ADT, whose stock dropped by as much as 2/3rds since IPOing in 2018, has now...