Audio Analytics Aggression Tested

Author: Ethan Ace, Published on Nov 20, 2015

What if you could use your IP cameras to detect fights before they start? 

That is the goal of Louroe / Sound Intelligence with their recently released Aggression Detector audio analytics. Claiming that "90% of physical aggression are preceded by verbal aggression", these analytics are designed to alert guards before verbal altercations turn physical.

We tested the Aggression Detector using both live subjects and recorded clips of multiple scenes, to see just how these analytics perform.

Here is the app main view that we used to monitor and optimize the audio analytics:

**** ** *** ***** *** **** ** ******* ** ****** fights ****** **** *****? 

**** ** *** **** ******** / ***** **************** ***** ******** ****************** ******** ***** *********. ******** **** "**% ** ******** ********** *** ******** ** verbal **********", ***** ********* *** ******** ** ***** ****** ****** verbal ************ **** ********.

** ****** *** ********** ******** ***** **** **** ******** *** ******** clips ** ******** ******, ** *** **** *** ***** ********* perform.

**** ** *** *** **** **** **** ** **** ** ******* and ******** *** ***** *********:

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

*******

******/***** ************ ********** ******** ********* *** * *********** ****** ******** to ************ *******, ********* ***** ** ****** ***** *** ********* go *********, ******** ****** ******/************ ********. 

*******, **** *** *** ******** *** *** *********, *** *** best **** ** ******** ***** *****, ** ****** ** ******** ******** will ******* ******** ***** ******, ***** **** ********** ***** ****** reduce analytics' ******* ** *********** ******. 

Key ********

** *** *****, ******'* ********** ********* *********** ** ***** *********** over *** ****** ** ***** **** ** ******* **** ****** area (**** ****** ***** *************, ****** ******* **** *** ***** ** other *******, ** ***** ***********).

*******, **** ***-********** ****** ******** ****** ***** ****** ** ******* degrees:

  • *****/***** *****:***** ****** *** ****** ********* **** ******** ***** ******, ********** of ***********. ****** ********** *** ***** ********** ********* ** ***** applications.
  • ****, ***-********** ******: ** **** *****, ****** ***-********** ******, ******, etc., ********* ******. **** *** ******** *** ******** * *** times (

********* ******** ********** ******** ****** ** ******* *** *******. ***** shouts ** **** ****** ***** ********* ********* ****** *** *****.

****** ******** ***** *** ** **** ** **** *********** *** best ***********. ******** **** *** *** *********** *** ********* ****** in *** *****, **** **** ********** ***** ****** *********** ******** detection ***********. 

** ****** *** ***** ***********. *** ****** ******* ** ******* I/O *** ** ****.

*******

**** *** ******'* ********** ********* ** $*** *** *******.

Potential ************

*** **** *** *** ***** ********** ********* ** ** ******** quiet ***** ***** ********** ****** **** ****** ****** *** ******* background *****, ********* *******, *********, ****** ********, **********, ***.

***** ********* ***** ** ****** ** *******, *** *** ********* volume *** ***** ***** ** ****** ***** ******/***** ** ** between ******* **** ****** ******* ******** ***** ******. ***** ***** *** be *** ******* ** ***** **** *******, *** **** ***** largely ****** *** ******** ** *** ********.

** **** ***** ***** ****** ****** *** ******, **** ** stadiums, ***** ****** *** ****** ** ** **** ******** *** to ***** *****.

*******, ** **** **** ***** **** ** ******* ** *****, **** are ****** ******** ** ******** ****** ****** *** ********** *** to *** ********* ***** *** ********** ******, ****** *** ********* unsuitable.

************/*************

******'* ********** ******** *** * ****** ************* ******, **** **** one ******** *******: ***********, *********** ** *** *****. **** ****** also ***** **** **** ***** ******** ** ***** ******:

  1. ***** ***** ********:*** *** ***** ***** ***** ********, **** *** ****** ***** displayed ** *****, ******* ** ****** **** ***** *** ********* threshold, ** ****** **** ********, *** ******* *** **** ********** is ********. ***** ********** ** ******, *** ********** **** ******* from ***** ** ***** ***.
  2. ***** ***********: *** ****** ***** ******** ********* ********, **** ****** ******* frequencies ********* ** *** *** **** ******, ****** *** ***, and **** *** ***.
  3. **************: *******, ** *** ******, ******** ************** ** *****. ****** ***** from ***** (********** ***** ****) ** **** (************), **** ** green *** ***-******** ***** ******, *** ******/******/*** *** ********** ****** of ******/**********.

** ******** ********* ********** *********** *** ********* *********** **** *** course ** ******** **** ** ***** ** ******** ***** ***** ******/****** activations. *********** ******** **** **** **** ********* ** *** ********** used, **** ******** *******, *** ********** ***** ******* ** *** time ** ***********.

***** **** ***** ********, ***** ****** ****** **** *** ***** settings. ** ****** ***** ******* ** **** ******, ********* *** specific ***********, ** *** ***** ************ *****.

Video ***********

*** ***** ***** ******* ************ *** ************* ** **** ******, including *********** ********, *** *****, *** ****:


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

******'* ********* *** *** ********* **** *** ** *** ***** tested: ********, *******, *****, *** ********. ******* ** ***** **** applications, **** *** ** **** ** ******* *** ************* ** relay ******* ** *** ******, ***** *** ** ******** ********** to *** ***.

** ***** ******* *** *** *********, ***** *** **** ******* email/SMS ******** *** ******.

Audio ******** ********

*** ******** ***** **** ******** ******** ** ******* ************, **** live *** **** ******** *****.

**** **** ****** ********** ***** *** ** **** *** ************* ********, as *** ********* ******** ** *** ********* ********** *** ******** playing *** **** **** *** ******* *** *** ****** ********* performance. However, ** **** ***** *** ***** ******** ****** ** * way ** ********** **** *** ******* ** ******** *******.

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

*****, **** ******* ***** ******** ** * ***** **** * crowd ** **********. ****** ****** *** ****, ***** ** *** large ******* ** ****** ** *** ******** ****** *** *** frequencies ***** ** *** ***********. ********** ****** **** ********, *** not ******** ** **** *******:

****, ***-********** ******

****, **** ******* ***** ****, *** *** ********** ******. **** that ******** ****** **** **********, ** *** ******** ****** ***** all ******. *******, ******* ********* ******, *** ****** ** *** analyzed ** ********.

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

*******, **** ******* ***** ******* ***** ***** ** *** ***********. Even **** ******* ****** *** ******* ***********, ****** *** ****** constant:

Test **********

**** *** ********* ***** ** **** ***** **** ****** ******** A *** *** **-* ***** *******.

*** ********* ********/******** ******** **** **** ** **** ****:

  • ******/***** ************ ********** ********: *.*.*-******
  • **** *****: *.**.*.*
  • ***********: *.*.*.*****
  • ******* ******** ******: *.*.****.**
  • ********* ********: **** (*.**)

Comments (8)

Undisclosed #1

11/21/15 07:46am

**** ******** ******!

****** *********,

*** ***** ********* ****** *********, ** **** **** **** *** the ****** *** **** ****?

*** *** **** **** *** ***** **** ******** **** *** room *** ***** ** **** *** **** **** *** ***, or **** ***** *** ***** ******** ** **** *** **** level *****?

*********** **** ********* ***** ******** *** *** ***** ***** ****** and ********* ******** ***** *** ******, ** *** ******* ** in ****** ** *****, ****, ******* *** ****** **** *** could ****** ** *** **** *****.

* ******** * ***** **** ******* **** *** ***** ************ could ****** ********. ** **** **** ** **** *******? ** so ** ** ****** ********, ** ******** ****** ***** *** it ********* ********.

*******, *** *** **** ***** **** ** ***** ********* ** the ***** **** ** **** ****** **********. *** **** ***** any ***** *********? * **** **** **** *'* *************** * particularly ************* ******, * ************ ***** ******** ** *************** ** sharing ** ********* **** *** ******. ** **** ***** * have **** **** ** *** ** ** ******** ********** **** a *** ********* ****.

** * ***** *'* ****** **, *** *** *** * chance ** **** ** ** ********** ******, *** ******** ******, and *** ** **** ** ******* *********?

******!

Cameron Javdani

Louroe Electronics | 11/23/15 09:04pm

*** ******** ****** *** *** ******, *** *** *** ****** the ***** **** ******** *** ******** ** *****.

*** ******** ** ******** ** *** ********** ***** ******* *** compression ********** **** ***'* ****** *** ******* ***********. ** ******* an *** **** * ******* ***** **** ** ******* * detection, *** ***'* ** ***** ** * ****** **** ******* at **** *****.

******** ********* ** ** *********** ****. ********* ** *** ******** a ***** **** ***'* *** * *********, *** ****'* ******* of * ******** ***** *** *** *** **** **************. ** as **** ** ****** ****'* ****** ********** ***** ***** ** each ***** ***'* ***** *** * ********* ********** ** ******** being ******.

Sal Visone

IPVMU Certified | 11/26/15 05:37am

*'* ** ******* ** *** ** **** **** ******* ******* additional ***** ********* ******** ******* ***********, ******** *** *********.

Mark Strange

IPVMU Certified | 11/28/15 03:54am

**** **** ******* ****** **** ***** ** ******** ******** ** is ** **** *** **** **********? ** **** ****** ***** can't ** ******** ******* ******* ******* **** **** *******.

John Honovich

IPVM | In reply to Mark Strange | 11/29/15 08:37pm

****** ****: "*** ******** ***'* ********* ** ***** ** ********* *** ****** vocal ****** *** *** ********** ****** ** ***********."

**** ***** **** ****** *** **** / *******. *** ******** also **** *** ****** *****.

**********, ** ** * ***** ***** *** ** **** **** technically ********* **** ***** *********.

Undisclosed #1

In reply to John Honovich | 11/29/15 08:49pm

* ***** *** ** **** ******* ***** ** ** ******* the ********* ** ***** **** ***** *** ****** *********, ** such ****** ***** *** ** ********** ************ ** * ******* conversation, *** ***** ***** *** ******* ** ********* ***** *******.

Matt Alvey

11/30/15 02:09pm

****** *** *** ******. ********** ** **** *******, ** ** an ********** ******* **** ******! *** *** *** **** ** Axis ***** ** *** *****, *** * ***'* ********** ***** you're ***** *** ******? ** *** **** **** ***'** **** using *** *****'* ***** *******?

John Honovich

IPVM | In reply to Matt Alvey | 11/30/15 02:19pm

****, *** ***** ********* *** ** ******* ** *** **** camera *** *** *** ** ********* ** *** **** ******. This ** ***** ** *** ****** *****, ***** *'** ****** below:

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

Sports Stadium Security Design Recommendations on Jul 24, 2017
Sports stadiums pose many challenges for designing security systems. The facilities vary from being mostly vacant, to packed with tens of thousands...
Axis Door Station Tested (A8105-E) on Jul 19, 2017
Axis continues their push into niche markets, especially audio, with network speakers, an IP horn, and video door stations. We bought and tested...
Genetec Mission Control Tested on Jul 13, 2017
Genetec continues to move up market with their Mission Control, "Decision Support System", bringing PSIM-like procedures and incident management to...
OnSSI Gets $16 Million Funding on Jul 11, 2017
OnSSI has had a rollercoaster past few years. Between acquiring VMS company Seetec, breaking up with former OEM partner Milestone and a rocky...
Nest Cam IQ Tested on Jul 10, 2017
Nest has released their latest entry in their camera line, the Nest Cam IQ, touting 4K "Supersight", facial recognition, "HD audio", invisible IR,...
ONVIF Widely Used Toolkit gSOAP Vulnerability Discovered on Jul 10, 2017
A vulnerability has been discovered in a toolkit that video surveillance manufacturers widely use for implementing ONVIF. In this report, we...
H.265 / HEVC Codec Tutorial 2017 on Jun 30, 2017
For years, video surveillance professionals have talked about the potential for H.265. Now, in 2017, H.265 is starting to gain mainstream...
Hikvision H.265+ Tested on Jun 27, 2017
Hikvision, which in the past few years released H.264+ (see test results) has now released H.265+, that claims even greater bandwidth savings. We...
Milestone / Canon Launch Cloud Startup Arcus Global on Jun 27, 2017
Milestone has spun off a business, Arcus Global, funded by their parent company Canon. The new company aims to transform the VSaaS market with an...
VMS UI - Light vs Dark Preferences on Jun 16, 2017
Several VMS manufacturers have the ability to choose a user interface with either a light or dark color theme. 150+ integrators told us which they...

Most Recent Industry Reports

$28M Drone Detection Startup Examined (Dedrone) on Jul 25, 2017
Dedrone has received ~$28M in funding to build what they call an "automatic anti-drone solution", a system to detect drones, and then automatically...
Dahua Suffers Second Major Vulnerability, Silent on Jul 25, 2017
Less than 3 months ago, Dahua received DHS ICS-CERT's worst score of 10.0 for their backdoor. Now, Dahua has received another 10.0 score for a new...
Hikvision H.265+ Bullet Tested (2035) on Jul 24, 2017
Continuing our tests of Hikvision's new low cost Value Plus line, we bought and tested the 3MP DS-2CD2035FWD-I, now including H.265+. We shot the...
Sports Stadium Security Design Recommendations on Jul 24, 2017
Sports stadiums pose many challenges for designing security systems. The facilities vary from being mostly vacant, to packed with tens of thousands...
Competing Against Convergint on Jul 24, 2017
No integrator is more aggressively expanding than Convergint Technologies. Owned and funded by private equity firm KRG, Convergint has acquired...
Security Robots Are Just Entertainment on Jul 21, 2017
Great entertainment, no real security value.  That is the happy (or sad) state of security robots in 2017. Knightscope robot's drowning, the...
Wireless Burglar Alarm Sensors Guide on Jul 21, 2017
Wireless sensors for burglar alarm sensors are an increasingly common option for the historical labor intensive wired alarm systems. However,...
Competing Against ADT on Jul 20, 2017
ADT is one of the biggest players in the security industry, with ~$4 billion revenue. In 2017, they were acquired / merged with Protection...
Hikvision Launching Deep Learning Recorders on Jul 20, 2017
Hikvision has become a common choice for super low cost NVRs. Now, Hikvision is aiming to move up market, with deep learning NVRs that claim far...
PR Campaign Exploiting Manufacturer Cybersecurity on Jul 20, 2017
Manufacturers increasingly have a bulls-eye on their back. As cyber security solutions providers grow, they realize a great way to get publicity...

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