Can you review the Aggression Detector? I'd like to know more about it.
Audio Analytics Released (Louroe / Sound Intelligence)
The most well-known specialist in audio surveillance is now adding audio analytics. Partnering with Sound Intelligence [link no longer available], Louroe is now offering gunshot glass break, car alarm and aggression detection.
In this note, we examine the capabilities, pricing and how it integrates with conventional cameras and video management systems.
No better place to test it than NYC...
Specifically, I'd like to see how it works in group homes, halfway houses, clinics, offices, places where people can get angry and violent with little notice. Most of the places I'd use this kind of thing are government funded and unlikely to be able to afford to pay enough security officers. I'm thinking force multiplier.
I'd also like to see how it avoids false positives, say, a bunch of clients sitting in a common room watching TV. You can have a security officer or a resident supervisor sitting in the corner tweeting from their phone, but then they aren't off doing other stuff.
Those are good ideas, thanks. We'll put it in queue.
I wonder if it alarms on "CAN YOU DIG IT!?"
Is that from the Tom Hanks Dragnet remake from the 80s?
Being that I am in the NYC area and support a number of 'multi-family housing' developments, perhaps I can be of assistance in testing? I'd just need the units (and specific software?), a VMS is already in place.
Disclaimer: My employer is Next Level Security Systems (NLSS)
NLSS has audio analytics of the same names built into our NLSS Gateways, and they work quite well.
It is noteworthy to point out that, at least for ours, the audio has to be of high-fidelity AAC compression, which many cameras do not have. Most cameras only have telephony-grade G.711, which will not work. Our white paper on audio analytics guidelines is here.
We have tested Gunshot Detection at both indoor and outdoor ranges with a variety of weapons and calibers, and it works very well. We offer it for free to schools and universities. We do not advertise that offer because we could never figure out how to do it tastefully.
Glassbreak and Car Alarm work as you would expect. Concerning Verbal Aggression, it's spooky how well it works. It is not based upon cuss words, so it works in any language. Just as you can tell when children in another room start quarreling without hearing the actual words, it alerts upon the particular tone of human belligerence. It will not alert upon loud talking, laughing, or goofing around.
One day we were testing it in the office and wanted to try it with a female voice. At the time, we had as an office manager a very nice and well mannered young lady. However, we forgot to tell her it was not based upon cuss words. On cue, this sweet young thing lets loose a stream of filth that would have made a U.S. Marine lightheaded. (Seriously, I had to go and look up some of the words she said) Once she was done, we just stared at her with slack jaws. You could have heard a pin drop in that room except for the system "Alert...Alert...Alert" alarm going off.
Concerning privacy issues in those regions where audio surveillance is restricted, camera audio can be set to generate alerts but not be recorded.
I apologize for high-jacking the thread, but Kevin, we have been trying unsuccessfully to contact Next Level for a couple of days. How can we get in touch with someone who will return a phone call please??
To Mr. Honovich, is there a method I am not aware of that can provide members a method of contacting each other outside the confines of the website? Maybe it is there and I dont see it?
We don't have any direct messaging / email capability, by design. The main concern is abuse, i.e., manufacturers pester end users. However, we could add a functionality that lets members opt-in to be contacted and/or show their email. We'll think about that.
For now, I will email the both of you and put you in touch.
What is the advertised effective distance of the detection?
For both NLSS and Louroe.
From Louroe's brochure:
How far can a microphone "hear?" A similar question might be, How far can a camera "see?" For a camera, of course, that question is dependent upon the lens that is used. Use a longer focal length lens and a camera can "see" farther away. Similarly, how far an audio surveillance system can "hear" is greatly dependent upon the microphone selected. A "shotgun" microphone, for instance, can detect sound at much greater range than an omnidirectional one. I would defer to Louroe (fine company, wonderful people, great products) as the experts in higher performance audio systems at greater ranges.
At NLSS, we took a more practical approach. We assumed the use of a commonly available microphone paired with a higher-end camera supporting AAC compression. For our tests, we used a Sony SCA-M30 microphone on an Axis camera. We assumed glass break and aggression detection would be used indoors, confirmed performance to 15 meters, then dialled it back to 10 meters in our white paper on the subject. Similarly, we assumed car alarms and gunshot detection might be used outdoors, so we confirmed 50 metres for car alarms and 100-200 meters for gunshots (more powerful cartridges detectable at longer ranges). Since the microphone and camera are paired together, we only verified that the analytic and typical camera range were a match; we did not test for the absolute greatest range where audio analytics would work by themselves in perfect conditions.
For glass break, we used a commonly available simulator at a number of trade shows including the ISC floor. For aggression, we tested it ourselves in our offices in Carlsbad, California as described earlier in this thread. Car alarm was tested it in our parking lot. Gunshot detection was tested with a variety of weapons at an indoor range in Las Vegas, as well as an outdoor range at a sheriff's department in Florida.
As with video analytics, do not expect perfect performance with audio analytics; managing customer expectations is key.
A lot of the detection ranges, especially outdoor, depend on ambient conditions. Think of the path the sound needs to take from the source to where the mic is. If there is no straight shot or line of sight, the detection range will be reduced. If the sound reflects off buildings or walls, or if wind comes into play, the range will be reduced.
That said, in most applications I doubt you'll need to go 300 feet for verbal aggression detection or even 3,000 for gunshot detection. In offices, c-stores, law enforcement facilities, etc most of the areas covered are much smaller.
Great thread and insight to audio analytics. We are currently working on an EU funded project P-REACT (P-REACT.EU) that is combining video and audio analytics on an embedded system to create alerts to potential incidents in shops and transport domains. There are a number of trials planned in Italy and Greece etc in Qtr 1 of 2016 so I will revert back with some of the results at that stage.
The glass break detection could be very interesting. I'm currently working on a customer site where the lobby is surrounded with windows. Instead of using traditional glass break sensors you could use this module so you'd have more direct integration into your access control system. I think it may save money in the long run over a typical intrusion system, and you'd have a cleaner integration.
The aggression detection sounds really interesting, as was mentioned, for group homes. Interesting product ideas.
The price point of this makes it considerably less expensive then some other gunshot solutions. I have requested a test install.
Considering that most other gunshot detection systems are very pricey, and not overly "good", I'm very interested to hear details on your test.
It defies practical logic that the gunshot detection will be accurate and cost-effective enough to compete with ShotSpotter (and the related companies), but it would be very interestig if that did in fact happen.
I can only speak for NLSS when saying, vis-à-vis ShotSpotter, that our Gunshot Detection analytic does not provide bearing and range information; only which camera(s) heard the gunfire.
NLSS charges a one-time fee for audio analytic licensing, which applies to the entire VMS Gateway appliance regardless of how many cameras on that appliance use the analytic(s).
Car Alarm / Aggression: $600
Gunshot: $1000, educational organizations free
Be advised that cameras must support AAC compression, and generally only higher end cameras do so. In most cases, an external microphone is recommended. No analytic, audio or video, will ever provide perfect performance.
In fairness, there is an obvious admitted difference. Louroe/Sound Intel are not claiming to detect the spot of the fired shot, just that it occurred. That's lower value but also easier to do.
Part of ShotSpotter and similar gunfire location systems' high cost is the number of microphones they use to locate.
Those platforms use triangulation to 'locate' shots, so instead of just one mic that detects gunfire, they need at least three.
Like John says, simple gunfire detection is less complex and less hardware intensive to do, and therefore cheaper overall.
From the feedback I've received from multiple sources is that false alarms are still a MAJOR issue. One of these companies went so far as to setup their own "verification" center to have the alarms be human-filtered because the municipalities were getting overwhelmed. Of course this was spun as a value-add service.
"Of course this was spun as a value-add service."
No, not spun, that's RMR!