Peter K. wrote:
> "Leon" <leon_heller@hotmail.com> writes:
> 
> 
>>Why not break some glass, record the sound, and analyse it?
>>
> 
> 
> Because he'll just be analyzing that particular window of that
> particular glass at that particular time breaking. :-)
> 

If the system really has to detect the acoustic sound, the neural net approach 
is pretty obvious (despite the info that someone has seen fit to patent it). For 
a training set, there are several online sources of sound effects, as a Google 
search will demonstrate. For example, this site:
http://www.sounddogs.com

has a whole category of glass sounds.

An alternative "advanced" strategy would be to identify the MPEG-7-style sound 
descriptors for breaking glass, and apply those to any detected sounds above the 
threshold level.

The sensitivity of the detector will have to be carefully set, as breaking-glass 
sounds may leigitmately crop up in the home not least via the TV, or even the CD 
player. There is a famous breaking-glass sample in "Babooshka" by Kate Bush (or 
maybe breaking plates, not sure!); it would be a pity if the alarm was triggered 
by a moment of musical nostalgia, or by Bruce Willis in full surround sound mayhem.

Richard Dobson

"Leon" <leon_heller@hotmail.com> writes:

> So that he can get some idea of the characteristics of the sound. He
> can then develop a suitable sytem, perhaps using neural nets, once he
> has identified the relevant parameters. 

Sorry, Neutral Notworks don't work for me. :-)

> He'll need a lot of glass if he does it that way. 8-)

:-) Training over 100,000 epochs, yes, that is quite a bit!

Ciao,

Peter K.

-- 
"And he sees the vision splendid 
of the sunlit plains extended
And at night the wondrous glory of the everlasting stars."

 

Peter K. wrote:
> "Leon" <leon_heller@hotmail.com> writes:
>
> >
> > Why not break some glass, record the sound, and analyse it?
> >
>
> Because he'll just be analyzing that particular window of that
> particular glass at that particular time breaking. :-)

So that he can get some idea of the characteristics of the sound. He
can then develop a suitable sytem, perhaps using neural nets, once he
has identified the relevant parameters. He'll need a lot of glass if he
does it that way. 8-)

Leon

"Leon" <leon_heller@hotmail.com> writes:

> 
> Why not break some glass, record the sound, and analyse it?
> 

Because he'll just be analyzing that particular window of that
particular glass at that particular time breaking. :-)

Ciao,

Peter K.

-- 
"And he sees the vision splendid 
of the sunlit plains extended
And at night the wondrous glory of the everlasting stars."

 

sadlah@yahoo.com.sg wrote:
> Hi guys. Thanks a lot for the excellent replies. This is actually a
> Senior Design class and we were assigned to do a project on DSP. Since
> we have National Instrument's Speedy-33 board, it would be easier to
> interface with it with Labview. What we're trying to build here is a
> home security system that monitors(through microphones) a glass panel
> to see if a break-in occurs.
>
> I guess what I wanted to know is if there is a specific pattern for the
> input that i will be getting off the microphone. because i think the
> generated waveform really depends on how hard i hit it or even the
> position on the glass where the initial hit occured.
>
> More specifically, how can I use Labview to achieve this? Or what type
> of signal processing would I have to undertake? I would say the
> timeline that I have is about 2 months.

Why not break some glass, record the sound, and analyse it?

Leon

Hi guys. Thanks a lot for the excellent replies. This is actually a
Senior Design class and we were assigned to do a project on DSP. Since
we have National Instrument's Speedy-33 board, it would be easier to
interface with it with Labview. What we're trying to build here is a
home security system that monitors(through microphones) a glass panel
to see if a break-in occurs.

I guess what I wanted to know is if there is a specific pattern for the
input that i will be getting off the microphone. because i think the
generated waveform really depends on how hard i hit it or even the
position on the glass where the initial hit occured.

More specifically, how can I use Labview to achieve this? Or what type
of signal processing would I have to undertake? I would say the
timeline that I have is about 2 months.

sadlah@yahoo.com.sg wrote:

> Hello. I'm an undergraduate working on a project to build a home
> security system using DSP and NI's Speedy-33 board. My question is :
> 1) how can I detect breaking glass sound
>    using LabView?
> 2) how to connect external hardware(e.g
>    siren, lights) to the Speedy-33 board
>    that will be activated if breaking
>    glass is detected.
> 
> Thank you.
> 

I think that you have left out *MANY* significant details.

What is "Course Title".
What level, "undergraduate" is a *MITE* vague ;}
What is PURPOSE of course?
   Is it to learn "LabView" or is "LabView" a supplied *TOOL* ?
   Is it to properly specify a goal?'
What is the actual problem statement?

"Peter K." <p.kootsookos@iolfree.ie> wrote in message 
news:1140538375.679567.261220@f14g2000cwb.googlegroups.com...
>
> Noway2 wrote:
>
>> Thats a really good question and I too woudl really like to know how
>> these devices work.  I have a number of them installled in my home
>> alarm system and I have found that they are sensitve to vibration.
>> They are also supposed to be tuned to the sound of glass breaking and
>> that is even supposed to have been refined to particular types of glass
>> (window / door) so that if you drop something on the floor it doesn't
>> set off the alarm.  As much as I would like to try them out, I am
>> certainly not going to break a door or window to prove it :)
>
> You can also try playing a .wav file reasonably loudly close to one of
> the sensors.  That should set it off, also, provided the .wav was
> really recorded from breaking glass. :-)
>
Way back in the dim and distant past the acoustic detectors for smashed 
windows just used to look to see if there was a lot of high frequency 
component in the sound ( often triggering with an edge detector) they were 
horribly unreliable though and would go-off if people rubbed a ring over the 
outside of the shop window or parked their bike there and it slipped a bit., 
even a zipper tag on a coat blowing against the window or some 
rubbernecker's spectacle frame clattering on it was enough to set them off 
on maximum sensitivity and if you set the sensitivity lower you could often 
smash large chunks out without setting them off.  I expect things have got a 
bit more sophisticated now but I really recommend that whatever you finally 
settle on you check out sensitivity to 'normal' noises you can get out of 
unbroken windows.

Best of Luck - Mike


> 

>
> And if your algorithm is not sufficiently selective, it will trigger on
> any loud sound (like shutting a door), which might be very annoying.

Good Point.

With the ones I have, you can see them respond to ligh switches being
cut on or off.  While it doesn't trigger an alarm, you can see one of
the indicator LEDs blink indicating that it picked up the vibration in
the wall.

Well, try to break a few windows while recording resulting sound on a
high-quality mic, save your .wav files and try to analyze them using
Matlab or whatever you have...

There must be some unique pattern in the time-frequency distribution
specific to a breaking glass... In particular, you can do FFT and try
to isolate some specific frequencies, as well as some unique time
signature (The initial shock is followed by somewhat prolonged period
of falling glass fragments..)
Needles to say, the difficulty of designing a sufficiently robust
algorithm far exceeds the difficulty of its final DSP implementation,
so you can forget about your hardware for quite a while...

And if your algorithm is not sufficiently selective, it will trigger on
any loud sound (like shutting a door), which might be very annoying.