[FRIAM] Message to the non-posting 95%

[Pieter Steenekamp]

Stephen,

I run five parallel threads on the Raspberry Pi. One server and four
clients, one client for each camera. Each client continuously monitors the
feed on one camera and does basic motion detection on the images. It passes
only the images where motion has been detected to the server.
If there are no images with motion, the server will do (almost) nothing.
The server processes the images with motion on a first-come-first-served
basis. The "heavy-lifting" computing to detect humans in the images is done
in the Neural Compute Stick.
When a human is detected, the server then does the following:
it switches a light on;
it plays a sound clip, you can use any recorded MP3 sound clip, the default
is a barking dog;
send the images with boxes drawn around the detected humans per telegram to
as many users as you wish.

It is just amazing what you can achieve with relative little effort using
user-friendly low cost technology. I don't claim to have done significant
innovative or novel work, I've just combined available technology.

By the way, your Posenet example is cool!

Pieter


On Wed, 3 Feb 2021 at 00:10, Stephen Guerin <stephen.guerin at simtable.com>
wrote:

> Pieter,
>
> Very cool solution. Do you process a composited 1/4 resolution grid of the
> 4 video streams in the Rasberry Pi/Neural Compute Stick? Or do you switch
> the videos with the DVR and process in serial?
>
> -Stephen
> _______________________________________________________________________
> Stephen.Guerin at Simtable.com <stephen.guerin at simtable.com>
> CEO, Simtable  http://www.simtable.com
> 1600 Lena St #D1, Santa Fe, NM 87505
> office: (505)995-0206 mobile: (505)577-5828
> twitter: @simtable
> z <http://zoom.com/j/5055775828>oom.simtable.com
>
>
> On Tue, Feb 2, 2021 at 12:21 PM Pieter Steenekamp <
> pieters at randcontrols.co.za> wrote:
>
>> Hi Nick,
>>
>> Sorry for the late reply from a non-bloviator. I am very interested in
>> issues around complexity, but my time is soo limited that I don't get to
>> everything I'm interested in. I also just developed an AI product
>> www.truealarm.co.za, it recognizes a human in a security camera feed and
>> then takes appropriate action) and it does not give me much free time.
>>
>> Regards,
>> Pieter Steenekamp
>> Mossel Bay, South Africa
>>
>> On Wed, 27 Jan 2021 at 04:58, <thompnickson2 at gmail.com> wrote:
>>
>>> Dear non-bloviators,
>>>
>>>
>>>
>>> Some of us bloviators have suddenly woken to the realization that we
>>> have no idea what you are thinking or what topics require discussion in a
>>> forum vaguely related to complexity.  I for one, am curious.  Hallooooooo!
>>> Anybody out there?
>>>
>>>
>>>
>>> Nick
>>>
>>>
>>>
>>> Nick Thompson
>>>
>>> ThompNickSon2 at gmail.com
>>>
>>> https://wordpress.clarku.edu/nthompson/
>>>
>>>
>>> - .... . -..-. . -. -.. -..-. .. ... -..-. .... . .-. .
>>> FRIAM Applied Complexity Group listserv
>>> Zoom Fridays 9:30a-12p Mtn GMT-6  bit.ly/virtualfriam
>>> un/subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
>>> FRIAM-COMIC http://friam-comic.blogspot.com/
>>> archives: http://friam.471366.n2.nabble.com/
>>>
>> - .... . -..-. . -. -.. -..-. .. ... -..-. .... . .-. .
>> FRIAM Applied Complexity Group listserv
>> Zoom Fridays 9:30a-12p Mtn GMT-6  bit.ly/virtualfriam
>> un/subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
>> FRIAM-COMIC http://friam-comic.blogspot.com/
>> archives: http://friam.471366.n2.nabble.com/
>>
> - .... . -..-. . -. -.. -..-. .. ... -..-. .... . .-. .
> FRIAM Applied Complexity Group listserv
> Zoom Fridays 9:30a-12p Mtn GMT-6  bit.ly/virtualfriam
> un/subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
> FRIAM-COMIC http://friam-comic.blogspot.com/
> archives: http://friam.471366.n2.nabble.com/
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://redfish.com/pipermail/friam_redfish.com/attachments/20210203/ce0e64b3/attachment.html>