Hi,
I've done some work with a DVS128 sensor. I wrote an interface between
it and a large scale simulator running on a Cray XE6, and tested it with
an autoassociative recurrent attractor neural network. A report of
what I did can be found here:
http://www.diva-portal.org/smash/get/diva2:547770/FULLTEXT01.pdf
Although I think the concept of a silicon retinas is interesting I was
quite disappointed on the DVS. It is was hard to make it do anything
useful. How "neuromorphic" it is can be discussed. It solely relies on
temporal contrast, meaning that unlike the vertebrate visual system,
which employs spatial edge detection and spatial contrast adaptation, it
only detects local illuminance changes at single pixels. As you say,
this has the effect that a static scene will not produce any output
events. The sensor has either to be moved or pointed at a moving scene
to generate any output other than noise.
For me the DVS seems most useful for applications were a high-speed
camera would normally be needed. It has very low latency. However, in
situations where one can tolerate some latency it's better to use a
conventional camera and convert the image to a spike/address-event
representation in software. Then you have more control, and much higher
resolution.
Best,
Erik
On 2014-07-13 13:31 , Thanh Binh To wrote:
Hi Nupic-hacker,
in the branch Neuromorphic Computing some neuromorphic cameras, that
mimics the human retina, are available, for example Dynamic Vision Sensors
http://siliconretina.ini.uzh.ch/wiki/index.php
Unlike the conventional camera, this camera provides very sparse data
asynchronically, only when objects are going to move.
I hope that the combination of those camera with Nupic can bring
interessant results for some new applications.
Does anyone have any experiment with this camera?
Thanks.
Best regards
Binh
_______________________________________________
nupic mailing list
[email protected]
http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org
_______________________________________________
nupic mailing list
[email protected]
http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org
