[OSM-dev] Fwd: [GSoC] A GPX photo stamper.

Matt Amos zerebubuth at gmail.com
Fri Apr 3 11:40:24 BST 2009

sounds awesome!



On Fri, Apr 3, 2009 at 11:33 AM, Tijs Zwinkels
<openStreetMap at tumblecow.net> wrote:
> So, I've decided to take on this project. :)
> I'm currently writing my proposal, which I'll post to the wiki and submit at
> the GSoC site in 1 ~ 2 hrs time. (let me know if you want to see the
> intermediate versions, I can just post to the wiki whatever I have already)
> Just bouncing a few last ideas, mainly to define the scope of the project:
> - I've decided to focus on the automatic reading of street signs, and not
> specificly on the recognition of other items in the environment. However,
> one of the most challenging parts of this project is to segment street-signs
> from images succesfully, and I'll be using SIFT (among other things) for
> that. I fully expect the toolset that I develop to be very useful in
> recognizing other objects as well.
> - Since street-signs look differently in different parts of the world, for
> now I'll just try to automatically read dutch street-signs. I think this
> will give me enough variance to struggle with for now. :) - ofcourse, it
> shouldn't be hard to adapt this work to foreign street signs.
> - There is a large difference between whether the software should be able to
> catch and read street signs that just happen to be in a picture, or whether
> people took a picture with the intention of capturing a street sign. (by
> which we would view the sign from a relatively straight angle with a
> reasonably high resolution, not too much reflection, etc)
> For now I'll assume the latter case. If the performance is reasonable, we
> can always scale up to the more difficult cases.
> - Tijs Zwinkels
> On Thu, Apr 2, 2009 at 11:40 AM, Tijs Zwinkels <openStreetMap at tumblecow.net>
> wrote:
>> On Wed, Apr 1, 2009 at 5:31 PM, Matt Amos <zerebubuth at gmail.com> wrote:
>>> On Wed, Apr 1, 2009 at 4:23 PM, Stefan de Konink <stefan at konink.de>
>>> wrote:
>>> > I think stitching is something that is lets say 'available',
>>> > referencing
>>> > images is too. But I would really love to see some thing like robust
>>> > automatic traffic sign recognition, or maybe even streetname OCR.
>>> > Ambitious but certainly doable. And don't forget, these are things that
>>> > are not yet available on current camera's and DO require manual labor,
>>> > so
>>> > lets see what can be automated.
>>> automatic traffic sign recognition and streetname OCR - that would be
>>> immensely cool!
>>> certainly seems doable. google must be doing it for their automatic
>>> blurring on streetview. also, http://evernote.com/ has similar ideas.
>>> cheers,
>>> matt
>> This sound very neat, but ofcourse there is 'google-doable' and then there
>> is 'Tijs-in-three-months-doable'. ;)
>> I'm currently going through literature and the links to see if this seems
>> feasible. if so, I'll submit a proposal.
>> I'll be lurking on #osm to bounce the occasional idea.
>> - Tijs

More information about the dev mailing list