- From: Jens de Smit <jens.desmit@surfnet.nl>
- Date: Tue, 24 Aug 2010 15:01:08 +0200
- To: Alex Hill <ahill@gatech.edu>
- CC: Thomas Wrobel <darkflame@gmail.com>, public-poiwg@w3.org
>> For things that can't be done at all with co-ordinates (like your car >> example), we have to think of what other data to use so the device can >> get a fix on if its in view, and where it is. My view is this pretty >> much has to be an image. Some sort of image recognition of the car, >> that can then be associated with data. It could also be a RFID, or >> another identifying technology....but that would require a physical >> change to the car, so it seems less practical. > > I think this is a good example of why Rob Manson is proposing something > akin to a sensor-based approach. > Although image recognition seems to be the "ground truth" for > registering content to objects, that image recognition will > only likely be a part of a larger identification process. > Data communications between the vehicle will likely narrow the visual > search and provide vital disambiguation information. > While unrealistic only a decade years ago, it isn't inconceivable that > every object (i.e a Gillette Razor) will have a built in communication > and tracking device before we > have reliable image recognition on mobile devices. > Either way, I think we have to acknowledge that image recognition always > need some form of contextual aid - and that leads us to including other > complementary sources in the equation. ...which brings us back to the ongoing development of incorporating more and more sensors into devices and the fact that we want to and _need_ to use them to create better experiences. Jens
Received on Tuesday, 24 August 2010 13:01:41 UTC