The Vancouver Canucks Fan Zone along Georgia St. for Game 7 of the 2011 Stanley Cup Final
was captured at 5:46 pm on June 15, 2011. It is made up of 216 photos (12 across by 18 down)
stitched together, taken over a 15-minute span, and is not supposed to represent a single moment
in time. The final hi-res file is 69,394 X 30,420 pixels or 2,110 megapixels.
Special thanks to Bonita Howard and CBC Real Estate.
Given this, shot has to ask what sort of capability do LE and DOD entities have at their disposal
when it comes to detecting individual faces in a large crowd?
Adobe Flash image link - http://www.gigapixel.com/image/gigapan-canucks-g7.html
Put your cursor anywhere in the crowd and double-click a couple of time and then use the scroll
button in the center of your mouse. You can zero in on one single face. The clarity is unbelievable.
Sincerely,
Replies
This is not an aerial image. Ronnie captured this with a Gigapan robot from a building using a Canon T1i DSLR camera. There are many gigapixel images that have been captured from the ground. What would be interesting is capturing higher resolution panoramas or photogrammetry from the air. One problem is the maximum payload and the ability to fly at a slower velocity and in a more stable manner. It would also be really interesting to develop a mobile gps ground station that you could set up at a precise location and post process for error along with some control points.
a. high resolution oblique panoramas from the air.
b. high resolution near vertical imager ( similar to grassrootsmapping.org )
http://publiclaboratory.org/tool/balloon-mapping
c. DEM ( digital elevation maps ) from near vertical imagery or oblique imagery using photogrametry.
http://palentier.blogspot.com/
If you want to work on face recognition, you might look at machine vision libraries such as OpenCV
http://benosteen.wordpress.com/2010/03/03/face-recognition-much-eas...