2017-09-18 23:07:25 -0600 | received badge | ● Popular Question (source) |
2016-01-04 06:35:07 -0600 | received badge | ● Student (source) |
2015-01-14 22:14:29 -0600 | asked a question | Poor man's orthorecification? I am working on a project in which I need images I am collecting from a quadcopter to be the have the same scale thoughout (40 pixels in the center of the image = 4 feet and 40 pixels on the edge of the image = 4 feet). Perfect accuracy is not essential, but I do know the approximate altitude of the quadcopter taking the images. Additionally I know the field of view of the camera I am using. I know methods for orthorectifying images can get involved and require 3d models and such, but is there an easy way to do this by using the information I know and assuming the ground is flat? |
2014-10-21 11:06:23 -0600 | received badge | ● Supporter (source) |
2014-10-20 14:05:27 -0600 | commented question | Best machine learning algorithm for detecting cars in aerial images? @StevenPuttermans, follow up question - once a car was recognized, how did you "mark" it to denote it had already been detected? I would assume with the small rotations you would want to do to make sure no cars were missed that it would detect the same car in multiple orientations. If you don't mind sharing a little, could you maybe give some insight on how you accounted for that? |
2014-10-20 04:59:29 -0600 | asked a question | Best machine learning algorithm for detecting cars in aerial images? I am looking for a machine learning algorithm that will produce good results for detecting cars in aerial images. I'm currently looking at training my own Haar classifier, but if I am understanding correctly a Haar classifier will not take advantage of color. Since I am trying to detect the cars in a parking lot and all the images will be taken from the same altitude, it would make sense to exploit the fact that the cars will all be mostly certain colors and about the same size. Has anyone done anything similar or know of something that would work well for this? |