Difference between revisions of "Team Commando"
From GcatWiki
(→Image Processing) |
(→Image Processing) |
||
Line 27: | Line 27: | ||
*to-do: | *to-do: | ||
− | + | -figure out physical orientation of computer/camera | |
-build training set: every possible window configuration | -build training set: every possible window configuration | ||
− | -figure out how to get the images... | + | -figure out how to get the images... opencv documentation: http://opencv.willowgarage.com/documentation/cpp/features2d_common_interfaces_of_feature_detectors.html |
-decide on preprocessing method: threshhold, line detection, contrast upping, pulling out the windows, or doing none of that and trusting the neural net. | -decide on preprocessing method: threshhold, line detection, contrast upping, pulling out the windows, or doing none of that and trusting the neural net. | ||
-get the neural net trained and tested. | -get the neural net trained and tested. |
Revision as of 18:08, 26 April 2012
To Do
- command module navigation (Daniel and Matt)
- image processing (Steph, Evan, Jonah)
- decide on a camera
- abstract
Image Processing
- possible cameras
- http://www.logitech.com/en-us/webcam-communications/webcams/devices/6333
- http://us.playstation.com/ps3/accessories/playstation-eye-camera-ps3.html
- http://www.westernunion.com/wushop/category/product/304009645/search/Microsoft-LifeCam-VX-5000-Webcam---Red---Bulk/
- http://www.zagrosrobotics.com/shop/item.aspx?itemid=759
- software
- matlab toolbox
- http://homepages.inf.ed.ac.uk/rbf/BOOKS/PHILLIPS/cips2ed.pdf
- method
- attach laptop to iRobot
- receive signal from robot when it has arrived in room
- use laptop to take image
- process image to determine whether or not a window is open
- to-do:
-figure out physical orientation of computer/camera -build training set: every possible window configuration -figure out how to get the images... opencv documentation: http://opencv.willowgarage.com/documentation/cpp/features2d_common_interfaces_of_feature_detectors.html -decide on preprocessing method: threshhold, line detection, contrast upping, pulling out the windows, or doing none of that and trusting the neural net. -get the neural net trained and tested.