Difference between revisions of "ReacTable"

From Hackteria Wiki
Jump to: navigation, search
Line 1: Line 1:
 
This is a multi touch table that reads markers placed on the screen and does a corresponding action. Thus reading the object on the screen and functioning accordingly. The table uses reactivision software. This application was designed to track specially designed fiducial markers. By downloading the TUIO library you can cerate a program that operates on these markers. the table uses infra red light for finger tracking.
 
This is a multi touch table that reads markers placed on the screen and does a corresponding action. Thus reading the object on the screen and functioning accordingly. The table uses reactivision software. This application was designed to track specially designed fiducial markers. By downloading the TUIO library you can cerate a program that operates on these markers. the table uses infra red light for finger tracking.
 
a webcam takes in the feed and runs it through reactivision. It is then processed in processing and displayed again on the screen.
 
a webcam takes in the feed and runs it through reactivision. It is then processed in processing and displayed again on the screen.
 +
 +
'''We used this to give information and protocals when a certian object was put on it.'''
 +
 +
 +
 +
'''How reactivision works'''
 +
 +
In a nutshell the system works like this: reacTIVision tracks specially designed fiducial markers in a real time video stream. The source image frame is first converted to a black&white image with an adaptive thresholding algorithm. Then this image is segmented into a tree of alternating black and white regions (region adjacency graph). This graph is then searched for unique left heavy depth sequences, which have been encoded into the fiducial symbol. Finally the found tree sequences are matched to a dictionary to retrieve an unique ID number. The fiducial design allows the efficient calculation of the marker's center point as well as its orientation. OSC messages implementing the TUIO protocol encode the fiducials' presence, location, orientation and identity and transmit this data to the client applications.
 +
Additionally reacTIVision uses the result of the image segmentation in order to retrieve and identify small round white blobs as finger tips on the surface. A quick and dirty shape matching algorithm selects the actual finger blobs from the possible region candidates. A complementary blob tracking algorithm is also taking advantage of the same data in order to track eventually not recognized fiducials, for example where fast movements destroy the actual fiducial structure in the image.

Revision as of 12:04, 18 October 2010

This is a multi touch table that reads markers placed on the screen and does a corresponding action. Thus reading the object on the screen and functioning accordingly. The table uses reactivision software. This application was designed to track specially designed fiducial markers. By downloading the TUIO library you can cerate a program that operates on these markers. the table uses infra red light for finger tracking. a webcam takes in the feed and runs it through reactivision. It is then processed in processing and displayed again on the screen.

We used this to give information and protocals when a certian object was put on it.


How reactivision works

In a nutshell the system works like this: reacTIVision tracks specially designed fiducial markers in a real time video stream. The source image frame is first converted to a black&white image with an adaptive thresholding algorithm. Then this image is segmented into a tree of alternating black and white regions (region adjacency graph). This graph is then searched for unique left heavy depth sequences, which have been encoded into the fiducial symbol. Finally the found tree sequences are matched to a dictionary to retrieve an unique ID number. The fiducial design allows the efficient calculation of the marker's center point as well as its orientation. OSC messages implementing the TUIO protocol encode the fiducials' presence, location, orientation and identity and transmit this data to the client applications. Additionally reacTIVision uses the result of the image segmentation in order to retrieve and identify small round white blobs as finger tips on the surface. A quick and dirty shape matching algorithm selects the actual finger blobs from the possible region candidates. A complementary blob tracking algorithm is also taking advantage of the same data in order to track eventually not recognized fiducials, for example where fast movements destroy the actual fiducial structure in the image.