You don’t “need” a Kinect to do object isolation… Many other options.
The more sensor info the better… Any good dynamic beast has many sensor types… Sure IR would be good, not only to augment object isolation, but navigation of course too…
Projected laser works too…
All are good in MRL, you should probably start with the sensors you are most familiar with…
Oh… I was working on Kinect code in order to send it to a guy in exchange, he will solve a few other issues I have with the interface to OpenCV
It’s still very rough in the OpenCV frame grabbing area - the GUI had to be re-worked in order to (eventually) offer a lot more functionality - specifically the ability to configure different frame grabbers. At some point this will allow the saving of video footage for future unit testing, and the ability to read in pre-saved video files. It has the Kinect fame grabber, with a mode I added to do object segmentation/isolation called "interleave"
I’m interested specifically in the “Windows” platforms. It currently works with Linux, and I have a virtual windows XP x86 machine which I successfully tested the OpenCVFrameGrabber - There is a few other exotic hardware frame grabbers - no need to test those if you don’t have a FlyCapture or DC1394 camera. If it fails please send me the Log.txt file generated in the directory myrobotlab was started and the type of webcam you have.
