Yes, exactly. Last year Dave dropped the hint that the CUMcam2 would be back, and I'm hoping teams have spent some time in the off-season working with the camera.
Quote:
Originally Posted by Kevin Watson
The best thing to do at this point is to spend some time thinking about what the camera will "see" from the starting area. It's important to know a few things:
1) The camera has a very wide field of view of ~60 degrees.
2) The camera will not always "see" two lights. Recent data taken on a regulation field shows that the camera will only detect a single light if it's within about +/- 25 degrees of rotation relative to the camera.
3) If two lights are detected by the camera, the camera will return a single rectangle around both lights.
4) If only one light is detected by the camera, the number of pixels reported by the camera will be small (~10).
-Kevin
|
Kevin, There seems to be some confusion about this years camera code. At the kickoff we were all told that this years camera code could support multiple targets. Is this the case? And if so. How? The code on your repository appears to be no different than last years. Does the new code independantly track multiple centroids? Or does it average the independant targets to produce one centroid? From the above statement it appears that the only way to differentiate between multiple and isolated targets is by the number of pixels. If two targets are "seen" by the camera, how do you direct the camera to select one of the targets?