FIRST Robotics Competition Discussions

cancel
Showing results for 
Search instead for 
Did you mean: 

Vision Assistant Parameters for matching Target for steering control

I am new to Vision Assistant and our team's intent was to use the camera to drive the robot in a straight line to the target on the tote (I.E. control steering in autonomous mode). However, I couldn't come up with the right parameters to get a match.

But my bigger question is that since the target image from the camera will get bigger and change as the robot approachs the target will our approach even work??

Download All
0 Kudos
Message 1 of 6
(5,615 Views)

gto70ski,

Which functions are you using in vision assistant? If you're using geometric matching, you can set the parameters to accept a range of scaled target images. You could potentially also use color matching, rather than shape matching.

Message 2 of 6
(3,185 Views)

Muffin,

Thanks for the help! Pulled up geometric matching but will need to change camera settings to get an 8 bit binary image. I also saw object tracking under "Processing functions: Color". Hopefully will get time later today to work on the issue.

Thanks Again!

0 Kudos
Message 3 of 6
(3,185 Views)

I looked at the camera settings and do not see a way to downgrade the camera to producing 8 bit binary. The camera is normally producing a 640 X 480 RGB (32Bit) JPEG image. Therefore before I can use any processing, I need to get the image into 8 bit binary??

Again thanks for your help.

0 Kudos
Message 4 of 6
(3,185 Views)
0 Kudos
Message 5 of 6
(3,185 Views)

Have you looked at the 2015 Vision Example in the FRC Examples yet (from the Splash screen select Support->Find FRC Examples)? Or Tutorial 8 (from the Splash screen select Tutorials).

The approaches taken in the example code are by no means the only way to detect the totes, but I just wanted to make sure you knew they existed.

0 Kudos
Message 6 of 6
(3,185 Views)