I've been doing a little research about autonomous rovers. I saw a video of a rover with a webcam used for object avoidance. I've tried to find information on implementing this alongside an arduino. Can anyone point me in the direction of what to look for, or what searches I could use to find more information.
Loren
Webcam and Arduino don't sit well in the same sentence.
AWOL:
Webcam and Arduino don't sit well in the same sentence.
Even if they did, ultra sonic or infrared sensors would probably be just as effective, if not more so, for obstacle avoidance. A webcam could be better for things like object recognition.
I was thinking along the lines of the possibility of Raspberry Pi running the object avoidance and communicating commands with the arduino.
Loren:
I was thinking along the lines of the possibility of Raspberry Pi running the object avoidance and communicating commands with the arduino.
Well in that it could be feasible, but all the actual obstacle avoidance logic (AKA "the hard stuff") would be done on Pi. So for questions about that you'd probably want to go to their official forums. An Arduino would still be useful for controlling the motors, but that's relatively simple compared to visual object detection and ranging.
For the Raspberry Pi, which is Linux-based, anything computer vision related you'd want to go to the OpenCV documentation and forums. It's not "obstacle avoidance software" but rather a set of software routines to simplify interfacing with a camera and performing the image manipulation algorithms common for computer vision.
If you're looking for a simple technique I'd suggest a line-generating laser mounted above your camera and pointed at the floor about a meter ahead of the robot. Any obstacles will show up with a red line on them, and it's relatively straightforward picking out that red line from the image.
Roborealm is good software for this sort of thing, but it's Windows-based. Still worth looking at for ideas.
Chagrin:
If you're looking for a simple technique I'd suggest a line-generating laser mounted above your camera and pointed at the floor about a meter ahead of the robot. Any obstacles will show up with a red line on them, and it's relatively straightforward picking out that red line from the image.
Actually, it's better to have the camera facing "downward", and the laser line generator facing forward - that way you can do 3D ranging:
http://www.seattlerobotics.org/encoder/200110/vision.htm
Mount a red filter over the camera lens (if using a red laser - basically, your filter should match as close as possible to the wavelength of the laser) to drop out background light and make the laser stand out more.