[NotInControl]

Originally Posted by faust1706

The calculations on the image are not distance, so it doesn't really matter where the camera is as long as it is high enough up. Pardon my crude paint skills: incase the image doesn't show up: http://imgur.com/U4V1cxm

Imagine that black rectangle is exactly containing the field. All I would be doing is finding the position of the robot with respect to the black rectangle. So it doesn't really matter where the camera is on top. Yes, it would alter the values some, but not by much. I do agree with the lighting conditions comment, that could be a problem.

I assume the end result is calculating distance between objects in the frame. In order to do this, you either need to know the distance between the Camera and the object, or keep an object in view with known dimensions in frame at all times. This allows you to calculate the scaling factor for the height and width of the image and distance between pixels.

I assume you would want to calculate lateral distance between object in frame, because just knowing that object is at pixel x1,y1 and object 2 is at x2,y2 isnt of any value, unless you have determined the proper scaling factor (distance / pixel).

It is a lot easier to mount the camera fixed and have a constant distance, then assuming you can keep an object of known height in field of view at all times. Note again, even if you want to say the field will be in view at all times, as the quadcopter moves around a bit in its watch circle hovering, the skew of the lines of the field perimeter will change causing the scaling factor to be inaccurate and any distance between objects to be more inaccurate.

Originally Posted by faust1706

As for your other idea, that would be most ideal, but it requires other teams to participate in it. I want to do this project without have to ask other teams to alter their robots or do any extra work. I could easily see your idea be implemented and used to great success, but it requires other teams to play along.

Why do you believe this? Just like GPS in your car, you do not need all other cars to have GPS for you to use it. You can use the LPS to track yourself even if no other team uses it.

I assume you are stating this because you would like to know the location of all other objects. This is a true statement, you wouldn't, but even if you did, that information would be useful, but does not allow you to navigate without any local obstacle avoidance.

In either system, you still need to perform local object detection, because neither system can guarantee you won't collide into another non-stationary object.

The above-head camera, can not determine where a non-stationary object is going next. So if you must develop local obstacle avoidance anyway, then you should be able to navigate sucessfully, without other teams broadcasting their location as well.

How ever you plan to implement it, cool project, good luck,
Kevin