<<Prev 1 2 3 4 5 6 7 8 9 10 11 Next>>
Edge Detection
In order to follow the line we need to extract properties from the image that we can use to steer the
robot in the right direction. The next step is to identify or highlight the line with respect to the
rest of the image. We can do this by detecting the transition from background tile to the line and then
from the line to the background tile. This detection routine is known as edge detection.
The way we perform edge detection is to run the image through a convolution filter that is 'focused' on
detecting line edges. A convolution filter is a matrix of numbers that specify values that are to be
multiplied, added and then divided from the image pixels to create the resulting pixel value.
To learn more about convolution filters have a look at our help section.
We will start with the following convolution matrix that is geared to detect edges:
The next step is to run the images through this edge detector and see what we get ...
<<Prev 1 2 3 4 5 6 7 8 9 10 11 Next>>
|
