I am trying to calculate how much an object moved in each successive image captured by a stationary camera . What we are testing here is the repeatability of our setup, to place an object in the same place each time.
The object in question has a stamp located on its center, which has a simple shape (see below). The camera has only a few square millimeters (~ 25). There may be other artifacts in the image that need to be cleared, but all I can show at the moment is just a simple drawing.
Template http://i36.tinypic.com/10cq49d.jpg
What I'm trying to calculate is the offset, where the lines intersect in each image compared to the previous one. In the figure below, red lines indicate where the lines intersect in the second image, i.e. how far they have come.
Problem http://i35.tinypic.com/xptfr.jpg
My question is, using the C # library of image recognition, preferably EmguCV, how can I calculate the sizes of the green rectangle (offset)? I followed a few Emgu tutorials, and thanks to cunning transformations, the software can only detect two lines, but I don’t know how to get to where they intersect, since the library creates more than 500 mini-lines instead of two long ones.
Any help, ideas and suggestions are welcome. Thank!