Planar 3D object detection by using the generalized Hough transform

In this work we propose a new method to detect arbitrary planar shapes from a previous template and calculate the parameters that define the transformations between the new image and the template. The image contains a perspective projection of the template subjected to two angle transformations, called tilt and pan, a displacement, a rotation and a scaling. The method uncouples parameter calculation to improve computational requirements by comparing invariant information from the template and the image. The generalized Hough transform is used to compare this information and to vote into a parameter space