Fast panoramic video generation method using morphological corner detection

We present a method for building panoramic video for Video GIS. The panoramic video is composed of several images taken by adjacent cameras. The perspective transformation, which estimated from the appropriate corresponding pairs between the images, can construct the panoramic video without unwilling distortions. We use corner points for the corresponding feature, and morphological structures are utilized for fast and robust corner detection. We propose a criterion method of corner strength, which guarantees the robust detection of corner in any situations. For the transformation, 8-parameters are estimated from perspective equations, and bilinear color blending is used to construct a seamless panoramic video. Experiments show that our method yields good results in various conditions.