Use of object space matching for feature extraction in multiple aerial images

In certain applications of computer vision and digital photogrammetry, several images of the same scene are available. The dassical example in photogrammetry is aerotriangulation where a surface patch in object space may appear in as many as nine images. A similar situation exists where a moving robot continuously takes pictures. In all these cases, there is a need to find corresponding (conjugate) points in all the images involved. In this paper, we explore issues in object space matching using photogrammetric principles for computer vision. We provide a general philosophical basis for our research and demonstrate its utility with the example of multiple image point matching. In the proposed model, we reconstruct the shape and reflectance of the surface patch from the gray levels of the corresponding image patches. The geometry of the surface patch is approximated by a digital elevation model (DEM). For every surface grid element a reflectance value is introduced. Apart from the geometric and radiometric parameters of the surface patch, the exterior orientation of the image patches is introduced as unknowns. Since the image patches are rather small, a parallel projection is used instead of the central projection. The description of the mathematical model is followed by implementation details and results obtained from a prototype version of an automatic aerotriangulation system.