Unifying Stereo, Motion and Object Recognition via Epipolar Geometry

In this paper I try to show that through epipolar geometry we can unify the problems of image matching in stereo, motion and object recognition, which have been treated separately. Stereo matching has been known as a 1D search problem. But matching in motion and object recognition have been known as 2D search problems. I show that by recovering epipolar geometry underlying the images, the correspondence search problems in motion and object recognition can also be changed to be 1-dimensional, thus providing a framework to treat all these 3 problems in a uni ed way.