Robust homography estimation from planar contours based on convexity

摘要: We propose a homography estimation method from the contours of planar regions. Standard projective invariants such as cross ratios or canonical frames based on hot points obtained local differential properties are extremely unstable in real images suffering pixelization, thresholding artifacts, and other noise sources. explore alternative constructions global convexity contour discrete tangents concavities. show that frame can be robustly extracted arbitrary shapes with at least one appreciable concavity. Algorithmic complexity stability theoretically discussed experimentally evaluated number applications including shape matching, alignment pose estimation. conclude procedure is computationally efficient notably robust given ill-conditioned nature problem.