Problems concerning transformation estimation for remote sensing image registration are studied in this letter. Based on the affine-invariance property of triangle-area representation, a new algorithm called robust sample consensus judging is proposed. It can be embedded into most robust estimation algorithms with hypothesis-and-testing frameworks (such as random sample consensus) and can significantly improve their computational efficiency without sacrificing remote sensing image registration accuracy. Simulation and experimental results show the merits of the proposed algorithm.
展开▼