A Fast Global Optimal Strategy for Iteration Closest Point Using 2D-BnB and Its Application to Rail Profile Registration

Abstract

Profile registration is critical to rail wear measurement with line structured light, and the most popular registration method is iteration closest point (ICP). Unfortunately, ICP is often invalid in actual applications because it is easy to trap into local minima. To solve this problem, we propose a hybrid 2D-point-set registration method which combined ICP to branch and bound. In this way, we can ensure that the ICP algorithm converges to the global optimum. This strategy can achieve high-registration precision, but it suffers from large computation costs. To address this issue, we propose an acceleration scheme by sparsely sampling the point-set before registration to relieve computation burden. Extensive experiments are conducted to verify the precision, stability, and efficiency of our method. The results show that our method has superior precision and stability compared to the other typical profile registration methods. The ability to achieve fast registration speed which is suitable for dynamic measurement is another contribution of our work.