CAJ | 학술논문

为了解决图像配准中因外点引起迭代次数激增而导致的配准效率低下的问题，提出一种改进的相邻概率随机抽样一致性算法。首先通过自适应优化内点被采用概率，淘汰外点从而形成正循环采样，结合模型评价函数估计出临时模型并得到临时内点集，再根据内点相邻原则筛选部分内点进行重采样，最后采用预检验技术得到最佳模型参数。实验结果表明：在数据外点率较高的情况下该算法能有效减少迭代次数，缩短算法时间，从而提高了算法效率。
위료해결도상배준중인외점인기질대차수격증이도치적배준효솔저하적문제，제출일충개진적상린개솔수궤추양일치성산법。수선통과자괄응우화내점피채용개솔，도태외점종이형성정순배채양，결합모형평개함수고계출림시모형병득도림시내점집，재근거내점상린원칙사선부분내점진행중채양，최후채용예검험기술득도최가모형삼수。실험결과표명：재수거외점솔교고적정황하해산법능유효감소질대차수，축단산법시간，종이제고료산법효솔。
In order to solve the problem of the inefficient of the image registration due to the abruptly increasing iterations for the exterior point ,this paper proposes an improved adjacent probability random sampling consistency algorithm .At first ,through adapting the optimizing interior point probability ,a positive cycle sampling can be formed by eliminating exterior point .And then ,the temporary interior point set can be obtained by estimating the temporary model with the model evaluation function ,and parts of the interior points can be selected and re -sampled according to the principle of adjacent interior point .Finally ,the optimal model parameters can be obtained by combining the pre -inspection technique .Experimental results show that the algorithm can effectively reduce the number of interations and shorten the running time ,thereby improving the efficiency of the algorithm in the case of a higher proportion of exterior point .