作者: C. Dorai , J. Weng , A.K. Jain
DOI: 10.1109/34.625115
关键词:
摘要: This paper deals with robust registration of object views in the presence uncertainties and noise depth data. Errors multiple a 3D severely affect view integration during automatic construction models. We derive minimum variance estimator (MVE) for computing transformation parameters accurately from range data two object. The results our experiments show that estimates obtained using MVE are significantly more accurate than those computed an unweighted error criterion registration.