期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：1992
卷号：XXIX Part B3
页码：101-108
出版社：Copernicus Publications
摘要：The solution of a great, sparse, over-determined linear or linearized system ofequations needs euristics such as 'minimum degree' and 'dissection' to control fill-inso to reduce costs and resources. Euristics applied up to now are general and have beenstudied to be coupled with the method of solution of a normal system of equations. Thepurpose of this paper is double: to present a new euristic for a sub-class of problemsincluding adjustment procedures and solve the matrix block structure so obtained by amodified version of the classic QR factorization. In this way, fill-in resultscompletely confined into blocks that, according to their location within the matrix,allow to obtain a method of solution that is stable, less expensive and efficient forparallel implementations.
