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：2000
卷号：XXXIII Part B4 (/1-3)
页码：348-355
出版社：Copernicus Publications
摘要：Manual cartographic generalisation is a holistic process. However, most automatic approaches so far have been sequential; generalisation operators are applied one at a time in a given order. This has been the case both for model generalisation (generalisation of the conceptual model) and the fine-tuning phase (generalisation of the graphics). Our research seeks to demonstrate that fine-tuning phase of cartographic generalisation can be formulated as an optimisation problem and accordingly be solved in a single step. The paper proposes solutions to the two main problems in defining generalisation as an optimisation problem. Firstly, a set of appropriate analytical constraints for the generalisation process is given. In our approach, we are limited to formulating these constraints on point locations. Secondly, the least squares method is proposed to find the optimal solution. To solve the sparse normal equations we use the conjugate- gradient method. A prototype system for simultaneous generalisation has been written in C++. This prototype system communicates with a commercial map production system (LAMPS2 from Laser-Scan). The article concludes with some preliminary test results
关键词：Generalisation; Multi-scale database; Automation; Algorithm; Data Structure; ; Least Squares Adjustment
