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：2006
卷号：XXXVI-4/C42
出版社：Copernicus Publications
摘要：Primarily due to the progresses in spatial resolution of satellite imagery, the methods of segment-based image analysis for generating and updating geographical information are becoming more and more important. In the studies of Neubert and Meinel (2003) and Meinel and Neubert (2004) the capabilities of available segmentation programmes for high resolution remote sensing data were assessed and compared. This paper intends to supplement the preceding studies by considering recently available software. Moreover, a self-implemented optimised segmentation algorithm for the image processing software HALCON is included in the test. The achieved segmentation quality of each programme is evaluated on the basis of an empirical discrepancy method using pan- sharpened multi-spectral IKONOS data. Furthermore, an overview of further methods for quantitative image segmentation quality evaluation is given. Finally, the qualitative and quantitative outcomes are compared and contrasted to the previously tested software solutions. The stated results provide an approach to determine each programme's performance and appropriateness for specific segmentation tasks
关键词：Segmentation; Quality; Software; Methods; Comparison; High resolution; IKONOS
