高空间分辨率遥感影像分割定量实验评价方法综述

发布时间：2018-06-02 09:36

本文选题：高空间分辨率遥感影像 + GEOBIA　；参考：《地球信息科学学报》2017年06期

【摘要】：GEOBIA(Geographic Object-Based Image Analysis)技术针对高空间分辨率遥感影像分析的效果和精度远优于基于像元的传统方法。影像分割作为GEOBIA中的关键技术,学者们对此已经做了大量的研究,提出众多分割算法。对分割算法进行评价和分割技术本身同样重要,通过分割评价可以对分割算法的性能进行评价,比较不同分割算法的优劣,为影像选择合适的分割算法并设定合适的分割参数。影像分割的目的是为了实现影像分析操作的自动化,而主观评价法、系统评价法和分析评价法,因其无法给出客观定量指标的特点,难以应用于实时、自动化的高分辨率影像信息提取与分析系统当中。加之近年来针对分割评价方法的研究远远落后于分割算法本身,因此对定量分割评价方法进行综述对于影像分割方法及其应用研究意义重大。本文对现有的评价方法进行系统总结,建立了针对高空间分辨率遥感影像分割评价方法的分类体系。对各种方法,特别是定量的实验评价法进行对比,分析其应用范围和优劣,最后指出了高空间分辨率遥感影像分割评价未来的改进方向和应用前景。
[Abstract]:The effect and precision of GEOBIA(Geographic Object-Based Image analysis for high spatial resolution remote sensing image analysis is much better than the traditional method based on pixel. As a key technology in GEOBIA, many researchers have done a lot of research and put forward many segmentation algorithms. It is also important to evaluate the segmentation algorithm and the segmentation technology itself. The performance of the segmentation algorithm can be evaluated by the segmentation evaluation, the advantages and disadvantages of different segmentation algorithms can be compared, and the appropriate segmentation algorithm is selected and the appropriate segmentation parameters are set for the image. The purpose of image segmentation is to realize the automation of image analysis, but subjective evaluation, system evaluation and analysis evaluation are difficult to be used in real time because they can not give the characteristics of objective quantitative indexes. Automatic high-resolution image information extraction and analysis system. In addition, in recent years, the research on segmentation evaluation is far behind the segmentation algorithm itself, so the review of quantitative segmentation evaluation method is of great significance to the research of image segmentation methods and their applications. In this paper, the existing evaluation methods are systematically summarized, and a classification system for high spatial resolution remote sensing image segmentation and evaluation methods is established. This paper compares various methods, especially the quantitative experimental evaluation method, analyzes its application scope, advantages and disadvantages, and finally points out the future improvement direction and application prospect of high spatial resolution remote sensing image segmentation evaluation.
【作者单位】：中国地质大学(北京)信息工程学院;
【基金】：国家自然科学基金项目(41371347、41671369)
【分类号】：TP751

【相似文献】