Share Email Print

Proceedings Paper

Research on the classification result and accuracy of building windows in high resolution satellite images: take the typical rural buildings in Guangxi, China, as an example
Author(s): Baishou Li; Yujiu Gao
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The information extracted from the high spatial resolution remote sensing images has become one of the important data sources of the GIS large scale spatial database updating. The realization of the building information monitoring using the high resolution remote sensing, building small scale information extracting and its quality analyzing has become an important precondition for the applying of the high-resolution satellite image information, because of the large amount of regional high spatial resolution satellite image data. In this paper, a clustering segmentation classification evaluation method for the high resolution satellite images of the typical rural buildings is proposed based on the traditional KMeans clustering algorithm. The factors of separability and building density were used for describing image classification characteristics of clustering window. The sensitivity of the factors influenced the clustering result was studied from the perspective of the separability between high image itself target and background spectrum. This study showed that the number of the sample contents is the important influencing factor to the clustering accuracy and performance, the pixel ratio of the objects in images and the separation factor can be used to determine the specific impact of cluster-window subsets on the clustering accuracy, and the count of window target pixels (Nw) does not alone affect clustering accuracy. The result can provide effective research reference for the quality assessment of the segmentation and classification of high spatial resolution remote sensing images.

Paper Details

Date Published: 9 December 2015
PDF: 8 pages
Proc. SPIE 9808, International Conference on Intelligent Earth Observing and Applications 2015, 98083N (9 December 2015); doi: 10.1117/12.2207378
Show Author Affiliations
Baishou Li, Guilin Univ. of Technology (China)
Yujiu Gao, Guilin Univ. of Technology (China)

Published in SPIE Proceedings Vol. 9808:
International Conference on Intelligent Earth Observing and Applications 2015
Guoqing Zhou; Chuanli Kang, Editor(s)

© SPIE. Terms of Use
Back to Top