Share Email Print
cover

Proceedings Paper

Information extraction and application ability of residential area based on tiangong-2 images
Author(s): Wei Wu
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The Tiangong-2 Space Laboratory is the second space laboratory launched by China after Tiangong-1. It is equipped with a wide-band imager with wide-band, wide-field, multi-spectral features, and has application potential in regional planning of disaster prevention and disaster reduction, disaster monitoring and loss evaluation. This paper proposes a method of residential area extraction based on Tiangong-2 images. Taking full advantage of the spectral response characteristics of typical objects such as vegetation, water body and residential area in the images, on the basis of image geometry processing and image enhancement, image threshold segmentation and remote sensing index are used to realize the extraction of feature samples. Through the NAPCA transform and supervised classification of SVM, the extraction of residential areas is realized. The method can realize the rapid and semi-automatic selection of residential area, vegetation and water samples, and can obtain better extraction precision of residential areas. The experimental results show that the Tiangong-2 images with 100-meter spatial resolution can achieve the extraction accuracy of more than 70% of the residential area, and can be used for large-scale spatial distribution analysis of residential area and disaster impact area assessment.

Paper Details

Date Published: 6 May 2019
PDF: 7 pages
Proc. SPIE 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018), 110693N (6 May 2019); doi: 10.1117/12.2524399
Show Author Affiliations
Wei Wu, National Disaster Reduction Ctr. of China (China)


Published in SPIE Proceedings Vol. 11069:
Tenth International Conference on Graphics and Image Processing (ICGIP 2018)
Chunming Li; Hui Yu; Zhigeng Pan; Yifei Pu, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray