Texture based built-up area extraction from Zi Yuan and spot imagery

The paper addresses built up information extraction from high resolution imagery from two satellites, ZY-1 02C and SPOT-5. The testing is part of a larger experiment that explores spectral, textural and morphological satellite image properties aiming to extract built up information for global built up mapping and characterization. In this work we test SPOT-5 and ZY-1 02C satellites for textural properties associated to built-up. The work is exploratory in nature. We compute image textures using a ”built-up presence index (Pantex)” algorithm. We then compare the texture values with a reference built-up map derived from building footprints map by computing the Receiver Operative Characteristics (ROC). We processed four bands: ZY-HR Panchromatic, ZY Panchromatic, and two “brightness” bands derived from the ZY Pan-sharpened, and SPOT Pan-sharpened. Pan-sharpened products combine both the panchromatic and the multispectral imagery. For each dataset we use two texture windows for a total of eight tests. The study is conducted on imagery covering the city of Firenze, Italy. The landscape is characterized by dense city centres as well as rural scattered settlement. The area is deemed suitable to benchmarking imagery for built up information related to human settlements of different densities. The test shows that the information from SPOT and ZY are generating similar result. However, spatial resolution of panchromatic bands show to have great importance over other factors in extracting built up information.