Urban Area Extent Extraction in Spaceborne HR and VHR Data Using Multi-Resolution Features

Sensors

Gianni Cristian Iannelli¹  Gianni Lisini¹  Fabio Dell➬qua¹  Raul Queiroz Feitosa¹  Gilson Alexandre Ostwald Pedro da Costa¹ 

[1] Department of Industrial and Information Engineering, University of Pavia, Via Ferrata 5, Pavia 27100, Italy; E-Mails:

关键词: urban areas;    multi-resolution processing;    feature fusion;   

DOI  :  10.3390/s141018337

来源: mdpi

【 摘 要 】

Detection of urban area extents by means of remotely sensed data is a difficult task, especially because of the multiple, diverse definitions of what an “urban area” is. The models of urban areas listed in technical literature are based on the combination of spectral information with spatial patterns, possibly at different spatial resolutions. Starting from the same data set, “urban area” extraction may thus lead to multiple outputs. If this is done in a well-structured framework, however, this may be considered as an advantage rather than an issue. This paper proposes a novel framework for urban area extent extraction from multispectral Earth Observation (EO) data. The key is to compute and combine spectral and multi-scale spatial features. By selecting the most adequate features, and combining them with proper logical rules, the approach allows matching multiple urban area models. Experimental results for different locations in Brazil and Kenya using High-Resolution (HR) data prove the usefulness and flexibility of the framework.

【 授权许可】

CC BY   
© 2014 by the authors; licensee MDPI, Basel, Switzerland.