Automatic detection of urban area from the remote sensing imagery based on improved D-S evidence theory

ABSTRACT

Urban area detection from the remote sensing imagery has important significance in dynamic monitoring on the use types of city land and the city development planning. An approach for full-automatic detection of urban area is proposed, which can fuse any number of features. The combination formula of the traditional D-S evidence theory (TDSET) is improved by adding a processing factor for conflicting evidences based on the original fusion function. For the validity of the proposed method, three positive evidences (gradient mean, Harris feature points and spectral homogeneity) as well as one negative evidence (local gradient orientation density) are selected to test three GeoEye images. Experimental results show that the precision of the proposed method achieves 96.89% and its recall is 86.52%, where the recall increases about 50% comparing with the TDSET.

KEYWORDS:

• Remote sensing imagery
• urban area
• D-S evidence theory
• feature fusion

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes on contributors

Wenzao Shi received the MSc degree in computer sciences in 2007 from the Fujian Normal University, and the PhD degree in communication and information system in 2016 from the Fuzhou University, China. Starting in October 2007, he worked in Fujian Normal University. He is the member in the Key Laboratory of OptoElectronic Science and Technology for Medicine of Ministry of Education. His research interests include digital image segmentation and object extraction, change detection, and remote sensing imagery analysis. He has published more than 20 articles in journals and proceedings and obtained 40 patents.

Zhengyuan Mao is a professor in National Engineering Research Centre of Geospatial Information Technology, Fuzhou University, China. His research interests include the Geographic Information Modeling and analysis, clustering and the change detection from remote sensing imagery. He has published more than 40 articles in journals, books, and proceedings.

Additional information

Funding

This work was supported by the Natural Science Foundation of Fujian Province (2017J01464) and the Program for Changjiang Scholars and Innovative Research Team in University (Grant No. IRT_15R10).