DocumentCode :
150274
Title :
Building extraction from VHR imagery using Morphological Shadow and Building Operator
Author :
Singh, Koushlendra K. ; Mehrotra, Akhil
Author_Institution :
Electron. & Comput. Eng. Dept., Dronacharya Coll. of Eng., Gurgaon, India
fYear :
2014
fDate :
5-7 March 2014
Firstpage :
463
Lastpage :
467
Abstract :
An automatic building extraction method for very high resolution satellite images is presented in this paper. Two novel operators Differential Morphological Shadow Operator (DMSO) and Differential Morphological Building Operator (DMBO) for extracting shadows and buildings respectively are proposed. The method identifies shadows using DMSO. After masking out the shadow, DMBO is applied to obtain the building candidates. The building candidates are filtered using four parameters including shadow test, Shape Index (SI), area and rectangular fit to remove false detections and obtain only buildings. The proposed method was tested on two VHR satellite images acquired by Geoeye-1.The results of the proposed method were compared with two other state of the art methods and it was observed that the proposed method outperformed the other two methods.
Keywords :
buildings (structures); feature extraction; filtering theory; geophysical image processing; image resolution; DMBO; DMSO; Geoeye-1; SI; VHR imagery; VHR satellite images; automatic building extraction method; building candidates; differential morphological building operator; differential morphological shadow operator; false detections; filtering; shadow masking; shadow test; shadows extraction; shape index; very high resolution satellite images; Accuracy; Buildings; Object recognition; Remote sensing; Satellites; Shape; Transforms; NDVI; bottom hat transform; shape index; top hat transform;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computing for Sustainable Global Development (INDIACom), 2014 International Conference on
Conference_Location :
New Delhi
Print_ISBN :
978-93-80544-10-6
Type :
conf
DOI :
10.1109/IndiaCom.2014.6828181
Filename :
6828181
Link To Document :
بازگشت