Volume 9 Number 10 (Oct. 2014)
Home > Archive > 2014 > Volume 9 Number 10 (Oct. 2014) >
JCP 2014 Vol.9(10): 2365-2370 ISSN: 1796-203X
doi: 10.4304/jcp.9.10.2365-2370

Automatic Extraction of the Building Rectilinear Rooftops Based on Region over Growing

Min Qi1, Jiankui Jia1, Yuelei Xu2, Ke Li3
1School of electronics and information, Northwestern Polytechnical University, Xi’an,P.R. China
2Aeronautics and Astronautics Engineering college, Air Force Engineering University, Xi’an, P.R. China
3School of automation, Northwestern Polytechnical University, Xi’an, P.R. China

Abstract—Extracting the building rooftops from the satellite image has been an active research subject with a wide range of applications. However, most of previous approaches have some drawbacks: being sensitive to initial seed points which are defined by the operator according to his experiences; threshold selection is also finished by such interactive works; unexpected results for color image; needing extra data source. In order to solve those problems, this paper proposes an automatic approach that extracts building rooftops from a single satellite image, and furthermore makes the rooftops be of rectilinear contour in order to supply modeling data for 3-D building reconstruction. Firstly, an automatic method is proposed to obtain the initial seed points for the region growing method. Secondly, by over growing strategy aided with Canny edge map, the building areas can be departed from the non-building areas avoiding the difficulty of threshold selection. Thirdly, the rooftops are later refined and fitted by a block operation algorithm to get the rectilinear boundaries, and then the rectilinear contours are extracted by boundary tracking. It shows the quick and considerably precise results, and the tree occlusion problem is also solved in a degree.

Index Terms—building extraction, region growing, rectilinear fitting, satellite images

[PDF]

Cite: Min Qi, Jiankui Jia, Yuelei Xu, Ke Li, "Automatic Extraction of the Building Rectilinear Rooftops Based on Region over Growing," Journal of Computers vol. 9, no. 10, pp. 2365-2370, 2014.

General Information

ISSN: 1796-203X
Abbreviated Title: J.Comput.
Frequency: Bimonthly
Editor-in-Chief: Prof. Liansheng Tan
Executive Editor: Ms. Nina Lee
Abstracting/ Indexing: DBLP, EBSCO,  ProQuest, INSPEC, ULRICH's Periodicals Directory, WorldCat,etc
E-mail: jcp@iap.org
  • Nov 14, 2019 News!

    Vol 14, No 11 has been published with online version   [Click]

  • Mar 20, 2020 News!

    Vol 15, No 2 has been published with online version   [Click]

  • Dec 16, 2019 News!

    Vol 14, No 12 has been published with online version   [Click]

  • Sep 16, 2019 News!

    Vol 14, No 9 has been published with online version   [Click]

  • Aug 16, 2019 News!

    Vol 14, No 8 has been published with online version   [Click]

  • Read more>>