Volume XL-5/W4
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XL-5/W4, 69-75, 2015
https://doi.org/10.5194/isprsarchives-XL-5-W4-69-2015
© Author(s) 2015. This work is distributed under
the Creative Commons Attribution 3.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XL-5/W4, 69-75, 2015
https://doi.org/10.5194/isprsarchives-XL-5-W4-69-2015
© Author(s) 2015. This work is distributed under
the Creative Commons Attribution 3.0 License.

  18 Feb 2015

18 Feb 2015

COMPLEX BUILDING DETECTION THROUGH INTEGRATING LIDAR AND AERIAL PHOTOS

R. Zhai R. Zhai
  • College of Informatics, Huazhong Agricultural University, 430070, Wuhan, China

Keywords: Building Detection, LiDAR, Aerial Imagery, Image Segmentation, Multiple Seed Selection, Region Growing

Abstract. This paper proposes a new approach on digital building detection through the integration of LiDAR data and aerial imagery. It is known that most building rooftops are represented by different regions from different seed pixels. Considering the principals of image segmentation, this paper employs a new region based technique to segment images, combining both the advantages of LiDAR and aerial images together. First, multiple seed points are selected by taking several constraints into consideration in an automated way. Then, the region growing procedures proceed by combining the elevation attribute from LiDAR data, visibility attribute from DEM (Digital Elevation Model), and radiometric attribute from warped images in the segmentation. Through this combination, the pixels with similar height, visibility, and spectral attributes are merged into one region, which are believed to represent the whole building area. The proposed methodology was implemented on real data and competitive results were achieved.