Title: Multi-type change detection of building models by integrating spatial and spectral information
Authors: Chen, Liang-Chien
Huang, Chih-Yuan
Teo, Tee-Ann
Department of Civil Engineering
Issue Date: 2012
Abstract: Detecting building changes followed by updates is preferable for efficient revisions to building models. Additionally, more change types can be detected with spatial information provided by building models for reducing land surveying work. Therefore, for efficient building of model revision and land surveys, this work applies a new multi-type change detection scheme with new light detection and ranging (LIDAR) point clouds, new aerial images and existing building models. By integrating the spatial information from LIDAR data and image-based spectral information, this work identifies changes to existing buildings and identifies newly built and changed buildings. To provide an initial value for further revisions, new building regions are generated from change detection results. Experimental results demonstrate that the proposed scheme has high accuracy for both change type determination and building region generation. To provide comprehensive observations, experimental results deemed unreliable are scrutinized.
URI: http://hdl.handle.net/11536/16196
ISSN: 0143-1161
Volume: 33
Issue: 6
End Page: 1655
Appears in Collections:Articles

Files in This Item:

  1. 000302162000001.pdf