Recently, in the area of GIS (Geographic Information System), lots of researchers are attracted to efficient update of a digital map data. However, its update cost in the conventional methods is not low. On the other hand, in the case of carrying out some works in a municipal government by employing GIS, the following problem occurs. That is, it is not easy to carry out them because the shape or 'existence or not' of a building on a base map of road ledger generated from GIS is not always relevant to its truth. In our discussion, we limit the scope to building shape. The purpose of our research is to develop an efficient and available update method of building shape with satisfying the following two conditions: (i) it does not contain a data structuring phase from raster images and the update cost in it is not too high, and (ii) it use a map updated more frequently than the basic map which should be updated, and is practically available. Authors investigate semi-automatic and pseudo update of a building by employing an urban design map which has higher update frequency but less precision than the base map of road ledger. In here, 'pseudo' means that we put the major interest to carry out the municipal government works and provide the first priority with the relevance to the truth on the shape or 'existence or not' of a building, even if we sacrifice its precision of the map. In the present paper, we propose its concrete algorithm and evaluate it. According to the evaluation, our proposition has achieved 85.0 % recall and 91.9 % precision. Our proposition has also obtained good result in qualitative evaluation.
[1]
Peng Gong,et al.
Automated building change detection using UltraCamD images and existing CAD data
,
2010
.
[2]
F. Samadzadegan,et al.
Automatic Image to Map Registration Based on Genetic Algorithm
,
2006
.
[3]
Dan Klang,et al.
AUTOMATIC DETECTION OF CHANGES IN ROAD DATABASES USING SATELLITE IMAGERY
,
2003
.
[4]
Ryosuke Shibasaki,et al.
Building change detection Algorithm Using Aerial Imagery and Precise 3-D Data
,
2005
.
[5]
Shintaro Watanabe,et al.
Detecting building changes using epipolar constraint from aerial images taken at different positions
,
2001,
Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).