Automatically Annotating and Integrating Spatial Datasets

  • Ching-Chien Chen
  • Snehal Thakkar
  • Craig Knoblock
 et al. 
  • 15


    Mendeley users who have this article in their library.
  • 12


    Citations of this article.


Recent growth of the geo-spatial information on the web has\r
made it possible to easily access a wide variety of spatial data. By inte-\r
grating these spatial datasets, one can support a rich set of queries that\r
could not have been answered given any of these sets in isolation. How-\r
ever, accurately integrating geo-spatial data from different data sources\r
is a challenging task. This is because spatial data obtained from various\r
data sources may have different projections, different accuracy levels\r
and different formats (e.g. raster or vector format). In this paper, we de-\r
scribe an information integration approach, which utilizes various geo-\r
spatial and textual data available on the Internet to automatically anno-\r
tate and conflate satellite imagery with vector datasets. We describe two\r
techniques to automatically generate control point pairs from the satel-\r
lite imagery and vector data to perform the conflation. The first tech-\r
nique generates the control point pairs by integrating information from\r
different online sources. The second technique exploits the information\r
from the vector data to perform localized image-processing on the sat-\r
ellite imagery. Using these techniques, we can automatically integrate\r
vector data with satellite imagery or align multiple satellite images of\r
the same area. Our automatic conflation techniques can automatically\r
identify the roads in satellite imagery with an average error of 8.61 me-\r
ters compared to the original error of 26.19 meters for the city of El Se-\r
gundo and 7.48 meters compared to 15.27 meters for the city of Adams\r
Morgan in Washington, DC.

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document


  • Ching-Chien Chen

  • Snehal Thakkar

  • Craig Knoblock

  • Cyrus Shahabi

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free