"Automatically and Accurately Conflating Road Vector Data, Street Maps and Orthoimagery"

9/02/05: 10:30 AM, webcast
11th Floor Large Conference Room
Host: Patrick Pantel, schedule

Abstract: Recent growth of the geospatial information on the web has made it possible to access various spatial data. By integrating diverse spatial datasets, one can support the queries that could have not been answered given any of these sets in isolation. However, accurately integrating different geospatial data remains a challenging task because diverse geospatial data may have different projections and different accuracy levels. Most of the existing conflation algorithms only handle vector-vector data integration or require human intervention to accomplish vector-raster or raster-raster data integration. We propose an approach, named AMS-Conflation, that achieves automatic geospatial data integration by exploiting multiple sources of geospatial information. In particular, we focus on vector-imagery and map-imagery conflation. For vector-imagery conflation, we describe techniques to automatically generate control points by exploiting the information from the road vectors to perform localized image processing on the imagery. We also evaluate various filtering algorithms to eliminate inaccurate control point pairs. Based on the experimental results, these techniques automatically align the roads to orthoimagery, such that in one of our experiments, 85% of the conflated roads are within 4.5 m from the real road axes compared to 55% for the original roads for partial areas in St. Louis, MO. For map-imagery conflation, our approach can take a map of unknown coordinates and automatically align it with an image. Our approach first aligns road vectors with imagery using vector-imagery conflation techniques to generate control points on the imagery. For the maps, our approach utilizes image processing techniques to detect intersections. Furthermore, we present an algorithm (called GeoPPM) to compute the matched point pattern from the two point sets. The experimental results show that GeoPPM only misidentified one point pattern from the fifty tested maps. The experimental results also show that our approach can align a set of TI GER maps with imagery for an area in St. Louis, MO, such that 85.2% of the conflated map roads are within 10.8 m from the real road axes compared to 51.7% for the original and geo-referenced TIGER map roads.

About Ching-Chien (Jason) Chen: Dr. Ching-Chien (Jason) Chen is currently the Director of Research and Development at Geosemble Technologies. He received his Ph.D. in Computer Science from University of Southern California in May 2005 for a dissertation that presented novel approaches to automatically align road vector data, street maps and orthoimagery. His research interests are distributed web service discovery and the fusion of geographical data, such as imagery, vector data and raster maps with open source data. His current research activities include the automatic conflation of geospatial data, automatic processing of raster maps and design of GML-enabled and GIS-related web services. Dr. Chen has proposed various approaches to accomplish automatic vector to imagery and map to imagery conflation. His proposed techniques were published in some major GIS and spatial database conferences, such as SSTD 2003 and ACM GIS 2004. He has pending patents in the techniques for automatic vector to imagery integration and automatic map to imagery r egistration. He had also developed several GIS applications and GIS web services to support geospatial data integration and annotation in the imagery. He currently holds Microsoft Certified Solution Developer (MCSD) certification.

Last updated: Mon Jun 19 17:44:06 2006