A novel approach to automated road extraction using a hybrid combination of self-organization and model-based extraction techniques is introduced. We use a self-organized mapping technique to first delineate the medial axis topology of road features. This is accomplished through a local clustering of class-binarized spatial information provided from a region segmentation. Since the cluster analysis exemplifies a center-of-gravity solution, it is not sensitive to edge definition. Topological structure is subsequently derived through the application of a graph-theoretic approach to link convergent cluster centers. Taking initialization cues from the centerline extraction results of self-organization, a model-based fitting algorithm is then applied to robustly delineate road segment orientations and widths. Preliminary results demonstrate the ability of this approach to automatically extract road centerline position as well as road segment width and orientation in high spatial resolution urban imagery.
[1]
Teuvo Kohonen,et al.
Self-Organizing Maps, Second Edition
,
1997,
Springer Series in Information Sciences.
[2]
David M. McKeowan.
Research in the Automated Analysis of Remotely Sensed Imagery: 1994-1995
,
1998
.
[3]
Teuvo Kohonen,et al.
Self-Organizing Maps
,
2010
.
[4]
C. Steger,et al.
AUTOMATIC ROAD EXTRACTION BASED ON MULTI-SCALE, GROUPING, AND CONTEXT
,
1999
.
[5]
Louis A. Oddo,et al.
Automatic 3D target model generation
,
1993,
Optics & Photonics.
[6]
Keith Price,et al.
Road Grid Extraction and Verification
,
1998
.
[7]
Louis A. Oddo,et al.
Global shape entropy: a mathematically tractable approach to building extraction in aerial imagery
,
1992,
Other Conferences.