Share Email Print
cover

Proceedings Paper

Multispectral lines of communication extraction
Author(s): James R. Lersch; A. Evan Iverson; Karen F. West
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

A new technique for the extraction of lines of communication (LOCs) from Landsat Thematic Mapper (TM) data is presented. A multi-stage approach is taken. First, LOC segments are detected. Next, gaps between segments are filled by a segment connection routine. Finally, the connected segments are identified. In the segment detection stage a distinction is made between wide LOC and narrow LOC segments. Wide LOC segments are detected by a neural network based segmentation algorithm. Input to the network are spatial and spectral features computed about each pixel. Narrow LOC segments are detected by a cost minimization algorithm designed to work on the multispectral data. Segment connection is performed by connecting those LOC segments that have consistent alignment, position, and spectral signatures. The identification stage consists of a neural network with inputs of shape and spectral features about each connected LOC. While the system is still being refined, most critical pieces have been prototyped and tested. Initial results are encouraging.

Paper Details

Date Published: 8 July 1994
PDF: 12 pages
Proc. SPIE 2231, Algorithms for Multispectral and Hyperspectral Imagery, (8 July 1994); doi: 10.1117/12.179784
Show Author Affiliations
James R. Lersch, Science Applications International Corp. (United States)
A. Evan Iverson, Science Applications International Corp. (United States)
Karen F. West, Science Applications International Corp. (United States)


Published in SPIE Proceedings Vol. 2231:
Algorithms for Multispectral and Hyperspectral Imagery
A. Evan Iverson, Editor(s)

© SPIE. Terms of Use
Back to Top