The University of Michigan - Ann Arbor
Electrical Engineering and Computer Science
Department
Radar Image Processing
Lab
Classification
Land-cover classification is one of the main uses for
remotely-sensed imagery of nay kind and SAR is no exception. The ecological
and climate-modeling communities use this data to produce models with higher
fidelity than before. Others also use the data over smaller areas such
as the U.S. Forest Service which needs estimates of forest growth and health.
Potentially this could even be used for identifying health and type of
crops. In every case, the image must first be classified to the species
level before other details can be determined.
Some examples are shown below. The image on the left shows a classification
using a composite of the ERS and JERS Satellite SAR data. The image
on the right shows a portion of the same area but classified using multi-frequency
and multi-polarization SIR-C SAR data. The 2 methods agree well with
each other and with reality.


Some of our publications in this area:
- Dobson, M.C., L.E. Pierce, K. Sarabandi, F.T. Ulaby,
and T. Sharik, ``Preliminary analysis of ERS-1 SAR for forest ecosystem
studies,'' IEEE Trans. Geosci. Remote Sensing., vol. 30, no. 2, 203-211,
March 1992. [Abstract] [umERS1.pdf]
- Way, J. B., E. Rignot, K. McDonald, R. Oren, R. Kwok,
G. Bonan, C. Dobson, L. Viereck and J. E. Roth, Evaluating the Type and
State of Alaska Tiaga Forests with Imaging Radar for Use in Ecosystem Flux
Models, IEEE Transactions Geoscience and Remote Sensing, Vol. 32, No. 2,
pp. 353-370, March 1994. [Abstract] [umAlaska.pdf]
- Sarabandi, K., L. Pierce, Y. Oh, and F.T. Ulaby, ``Power
lines: Radar measurements and detection algorithm for polarimetric SAR
images,'' IEEE Trans. Aerospace and Electronic Sys., vol. 30, no. 2, 632-648,
April 1994. [Abstract] [umPower.pdf]
- Pierce, L. E., F. T. Ulaby, K. Sarabandi, and M. C. Dobson,
Knowledge-Based Classification of Polarimetric SAR Images, IEEE Transactions
Geoscience and Remote Sensing, Vol. 32, No. 5, pp. 1081-1086, Sept. 1994.
[Abstract] [umKnowledge.ps.gz
(2.5MB)] [umKnowledge.ps.zip (2.5MB)]
[umKnowledgeBW.ps.gz (0.7MB)] [umKnowledgeBW.ps.zip
(0.7MB)]
- Dobson, M. C., F. T. Ulaby, and L. E. Pierce, Land-Cover
Classification and Estimation of Terrain Attributes Using Synthetic Aperture
Radar, Remote Sensing of Environment, Vol. 51, No. 1, pp. 199-214, Jan.
1995. [Abstract] [umClassEst.pdf]
- Dobson, M. C., L. E. Pierce, and F. T. Ulaby, Knowledge-Based
Land-Cover Classification Using ERS-1/JERS-1 SAR Composites, IEEE Trans.
Geoscience and Remote Sensing, Vol. 34, No. 1, pp. 83 - 99, Jan. 1996.
[Abstract] [umKnowlERS.pdf]
- Kasischke, E. S., J. M. Melack and M. C. Dobson, The
Use of Imaging Radars for Ecological Applications - A Review, Remote Sensing
of Environment, January 1996, accepted. [Abstract]
[umEcology.pdf]
- Pierce, Leland, Kathleen Bergen, M. Craig Dobson, Fawwaz
T. Ulaby, Multi-Temporal Land-Cover Classifiation using SIR-C/X-SAR Imagery,
Remote Sensing of Environment, in press. [Abstract]
[umMultitemp.pdf]
- Dobson, M. Craig, Leland E. Pierce, Fawwaz T. Ulaby,
Evaluation of SAR Sensor Configurations for Terrain Classification
and Forest Biophysical Retrievals, International Journal of Remote Sensing,
submitted 3-98. [Abstract] [umSensconfig.pdf]
The web address for this document is: http://www.eecs.umich.edu/RADLAB/sar_image_lab/classification.html
last update: 3-19-98
Any questions or comments should be directed to: Leland
Pierce <lep@eecs.umich.edu>
Radar Image Processing Lab
The University of Michigan - EECS Dept.
1301 Beal Ave
Ann Arbor, MI 48109-2122