Entropy-Alpha Classification Alternative for Polarimetric SAR Image

Details Entropy-Alpha Classification Alternative for Polarimetric SAR Image Entropy-Alpha Classification Alternative for Polarimetric SAR Image

Apr 2003

adsabs.harvard.edu/cgi-bin/nph-data_query?bibcode=2003esasp.529e..46p&link_type=abstract

Proceedings of the Workshop on POLinSAR - Applications of SAR Polarimetry and Polarimetric Interferometry (ESA SP-529). 14-16 Ja

Statistics

Applications

Scientific paper

In this work we discuss SAR target entropy and alpha angle relations to other scattering covariance matrix characteristics and similarity invariants. It is shown that the sum of squared elements of the coherency matrix, normalized by its trace and determinant, has many common features with target entropy parameter. The first element of the matrix is very similar to alpha angle parameter describing scattering mechanism. Possibilities to use the sum of squared elements, determinant and first element of normalized coherency matrix for classification are studied. It appears that classification schemes very similar to entropy-alpha can be established. However, classification results differ slightly from those of entropy-alpha classification as here discussed two-parameter classifications depend on three variables, although parameters are in all cases the same. As an example, NASA/JPL AIRSAR L-Band image of the San Francisco Bay was classified with both proposed schemes and original entropy-alpha classification. The size of the used image was 224 x 256 pixels. The new algorithms classified 97% and 96%, respectively, of pixels to the same classes as entropy-alpha classification. The discussed similarity invariants are straightforward to calculate and they have been used to describe covariance matrix properties in statistics. Virtually are proposed classification algorithms equivalent with entropy-alpha classification because all three use the same amount of information from covariance matrix. However, proposed parameter pairs are much easier to calculate, as they do not require the computation of eigenvalues and eigenvectors.

Affiliated with

Also associated with

No associations

Rating

Entropy-Alpha Classification Alternative for Polarimetric SAR Image does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Entropy-Alpha Classification Alternative for Polarimetric SAR Image, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Entropy-Alpha Classification Alternative for Polarimetric SAR Image will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-846797