272017-10-05 14:33:08Jaarac262017-10-05 14:32:00Jaarac252017-10-05 13:04:41Jaarac242017-10-04 14:34:12Jaarac232017-10-04 14:27:36Jaarac222017-07-18 19:24:28Jaarac212017-07-18 15:00:14Jaarac202017-07-18 14:56:27Jaarac192017-07-17 15:09:00Jaarac182017-07-17 15:08:07Jaarac172017-07-17 14:18:10Jaarac162017-07-17 14:01:34Jaarac152017-07-17 13:58:45Jaarac142017-07-17 13:52:38Jaarac132017-07-15 14:33:12Jaarac122017-07-15 14:32:03Jaarac112017-07-15 14:24:19Jaarac102017-07-15 14:18:07Jaarac92017-07-15 14:13:50Jaarac82017-07-12 19:54:32Jaarac72017-03-30 12:46:47Jaarac62017-03-30 12:46:30Jaarac52016-10-27 10:36:15Jaarac42016-09-13 12:18:53Jaarac32016-09-13 12:18:35Jaarac22016-09-13 12:17:35Jaarac12016-08-17 18:45:00Jaarac

In this letter we study the application of the Fisher Vector (FV) to the problem of pixel-wise supervised classification of PolSAR images. This is a challenging problem since information in those images is encoded as complex-valued covariance matrices. We observe that the real part of these matrices preserve the positive semidefiniteness property of their complex counterpart. Based on this observation, we derive a FV from a mixture of real Wishart pdfs and integrate it with a Potts-like energy model in order to capture spatial dependencies between neighboring regions. Experimental results on two challenging datasets show the effectiveness of the approach.

Javier Redolfi, Jorge Sánchez, and Ana Georgina Flesia "Fisher Vectors for PolSAR Image Classification" IEEE Geoscience and Remote Sensing Letters, 99, Septiembre 2017. (link)

sartb.tar.gz How to install.

For evaluation, we consider a subset of the images that were available trough PolSARpro by the European Space Agency (ESA). This subset consists of two fully polarimetric images over the San Francisco Bay (SFB) area, USA, and over an agricultural region in the Flevoland (FL) province in The Netherlands. dataset

Pseudocolor representation of the polarimetric data (left) and the ground truth labels (right). sfb.png

Pseudocolor representation of the polarimetric data (left) and the ground truth labels (right). flev.png

Dataset CWC RWM ($K$=32, $n$=3) Ours ($K$=16, $n$=5) SFB 0.8848 (0.0602) 0.9081 (0.0238) 0.9707 (0.0079) FL 0.8762 (0.0223) 0.8608 (0.0312) 0.9144 (0.0191)

sfb_segmentation.png fl_segmentation.png

Method BareSoil Beet Forest Grasses Lucerne Peas Potatoes Rapeseed Beans Water Wheat Mean Wang etal. [1] 0.9878 0.9371 0.9496 0.8489 0.9231 0.9555 0.8896 0.9486 0.9653 0.9642 0.8864 0.9324 Ours ($K=16, n=5$) 1.0 0.9926 0.9770 0.9920 0.9261 0.9993 0.9959 0.9983 0.9757 0.8472 0.9971 0.9728

Method Accuracy W-DSN [2] 0.9268 (-) Ours ($K$=16, $n$=5) 0.9688 (0.0062)

[1] H. Wang, Z. Zhou, J. Turnbull, Q. Song, and F. Qi, “Pol-SAR classification based on generalized polar decomposition of mueller matrix,” IEEE Geosc. Remote Sens. Lett., vol. 13, no. 4, pp. 565–569, 2016. [2] L. Jiao and F. Liu, “Wishart deep stacking network for fast polsar image classification,” IEEE Trans. Image Process., vol. 25, no. 7, pp. 3273–3286, 2016.