Remote sensing of environment research has explored the benefits of using synthetic aperture radar imagery systems for a wide range of land and marine applications since these systems are not affected by weather conditions and therefore are operable both daytime and nighttime. The design of image processing techniques for  synthetic aperture radar applications requires tests and validation on real and synthetic images. The GRSS benchmark database supports the desing and analysis of algorithms to deal with SAR and PolSAR data.

Last Updated On: 
Tue, 11/12/2019 - 10:38
Citation Author(s): 
Nobre, R. H.; Rodrigues, F. A. A.; Rosa, R.; Medeiros, F.N.; Feitosa, R., Estevão, A.A., Barros, A.S.

This dataset contains multispectral high resolution 1627 image patches of size 10 x 10 pixels with each pixel size of 10mx10m. These patches are generated from the Sentinel-2 (A/B) satellite images acquired during the period of October 2018 to May 2019. It covered one life cycle (12 months) of the sugarcane crop in the region of the Karnataka, India. Many parameters like plantation season, soil type, plantation type, crop variety and irrigation type that affects the growth of the sugarcane crop are considered while generating the samples.

Categories:
60 Views

Presented here is a dataset used for our SCADA cybersecurity research. The dataset was built using our SCADA system testbed described in our paper below [*]. The purpose of our testbed was to emulate real-world industrial systems closely. It allowed us to carry out realistic cyber-attacks.

 

Instructions: 

Provided dataset is cleased, pre-processed, and ready to use. The users may modify as they wish, but please cite the dataset as below.

M. A. Teixeira, M. Zolanvari, R. Jain, "WUSTL-IIOT-2018 Dataset for ICS (SCADA) Cybersecurity Research," 2018. [Online]. Available: https://www.cse.wustl.edu/~jain/iiot/index.html.

Categories:
217 Views

The Dataset

We introduce a novel large-scale dataset for semi-supervised semantic segmentation in Earth Observation: the MiniFrance suite.

Instructions: 

##################################################

The MiniFrance Suite

##################################################

Authors:

Javiera Castillo Navarro, javiera.castillo_navarro@onera.fr

Bertrand Le Saux, bls@ieee.org

Alexandre Boulch, alexandre.boulch@valeo.com

Nicolas Audebert, nicolas.audebert@cnam.fr

Sébastien Lefèvre, sebastien.lefevre@irisa.fr

##################################################

About:

This dataset contains very high resolution RGB aerial images over 16 cities and their surroundings from different regions in France, obtained from IGN's BD ORTHO database (images from 2012 to 2014). Pixel-level land use and land cover annotations are provided, generated by rasterizing Urban Atlas 2012.

##################################################

This dataset is partitioned in three parts, defined by conurbations:

1. Labeled training data: data over Nice and Nantes/Saint Nazaire.

2. Unlabeled training data: data over Le Mans, Brest, Lorient, Caen, Calais/Dunkerque and Saint-Brieuc.

3. Test data: data over Marseille/Martigues, Rennes, Angers, Quimper, Vannes, Clermont-Ferrand, Cherbourg, Lille.

Due to the large-scale nature of the dataset, it is divided in several files to download:

- Images for the labeled training partition: contains RGB aerial images for french departments in the labeled training partition.

- Images for the unlabeled training partition (parts 1, 2 and 3): contain RGB aerial images for french departments in the unlabeled training partition.

- Images for the test partition (parts 1, 2, 3 and 4): contain RGB aerial images for french departments in the partition reserved for evaluation.

- Labels for the labeled partition

- Lists of files by conurbation and partition: contain .txt files that list all images included by city.

Land use maps are available for all images in the labeled training partition of the dataset. We consider here Urban Atlas classes at the second hierarchical level. Available classes are:

- 0: No information

- 1: Urban fabric

- 2: Industrial, commercial, public, military, private and transport units

- 3: Mine, dump and contruction sites

- 4: Artificial non-agricultural vegetated areas

- 5: Arable land (annual crops)

- 6: Permanent crops

- 7: Pastures

- 8: Complex and mixed cultivation patterns

- 9: Orchards at the fringe of urban classes

- 10: Forests

- 11: Herbaceous vegetation associations

- 12: Open spaces with little or no vegetation

- 13: Wetlands

- 14: Water

- 15: Clouds and shadows

##################################################

Citation: If you use this dataset for your work, please use the following citation:

@article{castillo2020minifrance,
title={{Semi-Supervised Semantic Segmentation in Earth Observation: The MiniFrance Suite, Dataset Analysis and Multi-task Network Study}},
author={Castillo-Navarro, Javiera and Audebert, Nicolas and Boulch, Alexandre and {Le Saux}, Bertrand and Lef{\`e}vre, S{\'e}bastien},
journal={Under review.},
year={2020}
}

##################################################

Copyright:

The images in this dataset are released under IGN's "licence ouverte". More information can be found at http://www.ign.fr/institut/activites/lign-lopen-data

The maps used to generate the labels in this dataset come from the Copernicus program, and as such are subject to the terms described here: https://land.copernicus.eu/local/urban-atlas/urban-atlas-2012?tab=metadata

Categories:
123 Views

This dataset was created from all Landsat-8 images from South America in the year 2018. More than 31 thousand images were processed (15 TB of data), and approximately on half of them active fire pixels were found. The Landsat-8 sensor has 30 meters of spatial resolution (1 panchromatic band of 15m), 16 bits of radiometric resolution and 16 days of temporal resolution (revisit). The images in our dataset are in TIFF (geotiff) format with 10 bands (excluding the 15m panchromatic band).

Instructions: 

The images in our dataset are in georeferenced TIFF (geotiff) format with 10 bands. We cropped the original Landsat-8 scenes (with ~7,600 x 7,600 pixels) into image patches with 128 x 128 pixels by using a stride overlap of 64 pixels (vertical and horizontal). The masks are in binary format where True (1) represents fire and False (0) represents background and they were generated from the conditions set by Schroeder et al. (2016). We used the Schroeder conditions to process each patch, producing over 1 million patches with at least one fire pixel and the same amount of patches with no fire pixels, randomly selected from the original images.

The dataset is organized as follow. 

It is divided into South American regions for easy downloading. For each region of South America we have a zip file for images of active fire, its masks, and non-fire images. For example:

 - Uruguay-fire.zip

 - Uruguay-mask.zip

 - Uruguay-nonfire.zip

Within each South American region zip files there are the corresponding zip files to each Landsat-8 WRS (Worldwide Reference System). For example:

- Uruguay-fire.zip;

      - 222083.zip

      - 222084.zip

      - 223082.zip

      - 223083.zip

      - 223084.zip

      - 224082.zip

      - 224083.zip

      - 224084.zip

      - 225081.zip

      - 225082.zip

      - 225083.zip

      - 225084.zip

Within each of these Landsat-8 WRS zip files there are all the corresponding 128x128 image patches for the year 2018. 

 

Categories:
315 Views

Level 2 data set. Averaging over multiple measurements were performed to reduce electronic noise and jitter

Instructions: 

%Program developed by Viviana Vladutescu for iROC alignment 3/30/2018

clc 

clear all

close all

fontSize=14;

 

load('Distances.mat')

 

% xlswrite('Distances.xlsx', Distances)

%Distances=[dist_STIF_av; dist_STIF_std; dist_PixSen_av; dist_PixSen_std; pi_pos_X_av; pi_pos_X_std; pi_pos_Y_av;... 

 %   pi_pos_Y_std; con_X_av; con_X_std; con_Y_av; con_Y_std; con2_X_av; con2_X_std; con2_Y_av; con2_Y_std];

 

 m=36;

 

dist_STIF_av=Distances(1,:);

 dist_STIF_std=Distances(2,:);

 dist_PixSen_av=Distances(3,:);

 dist_PixSen_std=Distances(4,:);

 pi_pos_X_av=Distances(5,:);

 pi_pos_X_std=Distances(6,:);

 pi_pos_Y_av=Distances(7,:);

 pi_pos_Y_std=Distances(8,:);

 con_X_av=Distances(9,:);

 con_X_std=Distances(10,:);

 con_Y_av=Distances(11,:);

 con_Y_std=Distances(12,:);

 con2_X_av=Distances(13,:);

 con2_X_std=Distances(14,:);

 con2_Y_av=Distances(15,:);

 con2_Y_std=Distances(16,:);

 

  col=find(dist_PixSen_av);

  figure(1)

 surface([dist_PixSen_av;dist_PixSen_av],[dist_STIF_av;dist_STIF_av],[col;col],...

         'facecol','no','edgecol','interp','linew',2);

     xlabel('DistPixSen', 'FontSize',fontSize)

   ylabel('DistSTIF','FontSize', fontSize)

   title('DistPixSen vs. DistSTIF','FontSize', fontSize)

   grid on

% surface([x;x],[y;y],[z;z],[col;col],...

%         'facecol','no',...

%         'edgecol','interp',...

%         'linew',2);

    

 figure(2)

 

 subplot(2,2,1)

   errorbar(dist_PixSen_av, dist_STIF_av,dist_STIF_std,'ro-')

   hold on

   surface([dist_PixSen_av;dist_PixSen_av],[dist_STIF_av;dist_STIF_av],[col;col],...

         'facecol','no','edgecol','interp','linew',2);

   xlabel('DistPixSen', 'FontSize',fontSize)

   ylabel('DistSTIF','FontSize', fontSize)

   title('DistPixSen vs. DistSTIF','FontSize', fontSize)

   legend('X')

   grid on

 

  

 subplot(2,2,2)

   errorbar(dist_PixSen_av,pi_pos_X_av,pi_pos_X_std,'k^-')

   hold on

   surface([dist_PixSen_av;dist_PixSen_av],[pi_pos_X_av;pi_pos_X_av],[col;col],...

         'facecol','no','edgecol','interp','linew',2);

%     hold on

%    plot(dist_PixSen_avcalc,pi_pos_X_av,'r:')

   xlabel('DistPixSen','FontSize', fontSize)

   ylabel('PiPosX','FontSize', fontSize)

   legend('X')

   title('DistPixSen vs. PiPosX','FontSize', fontSize)

   grid on

   

%    subplot(2,2,3)

%    errorbar(dist_PixSen_av,pi_pos_Y_av,pi_pos_Y_std,'b<:')

%    hold on

%    surface([dist_PixSen_av;dist_PixSen_av],[pi_pos_Y_av;pi_pos_Y_av],[col;col],...

%          'facecol','no','edgecol','interp','linew',2);

%    xlabel('DistPixSen','FontSize', fontSize)

%    ylabel('PiPosY','FontSize', fontSize)

%    legend('X','FontSize', fontSize)

%    title('DistPixSen vs. PiPosY','FontSize', fontSize)

%    grid on

   

   subplot(2,2,3)

   errorbar(dist_PixSen_av,con_X_av,con_X_std,'m>-')

   hold on 

   surface([dist_PixSen_av;dist_PixSen_av],[con_X_av;con_X_av],[col;col],...

         'facecol','no','edgecol','interp','linew',2);

   xlabel('DistPixSen','FontSize', fontSize)

   ylabel('Con1PosX','FontSize', fontSize)

   legend('X')

   title('DistPixSen vs. Con1X','FontSize', fontSize)

   grid on

   

%    subplot(2,4,5)

%    errorbar(dist_PixSen_av,con_Y_av,con_Y_std,'gx-')

%    hold on

%    surface([dist_PixSen_av;dist_PixSen_av],[con_Y_av;con_Y_av],[col;col],...

%          'facecol','no','edgecol','interp','linew',2);

% %     hold on

% %    plot(dist_PixSen_avcalc,con_Y_av,'r:')

%    xlabel('DistPixSen','FontSize', fontSize)

%    ylabel('Con1PosY','FontSize', fontSize)

%    legend('Y','FontSize', fontSize)

%    title('DistPixSen vs. Con1Y','FontSize', fontSize)

%    grid on

%    

 subplot(2,2,4)

   errorbar(dist_PixSen_av,con2_X_av,con2_X_std,'cv-.')

   hold on 

   surface([dist_PixSen_av;dist_PixSen_av],[con2_X_av;con2_X_av],[col;col],...

         'facecol','no','edgecol','interp','linew',2);

   %     hold on

   %    plot(dist_PixSen_avcalc,pi_pos_X_av,'r:')

   xlabel('DistPixSen','FontSize', fontSize)

   ylabel('Con2PosX','FontSize', fontSize)

   legend('X')

   title('DistPixSen vs. Con2X','FontSize', fontSize)

   grid on

%     subplot(2,4,7)

%    errorbar(dist_PixSen_av,con2_Y_av,con2_Y_std,'kp-')

%    hold on

%    surface([dist_PixSen_av;dist_PixSen_av],[con2_Y_av;con2_Y_av],[col;col],...

%          'facecol','no','edgecol','interp','linew',2);

% %    hold on

% %    plot(dist_PixSen_avcalc,con2_Y_av,'r:')

%    xlabel('DistPixSen','FontSize', fontSize)

%    ylabel('Con2PosY','FontSize', fontSize)

%    legend('Y','FontSize', fontSize)

%    title('DistPixSen vs. Con2Y','FontSize', fontSize)

%    grid on

  

   figure(3)

   

   subplot(2,2,1)

   errorbar(dist_STIF_av,dist_PixSen_av,dist_PixSen_std,'ro-')

   hold on

   surface([dist_STIF_av;dist_STIF_av],[dist_PixSen_av;dist_PixSen_av],[col;col],...

         'facecol','no','edgecol','interp','linew',2);

%     hold on

%    plot(dist_STIF_avcalc,dist_PixSen_avcalc,'r:')

   xlabel('DistSTIF', 'FontSize',fontSize)

   ylabel('DistPixSens','FontSize', fontSize)

   title('DistSTIF vs. DistPixSens','FontSize', fontSize)

      legend('DistSTIF')

   hold on

    grid on

   

    subplot(2,2,2)

   errorbar(dist_STIF_av,pi_pos_X_av,pi_pos_X_std,'k^-')

   surface([dist_STIF_av;dist_STIF_av],[pi_pos_X_av;pi_pos_X_av],[col;col],...

         'facecol','no','edgecol','interp','linew',2);

%     hold on

%    plot(dist_STIF_avcalc,pi_pos_X_av,'r:')

   xlabel('DistSTIF','FontSize', fontSize)

   ylabel('PiPosX','FontSize', fontSize)

   legend('PiPosX')

   title('DistSTIF vs. PiPosX','FontSize', fontSize)

   grid on

  

%    subplot(2,2,3)

%    errorbar(dist_STIF_av,pi_pos_Y_av,pi_pos_Y_std,'b<:')

%    surface([dist_STIF_av;dist_STIF_av],[pi_pos_Y_av;pi_pos_Y_av],[col;col],...

%          'facecol','no','edgecol','interp','linew',2);

% %    hold on

% %     plot(dist_STIF_avcalc,pi_pos_Y_av,'r:')

%    xlabel('DistSTIF','FontSize', fontSize)

%    ylabel('PiPosY','FontSize', fontSize)

%    legend('PiPosY')

%    title('DistSTIF vs. PiPosY','FontSize', fontSize)

%    grid on

   subplot(2,2,3)

   errorbar(dist_STIF_av,con_X_av,con_X_std,'m>-')

   hold on 

   surface([dist_STIF_av;dist_STIF_av],[con_X_av;con_X_av],[col;col],...

         'facecol','no','edgecol','interp','linew',2);

%     hold on

%    plot(dist_STIF_avcalc,con_X_av,'r:')

   xlabel('DistSTIF','FontSize', fontSize)

   ylabel('Con1PosX','FontSize', fontSize)

   legend('Con1PosX')

   title('DistPixSen vs. Con1X','FontSize', fontSize)

   grid on

%    subplot(2,4,5)

%    errorbar(dist_STIF_av,con_Y_av,con_Y_std,'gx-')

%    hold on

%    surface([dist_STIF_av;dist_STIF_av],[con_Y_av;con_Y_av],[col;col],...

%          'facecol','no','edgecol','interp','linew',2);

% %    hold on

% %    plot(dist_STIF_avcalc,con_Y_av,'r:')

%    xlabel('DistSTIF','FontSize', fontSize)

%    ylabel('Con1PosY','FontSize', fontSize)

%    legend('Y','FontSize', fontSize)

%    title('DistSTIF vs. Con1Y','FontSize', fontSize)

%    grid on

    

subplot(2,2,4)

   errorbar(dist_STIF_av,con2_X_av,con2_X_std,'cv-.')

   hold on

   surface([dist_STIF_av;dist_STIF_av],[con2_X_av;con2_X_av],[col;col],...

         'facecol','no','edgecol','interp','linew',2);

%    hold on

%    plot(dist_STIF_avcalc,con2_X_av,'r:')

   xlabel('DistSTIF','FontSize', fontSize)

   ylabel('Con2PosX','FontSize', fontSize)

   legend('Con2PosX')

   title('DistSTIF vs. Con2X','FontSize', fontSize)

   grid on

   %     subplot(2,4,7)

%    errorbar(dist_STIF_av,con2_Y_av,con2_Y_std,'kp-')

%    surface([dist_STIF_av;dist_STIF_av],[con2_Y_av;con2_Y_av],[col;col],...

%          'facecol','no','edgecol','interp','linew',2);

% %     hold on

% %    plot(dist_STIF_avcalc,con2_Y_av,'r:')

%    xlabel('DistSTIF','FontSize', fontSize)

%    ylabel('Con2PosY','FontSize', fontSize)

%    legend('Y','FontSize', fontSize)

%    title('DistSTIF vs. Con2Y','FontSize', fontSize)

%    grid on\

   figure (4)

   

   subplot(2,1,1) 

   

   rel_err_DSTIF_DPix=((dist_STIF_av-dist_PixSen_av)./dist_STIF_av).*100;

    surface([dist_STIF_av;dist_STIF_av],[rel_err_DSTIF_DPix;rel_err_DSTIF_DPix],...

       [col;col],'facecol','no','edgecol','interp','lines',':','linew',2);

   hold on

   plot(dist_STIF_av,rel_err_DSTIF_DPix,'cv-.')

   xlabel('DistSTIF','FontSize', fontSize)

   ylabel('Relative Error','FontSize', fontSize)

   title('Relative error ','FontSize', fontSize)

%  legend('Rel Error','Fit to Rel Error')

   legend('Relative Error DistSTIF DistPixSens')

    grid on

    

   subplot(2,1,2)  

  rel_err_DPix_DSTIF=((dist_PixSen_av-dist_STIF_av)./dist_PixSen_av).*100;

  surface([dist_PixSen_av;dist_PixSen_av],[rel_err_DPix_DSTIF;rel_err_DPix_DSTIF],...

       [col;col],'facecol','no','edgecol','interp','lines',':','linew',2);

   hold on

   plot(dist_PixSen_av, rel_err_DPix_DSTIF,'cv-.')   

   xlabel('DistPixSen','FontSize', fontSize)

   ylabel('Relative Error','FontSize', fontSize)

   title('Relative error','FontSize', fontSize)

%  legend('Rel Error','Fit to Rel Error')

   legend('Relative Error DistPixSens DistSTIF')

    grid on

 

   

   figure(5)

   

  rel_err_con1X_2X=((con_X_av-con2_X_av)./con_X_av).*100;

    

  surface([dist_STIF_av;dist_STIF_av],[rel_err_con1X_2X;rel_err_con1X_2X],...

       [col;col],'facecol','no','edgecol','interp','lines',':','linew',2);

  hold on

   plot(dist_STIF_av,rel_err_con1X_2X,'cv-.')

   xlabel('DistSTIF','FontSize', fontSize)

   ylabel('Relative Error','FontSize', fontSize)

   title('Relative error','FontSize', fontSize)

%  legend('Rel Error','Fit to Rel Error')

   legend('Relative Error Con1X to Con2X')

    grid on

    

    

 figure(6)

 

  subplot(2,1,1)

   %semilogy(dist_PixSen_av, dist_STIF_av,'ro-',dist_PixSen_av,pi_pos_X_av,'k^-',dist_PixSen_av,pi_pos_Y_av,'b<:',dist_PixSen_av,con_X_av,'m>-',dist_PixSen_av,con_Y_av,'gx-',dist_PixSen_av,con2_X_av,'cv-.',dist_PixSen_av,con2_Y_av,'kp-')

    semilogy(dist_PixSen_av, dist_STIF_av,'ro-',dist_PixSen_av,pi_pos_X_av,'k^-',dist_PixSen_av,con_X_av,'m>-',dist_PixSen_av,con2_X_av,'cv-.')

   xlabel('DistPixSen','FontSize', fontSize)

   ylabel('Instrument position','FontSize', fontSize)

  % legend('DistSTIF','PiPosX','PiPosY','Con1X','Con1Y','Con2X','Con2Y','FontSize', fontSize)

    legend('DistSTIF','PiPosX','Con1X','Con2X','FontSize', fontSize)

   title('All Instrum.Pos. vs. DistPixSens','FontSize', fontSize)   

   grid on

%    plot(dist_PixSen_av,con_Y_av)

%    title('DistPixSen vs. Con1Y','Fontsize',fontSize)

   subplot(2,1,2)

   %semilogy(dist_STIF_av,dist_PixSen_av,'ro-',dist_STIF_av,pi_pos_X_av,'k^-',dist_STIF_av,pi_pos_Y_av,'b<:',dist_STIF_av,con_X_av,'m>-',dist_STIF_av,con_Y_av,'gx-',dist_STIF_av,con2_X_av,'cv-.',dist_STIF_av,con2_Y_av,'kp-')

   semilogy(dist_STIF_av,dist_PixSen_av,'ro-',dist_STIF_av,pi_pos_X_av,'k^-',dist_STIF_av,con_X_av,'m>-',dist_STIF_av,con2_X_av,'cv-.')

   xlabel('DistSTIF','FontSize', fontSize)

   ylabel('Instrument Position','FontSize', fontSize)

   legend('DistPixSens','PiPosX','PiPosY','Con1X','Con2X','FontSize', fontSize)

   legend('DistPixSens','PiPosX','Con1X','Con2X','FontSize', fontSize)

   title('DistSTIF vs. All Instrum Positions','FontSize', fontSize)   

   grid on

   

   figure(7)

   subplot(2,1,1)

   errorbar(pi_pos_X_av,con_X_av,con_X_std,'g+-')

   hold on 

   surface([pi_pos_X_av;pi_pos_X_av],[con_X_av;con_X_av],[col;col],...

         'facecol','no','edgecol','interp','linew',2);

%     hold on

%    plot(pi_pos_X_av,con_X_av,'r:')

   xlabel('PiPosX','FontSize', fontSize)

   ylabel('Con1PosX','FontSize', fontSize)

   legend('X-X')

   title('PiPosX vs. Con1PosX','FontSize', fontSize)

   axis tight

   grid on

   

%    subplot(2,2,2)

%    errorbar(pi_pos_Y_av,con_Y_av,con_Y_std,'kh-')

%    hold on 

%    surface([pi_pos_Y_av;pi_pos_Y_av],[con_Y_av;con_Y_av],[col;col],...

%          'facecol','no','edgecol','interp','linew',2);

%    xlabel('PiPosY','FontSize', fontSize)

%    ylabel('Con1PosY','FontSize', fontSize)

%    legend('Y-Y','FontSize', fontSize)

%    title('PiPosY vs. Con1PosY','FontSize', fontSize)

%    axis tight

%    grid on

   

   subplot(2,1,2)

   errorbar(pi_pos_X_av,con2_X_av,con2_X_std,'g+-')

   hold on 

   surface([pi_pos_X_av;pi_pos_X_av],[con2_X_av;con2_X_av],[col;col],...

         'facecol','no','edgecol','interp','linew',2);

%      hold on

%    plot(pi_pos_X_av,con2_X_avcalc,'r:')

   xlabel('PiPosX','FontSize', fontSize)

   ylabel('Con2PosX','FontSize', fontSize)

   legend('X-X')%,'FontSize', fontSize)

   title('PiPosX vs. Con2PosX','FontSize', fontSize)

   axis tight

   grid on

     

%    subplot(2,2,4)

%    errorbar(pi_pos_Y_av,con2_Y_av,con2_Y_std','b^:')

%    hold on 

%    surface([pi_pos_Y_av;pi_pos_Y_av],[con2_Y_av;con2_Y_av],[col;col],...

%          'facecol','no','edgecol','interp','linew',2);

%    xlabel('PiPosY','FontSize', fontSize)

%    ylabel('Con2PosY','FontSize', fontSize)

%    legend('Y-Y')%,'FontSize', fontSize)

%    title('PiPosY vs. Con2PosY','FontSize', fontSize)

%    grid on

   axis tight

   

  

   %mean of stds

   PiXstdMean=nanmean(pi_pos_X_std);

   PiYstdMean=nanmean(pi_pos_Y_std);

   ConXstdMean=nanmean(con_X_std); 

   ConYstdMean=nanmean(con_Y_std);

   Con2XstdMean=nanmean(con2_X_std);

   Con2YstdMean=nanmean(con2_Y_std);

   DistPixSenstdMean=nanmean(dist_PixSen_std);

   DistSTIFstdMean=nanmean(dist_STIF_std);

   

   figure(8)

   

  % plot(1:36,pi_pos_X_std,'k^-',1:36,pi_pos_Y_std,'b<:',1:36,con_X_std,'m>-',1:36,con_Y_std,'kh-',1:36,con2_X_std,'g+-',1:36,con2_Y_std,'kp-',1:36,dist_STIF_std,'ro-',1:36,dist_PixSen_std,'r:')

      plot(1:36,pi_pos_X_std,'k^-',1:36,pi_pos_Y_std,'b<:',1:36,con_X_std,'m>-',1:36,con2_X_std,'g+-',1:36,dist_STIF_std,'ro-',1:36,dist_PixSen_std,'r:')

   xlabel('Step','FontSize', fontSize)

   ylabel('STD','FontSize', fontSize)

%    legend('PiPosX','PiPosY','Con1X','Con1Y','Con2X','Con2Y','DistSTIF','DistPixSen','FontSize', fontSize)

   legend('PiPosX','PiPosY','Con1X','Con2X','DistSTIF','DistPixSen','FontSize', fontSize)

   title('STD','FontSize', fontSize)

   grid on

   axis tight

%    text(15,0.7,{'Mean STDs', 'PiXstdMean=', num2str(PiXstdMean), 'PiYstdMean=', num2str(PiYstdMean),...

%                'Con1XstdMean', num2str(ConXstdMean),'Con1YstdMean', num2str(ConYstdMean),...

%                'Con2XstdMean',num2str(Con2XstdMean),'Con2YstdMean', num2str(Con2YstdMean),...

%                'DistSTIFstdMean', num2str(DistSTIFstdMean),'DistPixSenstdMean', num2str(DistPixSenstdMean),},...

%                'Color','black','FontSize',10)

   text(15,0.7,{'Mean STDs', 'PiXstdMean=', num2str(PiXstdMean), 'PiYstdMean=', num2str(PiYstdMean),... 

       'Con1XstdMean', num2str(ConXstdMean),'Con2XstdMean',num2str(Con2XstdMean),...

       'DistSTIFstdMean', num2str(DistSTIFstdMean),...

       'DistPixSenstdMean', num2str(DistPixSenstdMean),},'Color','black','FontSize',10)

          

%  z1=find(dist_PixSen_av<38);

 z2=find(dist_PixSen_av>20);

 

 

f2= fit(dist_PixSen_av(z2)',dist_STIF_av(z2)','poly2')

fit_f2=0.0005418.*((dist_PixSen_av(z2)').^2)-0.3428.*dist_PixSen_av(z2)'+342.6;

 

rms2=rms(dist_STIF_av(z2)'-fit_f2)

[r2,pval2]=corr(dist_PixSen_av(z2)',dist_STIF_av(z2)')

mdl2=fitlm(dist_PixSen_av(z2)',dist_STIF_av(z2)')

tbl2=anova(mdl2)

 

% corrected_DistSTIF2=dist_STIF_av(z2)'.\fit_f2;

% rel_err2=abs(corrected_DistSTIF2-1); %(relative error=|Theory-Meas|/Theory)

rel_err2=abs(dist_STIF_av(z2)'-fit_f2)./fit_f2;

f_rel_err2= fit(dist_PixSen_av(z2)', rel_err2,'poly2');

fit_rel_err2=(-1.232*10^(-7)).*((dist_PixSen_av(z2)').^2)+(2.488*10^(-5)).*dist_PixSen_av(z2)'+0.0002836; % coefficients from f_rel_err_PiPosX_PixSen

mean_rel_err2=mean(rel_err2)

 

col1=find(dist_PixSen_av(z2))

 

figure(9)

 

  subplot(2,1,1)

     surface([dist_PixSen_av(z2);dist_PixSen_av(z2)],[dist_STIF_av(z2);dist_STIF_av(z2)],[col1;col1],...

         'facecol','no','edgecol','interp','lines',':','linew',2);

     hold on 

    plot(f2,dist_PixSen_av(z2),dist_STIF_av(z2),'bd')%,dist_PixSen_av(z),FitSTIF,'^k')

      

    xlabel('DistPixSen','FontSize', fontSize)

    ylabel('DistSTIF','FontSize', fontSize)

    title('Distance and Fitting Lines to distances between beams on STIF relative to PixSen','FontSize', fontSize)

    legend('DistSTIF','DistSTIF','Fit')

    grid on

 

 subplot(2,1,2)

  surface([dist_STIF_av(z2);dist_STIF_av(z2)],[rel_err2';rel_err2'],[col1;col1],...

         'facecol','no','edgecol','interp','lines',':','linew',2);

     hold on

    plot(dist_STIF_av(z2), rel_err2','r*',dist_STIF_av(z2), fit_rel_err2','r-')

    xlabel('DistSTIF','FontSize', fontSize)

    ylabel('Relative Error','FontSize', fontSize)

    title('Relative error of fit of distance on STIF relative to PixSen','FontSize', fontSize)

    legend('Relative Error','Relative Error','Fit')

    grid on

 

% repeat the fit for pix sensor (as y) and pi_pos_X_av with fit_f from pix sens

 

f2_PiPosX_PixSen= fit(dist_PixSen_av(z2)',pi_pos_X_av(z2)','poly2')

fit_f2_PiPosX_PixSen=0.009709.*((dist_PixSen_av(z2)').^2)-12.84.*dist_PixSen_av(z2)'+2333

 rms2_PiPosX_PixSen_Fit2=rms(pi_pos_X_av(z2)'-fit_f2_PiPosX_PixSen)

 

 rel_err_PiPosX_PixSen=abs(pi_pos_X_av(z2)'-fit_f2_PiPosX_PixSen)./fit_f2_PiPosX_PixSen;

 mean_rel_err_PiPosX_PixSen=mean( rel_err_PiPosX_PixSen);

 

 f_rel_err_PiPosX_PixSen= fit(dist_PixSen_av(z2)', rel_err_PiPosX_PixSen,'poly2');

 fit_rel_err_PiPosX_PixSen=(3.062*10^(-7)).*((dist_PixSen_av(z2)').^2)+(7.746*10^(-7)).*dist_PixSen_av(z2)'+0.008499; % coefficients from f_rel_err_PiPosX_PixSen

% corrected_PixSen_PiPosX=dist_PixSen_av(z2)'.\fit_f2_PixSen_PiPosX;

% rel_err_PixSen_PiPosX=abs(corrected_PixSen_PiPosX-1); %(relative error=|Theory-Meas|/Theory)

 

 

 figure(10)

 

 subplot(2,1,1)

    surface([dist_PixSen_av(z2);dist_PixSen_av(z2)],[pi_pos_X_av(z2);pi_pos_X_av(z2)],[col1;col1],...

         'facecol','no','edgecol','interp','lines',':','linew',2);

    hold on

     plot(f2_PiPosX_PixSen,dist_PixSen_av(z2),pi_pos_X_av(z2),'bd')%,dist_PixSen_av(z),FitSTIF,'^k')

 

    xlabel('DistPixSen','FontSize', fontSize)

    ylabel('PiPosX','FontSize', fontSize)

    title('Distance and Fitting Lines to distances between beams on PixSen relative to PiPosX','FontSize', fontSize)

    legend('PiPosX','PiPosX','Fit')

    grid on

    

  subplot(2,1,2)

      surface([dist_PixSen_av(z2);dist_PixSen_av(z2)],[rel_err_PiPosX_PixSen';rel_err_PiPosX_PixSen'],...

       [col1;col1],'facecol','no','edgecol','interp','lines',':','linew',2);

     hold on 

     plot(dist_PixSen_av(z2),rel_err_PiPosX_PixSen','b^',dist_PixSen_av(z2), fit_rel_err_PiPosX_PixSen','b-')

      xlabel('DistPixSen','FontSize', fontSize)

    ylabel('Relative Error','FontSize', fontSize)

    title('Relative error of fit of distance on PixSen relative to PiPosX','FontSize', fontSize)

    %     legend('Rel Error','Fit to Rel Error')

   legend('Relative Error','Relative Error','Fit')

   grid on

 

Categories:
22 Views

This dataset includes the following data in supporting the submitted manuscript 'Datacube Parametrization-Based Model for Rough Surface Polarimetric Bistatic Scattering' to IEEE Transactions on Geoscience and Remote Sensing. 

  • LUT of coefficient c from fitting the contour level bounds
  • LUT of coefficient c from fitting the contour center shifts
  • specular scattering coefficients from the SEBCM simulated datacube
Categories:
24 Views

Modern science is build on systematic experimentation and observation.  The reproducibility and replicability of  the experiments and observations are central to science. However, reproducibility and replicability are not always guaranteed, sometimes referred to as 'crisis of reproducibility'. To analyze the extent of the crisis, we conducted a survey on the state of reproducibility in remote sensing. This survey was conducted as an online survey. The answers of the respondents are saved in this dataset in full-text CSV format.

Instructions: 

The file contains the answers to our online survey on reproducibility in remote sensing. The format is as comma-separated values (CSV) in full-text, i.e. the answers are saved in the full-text instead of numbers, allowing to easily understand and analyse.

 

The dataset also includes the report given from the website the survey was hosted on (kwiksurveys.com). This can be used for a quick overview of the results, but also to see the original quesetions and the possible answers. 

Categories:
106 Views

Synthetic Aperture Radar (SAR) images can be extensively informative owing to their resolution and availability. However, the removal of speckle-noise from these requires several pre-processing steps. In recent years, deep learning-based techniques have brought significant improvement in the domain of denoising and image restoration. However, further research has been hampered by the lack of availability of data suitable for training deep neural network-based systems. With this paper, we propose a standard synthetic data set for the training of speckle reduction algorithms.

Instructions: 

In Virtual SAR we have infused images with varying level of noise, which helps in improving the accuray fo blind denoising task. The holdout set can be created using images from USC SIPI Aerials database and the the provided matlab script (preprocess_holdout.m) tested on Matlab R2019b.

 

The usage for research purposes is for free. If you use this dataset, please cite the following paper along with the dataset: Virtual SAR: A Synthetic Dataset for Deep Learning based Speckle Noise Reduction Algorithms

Categories:
350 Views

Pages