Space Apps Challenge 2018

Lunar Village People (LVP) | Mission to the Moon!

Buenos Aires

Updates

Project

Members

Team Updates

Our looks for the regale at the USA Embassy, so cute!! :D

Romina Gabriela Hakl

Yesterday at the USA Embassy on Argentina, chatting with NASA´s argentinian Engineer Eugenia De Marco, What an honor! We thank very much to USA Embassy for this lovely evening.

Romina Gabriela Hakl

It´s been and intense week full of work energic group, and we are almost there!!! :D Go LVP!!!

Romina Gabriela Hakl

Lunar Village Pepole winners of Best Use of Hardware!!

Mercedes Agostinelli

Comparison of the results of the Matlab application and the identification of lava tubes.

Hernan M. R. Giannetta

Result of the Matlab Script App output and identification of the the lava tubes

Hernan M. R. Giannetta

qm-lroc-1540099157713.png (VIS- file used in the App to identify the lava tubes)

Hernan M. R. Giannetta

qm-lroc-1540099077964.png (IR file used in the App to identify the lava tubes)

Hernan M. R. Giannetta

  
          function [BW,maskedRGBImage] = createMask(RGB)
        
          %createMask  Threshold RGB image using auto-generated code from colorThresholder app.
        
          %  [BW,MASKEDRGBIMAGE] = createMask(RGB) thresholds image RGB using
        
          %  auto-generated code from the colorThresholder App. The colorspace and
        
          %  minimum/maximum values for each channel of the colorspace were set in the
        
          %  App and result in a binary mask BW and a composite image maskedRGBImage,
        
          %  which shows the original RGB image values under the mask BW.
        
          % Auto-generated by colorThresholder app on 22-Oct-2018
        
          %------------------------------------------------------
        
          % Convert RGB image to chosen color space
        
          RGB = im2double(RGB);
        
          cform = makecform('srgb2lab', 'AdaptedWhitePoint', whitepoint('D65'));
        
          I = applycform(RGB,cform);
        
          % Define thresholds for channel 1 based on histogram settings
        
          channel1Min = 47.714;
        
          channel1Max = 94.428;
        
          % Define thresholds for channel 2 based on histogram settings
        
          channel2Min = -35.728;
        
          channel2Max = -29.696;
        
          % Define thresholds for channel 3 based on histogram settings
        
          channel3Min = 13.372;
        
          channel3Max = 39.345;
        
          % Create mask based on chosen histogram thresholds
        
          BW = (I(:,:,1) >= channel1Min ) & (I(:,:,1) <= channel1Max) & ...
        
              (I(:,:,2) >= channel2Min ) & (I(:,:,2) <= channel2Max) & ...
        
              (I(:,:,3) >= channel3Min ) & (I(:,:,3) <= channel3Max);
        
          % Invert mask
        
          BW = ~BW;
        
          % Initialize output masked image based on input image.
        
          maskedRGBImage = RGB;
        
          % Set background pixels where BW is false to zero.
        
          maskedRGBImage(repmat(~BW,[1 1 3])) = 0;

view raw createMask.m hosted with ❤ by GitHub

  
          %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
        
          %
        
          % Matlab script 
        
          %
        
          % SpaceApp2018
        
          %
        
          % By: Hernan Giannetta (PhD)
        
          %
        
          % hgiannetta@frba.utn.edu.ar
        
          %
        
          % October 20-21, 2018
        
          %
        
          %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
        
          % Init
        
          clc;
        
          clear all;
        
          close all;
        
          % Local Variables
        
          ImageIRName =  'qm-lroc-1540099077964.png';
        
          ImageVISName =  'qm-lroc-1540099157713.png';
        
          outputfolderName='output';
        
          Image_Ori='Image_Ori';
        
          Image_VIS_original_filename='Image_VIS_original';
        
          Image_VIS_segmented_filename='Image_VIS_segmented';
        
          %------------------
        
          % Main
        
          %------------------
        
          %------------------
        
          % VIS Image
        
          %------------------
        
          ImageVISarray = imread(ImageVISName);
        
          % Image selection to analize
        
          I=ImageVISarray;
        
          figure, imshow(I), title('original image');
        
          % %I = imread('coins.png');
        
          % level = graythresh(I);
        
          % BW = im2bw(I,level);
        
          % figure,imshow(BW)
        
          %binarize
        
          I_Proc=segmentImage(I);
        
          BW = im2bw(I_Proc);
        
          figure; imshow(BW), title('segmentImage');
        
          % erode
        
          %SE1 = strel('arbitrary',eye(20))
        
          SE1 = strel('disk',2);
        
          BW1 = imerode(BW,SE1);
        
          figure; imshow(BW1), title('erode');
        
          % dilate image 
        
          SE2 = strel('disk',7);
        
          BW2 = imdilate(BW1,SE2);
        
          figure; imshow(BW2), title('imdilate');
        
          %edge detection
        
          [~, threshold] = edge(BW2, 'sobel');
        
          fudgeFactor = .5;
        
          BWs = edge(BW2,'sobel', threshold * fudgeFactor);
        
          figure, imshow(BWs), title('binary gradient mask');
        
          %dilate 
        
          se90 = strel('line', 3, 90);
        
          se0 = strel('line', 3, 0);
        
          BWsdil = imdilate(BWs, [se90 se0]);
        
          figure, imshow(BWsdil), title('dilated gradient mask');
        
          %Fill Interior Gaps
        
          BWdfill = imfill(BWsdil, 'holes');
        
          figure, imshow(BWdfill);
        
          title('binary image with filled holes');
        
          %Remove Connected Objects on Border
        
          BWnobord = imclearborder(BWdfill, 4);
        
          figure, imshow(BWnobord), title('cleared border image');
        
          %Smoothen the Object
        
          seD = strel('diamond',1);
        
          BWfinal = imerode(BWnobord,seD);
        
          BWfinal = imerode(BWfinal,seD);
        
          figure, imshow(BWfinal), title('segmented image');
        
          % erode image 
        
          SE1 = strel('disk',2);
        
          BWfinal2 = imerode(BWfinal,SE1);
        
          figure; imshow(BWfinal2), title('erode');
        
          % dilate image 
        
          SE2 = strel('disk',15);
        
          BWfinal3 = imdilate(BWfinal2,SE2);
        
          figure; imshow(BWfinal3), title('imdilate');
        
          %Smoothen2 the Object
        
          seD = strel('diamond',1);
        
          BWfinal = imerode(BWfinal3,seD);
        
          BWfinal = imerode(BWfinal,seD);
        
          figure, imshow(BWfinal), title('segmented image');
        
          BWoutline = bwperim(BWfinal);
        
          Segout = I; 
        
          Segout(BWoutline) = 255; 
        
          figure, imshow(Segout), title('outlined original image');
        
          %----------------------
        
          % IR IMAGE
        
          %----------------------
        
          ImageIRarray = imread(ImageIRName);
        
          % Image selection to analize
        
          I_IR=ImageIRarray;
        
          figure, imshow(I_IR), title('original image');
        
          % create a mask
        
          [BW,maskedRGBImage] = createMask(I_IR);
        
          figure, imshow(BW), title('create a mask');
        
          % erode image 
        
          SE1 = strel('disk',8);
        
          BWfinal2 = imerode(BW,SE1);
        
          figure; imshow(BWfinal2), title('erode');
        
          % dilate image 
        
          SE2 = strel('disk',8);
        
          BWfinal3 = imdilate(BWfinal2,SE2);
        
          figure; imshow(BWfinal3), title('imdilate');
        
          %Fill Interior Gaps
        
          BWdfill = imfill(BWfinal3, 'holes');
        
          figure, imshow(BWdfill);
        
          title('binary image with filled holes');
        
          %Smoothen2 the Object
        
          seD = strel('diamond',1);
        
          BWfinal = imerode(BWdfill,seD);
        
          BWfinal = imerode(BWfinal,seD);
        
          figure, imshow(BWfinal), title('segmented image');
        
          % displaying the segmented object
        
          BWoutline_IR = bwperim(BWfinal);
        
          Segout_IR = I_IR; 
        
          Segout_IR(BWoutline_IR) = 255; 
        
          figure, imshow(Segout_IR), title('outlined original image');
        
          %----------------------
        
          %   Arithmetic Image opperation VIS-IR
        
          %----------------------
        
          %Calculate the absolute difference of the two images.
        
          %Fill Interior Gaps
        
          BWdfill = imfill(BWoutline, 'holes');
        
          figure, imshow(BWdfill);
        
          title('binary image with filled holes');
        
          BWdfill_IR = imfill(BWoutline_IR, 'holes');
        
          figure, imshow(BWdfill);
        
          title('binary image with filled holes');
        
          % K = imabsdiff(BWdfill,BWdfill_IR);
        
          % figure, imshow(K), title('Arithmetic Image opperation VIS-IR');
        
          K = imadd(BWdfill,BWdfill_IR);
        
          figure, imshow(K), title('Arithmetic Image opperation VIS-IR');
        
          close all;
        
          % displaying the segmented object
        
          BWoutline_IR_Add = bwperim(K);
        
          Segout_IR = I_IR; 
        
          Segout_IR(BWoutline_IR_Add) = 255; 
        
          figure, imshow(Segout_IR), title('Lava Tube Identified');

view raw MatlabScriptSpaceApp2018_v3.m hosted with ❤ by GitHub

  
          function [BW,maskedImage] = segmentImage(im)
        
          %segmentImage segments image using auto-generated code from imageSegmenter App
        
          %  [BW,MASKEDIMAGE] = segmentImage(IM) segments image IM using auto-generated
        
          %  code from the imageSegmenter App. The final segmentation is returned in
        
          %  BW and a masked image is returned in MASKEDIMAGE.
        
          % Auto-generated by imageSegmenter app on 22-Oct-2018
        
          %----------------------------------------------------
        
          % Convert to grayscale
        
          im = rgb2gray(im);
        
          % Initialize segmentation with threshold
        
          mask = im>1; %(16)
        
          % Evolve segmentation
        
          BW = activecontour(im, mask, 2, 'Chan-Vese');
        
          % Form masked image from input image and segmented image.
        
          maskedImage = im;
        
          maskedImage(~BW) = 0;
        
          end

view raw segmentImage.m hosted with ❤ by GitHub

Hernan M. R. Giannetta

Dear Jury:

We have been experiencing difficulties to upload our proyect information through the Proyect flap during the weekend so we contacted organization to find a solution.

Thank you for your kind understanding. In this flap you will find the Proyect explanation at the very beggining of it.

Best regards,

Lunar Village People

Romina Gabriela Hakl

We won Best Use Of Hardware!!! And now we go international!!! OMG!!! Thank you so much!!! This is a wonderfull experience, and fortunately it continues!!!

Romina Gabriela Hakl

Ready, Stready, Go!

Romina Gabriela Hakl

RESOURCES

•LRO (Lunar Reconnaissance Orbiter)

•PhD Thesis-UTN : H. Giannetta “Studies of materials and MEMS processes for the implementation of a tunable microsensor in the infrared band”.

•“Thermal anomaly at the Earth's surface associated with a lava tube”

•Gravity meassurement , Mission NASA GRAIL

• Evidence of large empty lava tubes on the Moon using GRAIL gravit measurement of echo, Mission JAXA SELENE

• Detection of intact lava tubes at Marius Hills on the Moon by SELENE (Kaguya) lunar radar sounder.

Romina Gabriela Hakl

We are LVP!! :D

Romina Gabriela Hakl

Second day: minutes to display :O

Romina Gabriela Hakl

Working: First Day

Romina Gabriela Hakl

OBJECTIVE

Mission to the moon!: detection of nearby-to-lava-tubes zones suitable for landing through an improved sensor, and research for more lava tubes on Moon´s ground.

METHODOLOGY

Application of IR sensor improved with tunable bands based on graphene to increase spacial resolution for lava tubes detection and digital image processing. This correlated with use of Machine Learning model based on parameters such as Infrared, Gravimeter and Magnetic Suceptibility data available from NASA and also taken on the Moon.

CONSIDERATIONS

The best landing place will be selected focusing on:

-Basic needs of a suitable place for landing (pre-established by uses and customs): Adequate topography, no rocks, not abrupt field, with little amount of dust

-Scientific interest: Areas of historical geological interest (Extraction of samples for analysis), proximity to lava tubes that will be used as a base settlement refuge. (Detection of intact lava tubes at Marius Hills on the Moon by SELENE (Kaguya) lunar radar sounder)

-Proximity to reservoirs of water for supply. (The presence of ice has been detected in the areas of the lunar poles)

-Other, such as economic: presence of construction amterials (High areas: calcite, plagioclase, gabbro and anortite., A lot of aluminum: refractory. Ideal gaps for construction and glass for amalgamation. Low areas: basaltic lithology, associated with volcanic devices, titanium and iron oxides. Add info about the geological past of the moon)

Romina Gabriela Hakl

SpaceApps is a NASA incubator innovation program.

	function [BW,maskedRGBImage] = createMask(RGB)
	%createMask Threshold RGB image using auto-generated code from colorThresholder app.
	% [BW,MASKEDRGBIMAGE] = createMask(RGB) thresholds image RGB using
	% auto-generated code from the colorThresholder App. The colorspace and
	% minimum/maximum values for each channel of the colorspace were set in the
	% App and result in a binary mask BW and a composite image maskedRGBImage,
	% which shows the original RGB image values under the mask BW.

	% Auto-generated by colorThresholder app on 22-Oct-2018
	%------------------------------------------------------


	% Convert RGB image to chosen color space
	RGB = im2double(RGB);
	cform = makecform('srgb2lab', 'AdaptedWhitePoint', whitepoint('D65'));
	I = applycform(RGB,cform);

	% Define thresholds for channel 1 based on histogram settings
	channel1Min = 47.714;
	channel1Max = 94.428;

	% Define thresholds for channel 2 based on histogram settings
	channel2Min = -35.728;
	channel2Max = -29.696;

	% Define thresholds for channel 3 based on histogram settings
	channel3Min = 13.372;
	channel3Max = 39.345;

	% Create mask based on chosen histogram thresholds
	BW = (I(:,:,1) >= channel1Min ) & (I(:,:,1) <= channel1Max) & ...
	(I(:,:,2) >= channel2Min ) & (I(:,:,2) <= channel2Max) & ...
	(I(:,:,3) >= channel3Min ) & (I(:,:,3) <= channel3Max);

	% Invert mask
	BW = ~BW;

	% Initialize output masked image based on input image.
	maskedRGBImage = RGB;

	% Set background pixels where BW is false to zero.
	maskedRGBImage(repmat(~BW,[1 1 3])) = 0;

	%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
	%
	% Matlab script
	%
	% SpaceApp2018
	%
	% By: Hernan Giannetta (PhD)
	%
	% hgiannetta@frba.utn.edu.ar
	%
	% October 20-21, 2018
	%
	%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

	% Init

	clc;
	clear all;
	close all;

	% Local Variables

	ImageIRName = 'qm-lroc-1540099077964.png';
	ImageVISName = 'qm-lroc-1540099157713.png';

	outputfolderName='output';
	Image_Ori='Image_Ori';

	Image_VIS_original_filename='Image_VIS_original';
	Image_VIS_segmented_filename='Image_VIS_segmented';




	%------------------
	% Main
	%------------------


	%------------------
	% VIS Image
	%------------------

	ImageVISarray = imread(ImageVISName);

	% Image selection to analize
	I=ImageVISarray;

	figure, imshow(I), title('original image');


	% %I = imread('coins.png');
	% level = graythresh(I);
	% BW = im2bw(I,level);
	% figure,imshow(BW)

	%binarize
	I_Proc=segmentImage(I);
	BW = im2bw(I_Proc);
	figure; imshow(BW), title('segmentImage');
	% erode
	%SE1 = strel('arbitrary',eye(20))
	SE1 = strel('disk',2);
	BW1 = imerode(BW,SE1);
	figure; imshow(BW1), title('erode');
	% dilate image
	SE2 = strel('disk',7);
	BW2 = imdilate(BW1,SE2);
	figure; imshow(BW2), title('imdilate');


	%edge detection
	[~, threshold] = edge(BW2, 'sobel');
	fudgeFactor = .5;
	BWs = edge(BW2,'sobel', threshold * fudgeFactor);
	figure, imshow(BWs), title('binary gradient mask');

	%dilate
	se90 = strel('line', 3, 90);
	se0 = strel('line', 3, 0);
	BWsdil = imdilate(BWs, [se90 se0]);
	figure, imshow(BWsdil), title('dilated gradient mask');

	%Fill Interior Gaps
	BWdfill = imfill(BWsdil, 'holes');
	figure, imshow(BWdfill);
	title('binary image with filled holes');

	%Remove Connected Objects on Border
	BWnobord = imclearborder(BWdfill, 4);
	figure, imshow(BWnobord), title('cleared border image');

	%Smoothen the Object
	seD = strel('diamond',1);
	BWfinal = imerode(BWnobord,seD);
	BWfinal = imerode(BWfinal,seD);
	figure, imshow(BWfinal), title('segmented image');

	% erode image
	SE1 = strel('disk',2);
	BWfinal2 = imerode(BWfinal,SE1);
	figure; imshow(BWfinal2), title('erode');
	% dilate image
	SE2 = strel('disk',15);
	BWfinal3 = imdilate(BWfinal2,SE2);
	figure; imshow(BWfinal3), title('imdilate');

	%Smoothen2 the Object
	seD = strel('diamond',1);
	BWfinal = imerode(BWfinal3,seD);
	BWfinal = imerode(BWfinal,seD);
	figure, imshow(BWfinal), title('segmented image');


	BWoutline = bwperim(BWfinal);
	Segout = I;
	Segout(BWoutline) = 255;
	figure, imshow(Segout), title('outlined original image');


	%----------------------
	% IR IMAGE
	%----------------------


	ImageIRarray = imread(ImageIRName);

	% Image selection to analize
	I_IR=ImageIRarray;
	figure, imshow(I_IR), title('original image');

	% create a mask
	[BW,maskedRGBImage] = createMask(I_IR);
	figure, imshow(BW), title('create a mask');

	% erode image
	SE1 = strel('disk',8);
	BWfinal2 = imerode(BW,SE1);
	figure; imshow(BWfinal2), title('erode');
	% dilate image
	SE2 = strel('disk',8);
	BWfinal3 = imdilate(BWfinal2,SE2);
	figure; imshow(BWfinal3), title('imdilate');

	%Fill Interior Gaps
	BWdfill = imfill(BWfinal3, 'holes');
	figure, imshow(BWdfill);
	title('binary image with filled holes');

	%Smoothen2 the Object
	seD = strel('diamond',1);
	BWfinal = imerode(BWdfill,seD);
	BWfinal = imerode(BWfinal,seD);
	figure, imshow(BWfinal), title('segmented image');

	% displaying the segmented object
	BWoutline_IR = bwperim(BWfinal);
	Segout_IR = I_IR;
	Segout_IR(BWoutline_IR) = 255;
	figure, imshow(Segout_IR), title('outlined original image');




	%----------------------
	% Arithmetic Image opperation VIS-IR
	%----------------------


	%Calculate the absolute difference of the two images.

	%Fill Interior Gaps
	BWdfill = imfill(BWoutline, 'holes');
	figure, imshow(BWdfill);
	title('binary image with filled holes');

	BWdfill_IR = imfill(BWoutline_IR, 'holes');
	figure, imshow(BWdfill);
	title('binary image with filled holes');

	% K = imabsdiff(BWdfill,BWdfill_IR);
	% figure, imshow(K), title('Arithmetic Image opperation VIS-IR');

	K = imadd(BWdfill,BWdfill_IR);
	figure, imshow(K), title('Arithmetic Image opperation VIS-IR');

	close all;
	% displaying the segmented object
	BWoutline_IR_Add = bwperim(K);
	Segout_IR = I_IR;
	Segout_IR(BWoutline_IR_Add) = 255;
	figure, imshow(Segout_IR), title('Lava Tube Identified');

	function [BW,maskedImage] = segmentImage(im)
	%segmentImage segments image using auto-generated code from imageSegmenter App
	% [BW,MASKEDIMAGE] = segmentImage(IM) segments image IM using auto-generated
	% code from the imageSegmenter App. The final segmentation is returned in
	% BW and a masked image is returned in MASKEDIMAGE.

	% Auto-generated by imageSegmenter app on 22-Oct-2018
	%----------------------------------------------------


	% Convert to grayscale
	im = rgb2gray(im);

	% Initialize segmentation with threshold
	mask = im>1; %(16)

	% Evolve segmentation
	BW = activecontour(im, mask, 2, 'Chan-Vese');

	% Form masked image from input image and segmented image.
	maskedImage = im;
	maskedImage(~BW) = 0;
	end