eCognition tutorial: Almost connected components for clumps identification in eCognition

This post is inspired from a post by Steve Eddins, who works in Math works, a company that build MATLAB. He is a software development manager in the MATLAB and one of the co-author of a book " Digitial image processing with MATLAB".I use both MATLAB and eCognition, so I ponder if this can be done in eCognition. eCognition has basic Morphological Operators like dilation and erosion . Advance MM operators like by opening by reconstruction, connected component labeling or skeleton and many others are not available in eCognition.

The problem of almost connected components:

There is simple synthetic image containing a number of circular blobs.  How can we label and measure the three clumps instead of the smaller circles? Two circles are almost connected if circles are within 25 pixels unit.

Binary circles

Connected components labeling

Almost connected components labeling

Of course it can be solved in eCognition. But for this, you have to  be familiar with many concepts in eCognition. Concepts such as PPO, object variables, multi-level representation and temporary layers are required. My workflow for  the solution is as follows:

• Use multi-threshold segmentation to get circles
• Use distance map algorithm to get binary distance map
• Use chessboard segmentation to get pixel level unclassified objects
• Use  multi-thresholding segmentation based on the distance map to get  clump
• Copy level above
• Use object variable concept to assign each clump a unique ID
• Convert to sub-objects to get original circle at upper level

I will post rule-set after some time. I have given you enough hint how to proceed. Get your hands dirty !

Almost connected components labelling within eCognition

The concept of “almost connected components” can be applicable in remote sensing for clustering buildings detected in remote sensing images for analyzing of micro-climate of urban areas. There can be various other applications. Can you think of any ?

eCognition tutorial: Image object fusion in eCognition: Example of water bodies classification

eCognition is a powerful software for analysis for remote sensing images. Many people have this false impression that eCognition is all about segmentation. That’s not true. Segmentation is a just a part of it big chain that may involve segmentation, temporary classification, fusion, exploitation of contextual information etc. Many people believe that segmentation should be perfect at first time which is a fallacy. You can modify your segments as more information becomes available during the analysis. Typically in my any project I use segmentation at least 10 times. Yes at least 10 times .One of  the underutilized feature of eCognition is “Image Object Fusion” algorithm.The algorithm is an essential part of "iterative segmentation and classification" approach of GEOBIA. In this blog, I will show an example of image object fusion for classification of water bodies in a small remote sensing image. The step involves:

1. Segmentation
2. Initial classification of water
1. Establishment of customized feature RationNIR 
• RationNIR = (meanNIR/(meanR+meanB+meanG+meanNIR))*100
2. Classify objects that satisfy property
• RationNIR  less than 15 
• Area greater than 10 pixels ( to avoid small shadows)
3. Image object fusion using PPO ( Parent Process Object) to get whole water body
1. Starting from water classified in step 2, check neighboring water objects and if difference between water object and neighboring objects is less than 5 in RatioNIR. Run in a loop.
2. Process all water objects. 

Original image

Initial segmentation

Initial water classification

Final segmentation after image object fusion

Final water classification using image object fusion

Very powerful image object fusion algorithm

Step 3 is a one liner algorithm using "Image object Fusion".  Notice various parameters like Class filter, candidates classes, fitting function threshold, use absolute fitting value and weighted sum.To help you understand, I have made a "gif" to elaborate what is going on.

Blue: Initial water

Yellow: Active object

Red: Fused water after image object fusion







Here is the whole Rule set for water classification with image object fusion.

QGIS tutorial: Display with color symbology from data defined properties of shape files

How many of you have this problem: you classify your images in ecognition or any other software and exported classified image as shape file. Now you want to view the shape file in a GIS environment and with the same color for each class that was used in eCognition. Manually matching color RGB values from eCognition to shape colors for each class is a tedious task, specially when  you have many classes.

This problem can be solved with a little trick.

• Do your classification in eCognition. Assign class colors as you wish.


• Export classification result as shape file with Class attributes.


• Export classification result as thematic raster. By doing so, you will get a CSV file in which you can get RGB color codes for each class.


• Load your shape file in GIS (I use QGIS which is free. I am a poor guy therefore I always love free stuffs)


• Load the CSV file in QGIS


• Perform attribute Join of shape file and CSV file with key attribute join based on Class. With this you will get RGB values attached in attribute table of shape file.


• Double click color symbology of shape file and use data defined properties of  color attributes  of shape file.


• Build an expression for color selecting respective color attribute column from shape file.

import CSV file into QGIS

Attribute of shape file after performing join

Data defined properties

data defined properties for color

data defined properties for color

Normal display without color symbology

Display with color symbology

eCognition tutorial: Exporting eCognition features as images with array functionalities

There are instances when one would like to export different features from eCognition as a images to perform some tasks outside eCognition. eCognition doesn't provide a way to export many object features as images but it is only possible to export as a thematic raster in which each object has a unique ID, and features values are stored in a separated CSV file. To convert it into images, one has to mapped ID raster tiff file and data from CSV file.

If you want to get eCogntion features as images in an automatic way that can export any numbers of features as images in one go, then here is a way. For the purpose, we are going to utilize array handing capabilities of eCogntion and export each feature as separate tiff (My_1.tiff, My_2.tiff …. and so on) file. The rule set can be downloaded here. The rule set is flexible in the sense that you just have to update an array to store your feature list of interest. Number features can be any number (10, 20 or even 100 features). We will merge it afterwards in open source QGIS.

• Perform a segmentation
• Create a array and store features you want to export as images
• Loop over the array

1. For each feature, create a temporary image file
2. Export the temporary file as a unique name
3. Repeat until all features in the array are executed

• Now in QGIS, we use GDAL to stack individual images into one single image. We will use merge function of GDAL (Raster>Miscellaneous> Merge).

  

  Complete ruleset within eCognition

Ruleset  for exporting features as images 

GDALmerge function within QGIS

Color composite of three merge features

Thus produced merge features image now can be used for classification  in ENVI, ERDAS IMAGINE or writing custom script in Python or MATAB. Personally I use such images within Python using scikit-learn library.

eCognition tutorial: Exporting eCognition classification file to ENVI

The problem:

I was wondering if anyone could help me export a usable file from eCognition Developer for use in ENVI 5.0? I've classified an image using Multiresolution Segmentation followed by the Classification algorithm using selected samples from the Standard Nearest Neighbour and everything worked so far. I try and export it as an ENVI-supported file type (e.g. *.tif) the raster seems to have "lost" all the classification- leaving a grayscale image- useless! I have been able to open a *.jpg file, but as it is an image it has lost any previous classfication from Ecognition.

Solution:

This is not even a problem but for people who are just starting with ENVI is a big HEADACHE. It’s just a matter of a symbology. If you have been using the ENVI for a while you should know that ENVI uses two files for any image. One binary file and another hdr file where different information about the binary image are stored. One can simply open hdr files with a notepad. Normal raster images have “file type = ENVI Standard” whereas classification images have “file type = ENVI Classification” and some other information such number of classes, class names and class colours. So the classified tiff file that one exports from eCognition does not have those information, hence ENVI opens the classified tiff file as a normal file. There are values differentiating classes but colour information are lost. This is a problem if you want to do some other operation in ENVI that required a classification image as input.

So we need to convert it ENVI Classification type, somehow. So here is a way to do it.

1. Do your classification in eCognition.
2. Export it using “export thematic raster files” algorithm in eCognition with Export Type Don’t forget to select your classes in Class Filter parameters
3. Once you export it, you will have two files. One *.tiff file and other *.csv fil. Open *.csv file, there you will find class names and RGB colour for each class.
4. Open *.tif file in ENVI.
5. Then File> File Save as > ENVI Standard>Import file > Pick recently open tif file. Give a name and save it. Now you changed tiff file to ENVI file but remember, its still a normal ENVI standard file.
6. Open the file created in step 5. Then File> Edit Header Info > Select File type as ENVI classification. It will prompt you for number of classes, class names, colour information. Provide those information by using *.CSV file that you opened in step 3.
7.   Now you have a ENVI classification image with same class names and colour as in eCognition. Now smile and go for a coffee.

Example of a CSV file

Converting tiff file to ENVI file

Modifying header files

Editing class names and color information

Initial and Final image

Data exchange between MATLAB and Python: Reading and writing .mat fileswith Python

I am a MATLAB guy. I love MATLAB. I started with Fortan during my first degree at my Bachelor level. I came across with MATLAB only in year 2010 as a part of my Msc studies. Since then I been using it continuously for various tasks. Just recently, I started  using Python and I LOVE IT. The biggest reason being that Python is open-source and there are lots of Python libraries that can be used. But there are times; I have to shuffle data between MATLAB and python, because for some tasks I prefer MATLAB as I am accustom to it. So if you are in the same boat, then here I show you simple way to transfer data between MATLAB and Python. One has to use scipy.io module in Scipy for that purpose. If you have some old data or got some data online that are saved as MATLAB’s .mat file format, you can simply import it as:

import numpy as np
import scipy.io as sio
mydata = sio.loadmat('mydata.mat')

Now your mydata contains a dictinary with keys corresponding to the varible names saved in the original mydata.mat Saving a python variable to .mat file is also straight forward

# write one variable
x = np.arange(1,10,1)
# file name of the file
fname ='export_from_python.mat'
sio.savemat(fname, {'x':x})

When you read export_from_python.mat, you will get 'x' varialbe into MATLAB. If you want to write more than two variable:

# write two variables
x = np.arange(1,10,1)
y = np.ones((5,5))
fname ='export_from_python_1.mat'
sio.savemat(fname, {'x':x, 'y':y})

I do lot of work with classification of remote sensing images using many different types of machine learning algorithms. Proprietary software like ENVI and ERDAS are not flexible enough for me, as these software donot allow an efficient way to tune hyper-parameters that are algorithm specific. I dont like training models with defualt parameters. I do my model traning and classification in python. Here is the typical workflow.

1.  Import image and training data in python using GDAL
2. Train machine learning model in python using Sci-kit Learn
3. For accuracy assessment, i do it within python but for accuracy assessment visualization, i export  targets and outputs vectors from Python to MATLAB
4. Use 'plotconfusion' function from Neural Network toolbox for a visualization of confusion matrix. Here is the confusion Matrix  information that i got from MATLAB. Its nice, isnt it ?

Confusion matrix

Example of extracting grid nodes in MATLAB

For last few posts, I am writing about morphological image analysis with python with open source package scikit-image. In this post I want to show benefit of morphological image analysis with some real application. I been working with road extraction from satellite images for past few weeks and  one of the common task is to extract the grid corner nodes of the road network. So let’s assume the road grid has been already extracted and we want to extract intersection of grid network. Here I am showing three approaches for that based on synthetic data. Obviously with real data, the task is more complex and might require many slight modifications.

Here is the grid. You can generate such grid with checkerboard function in MATLAB with minor processing (edge detection and hole filling). Intersections of of grid lines have a property that it has 4 white pixels in 4-N neighborhood.  We can exploit this property to extract it. I am going to show to ways by which it can be done and in addition, another method based on extraction of corners will also be shown.

%make a checkerboard
I=checkerboard(20, 10,10)>0.5;
imshow(I)
% detect edge with canny
BW = edge(I,'canny');
figure, imshow(BW)
%make square structural element to fill holes with closing
SE = strel('square', 3);
BW1 = imclose(BW, SE);
figure, imshow(BW1)
% make a skeleton of the to lines 1 pixel thick
BW2 = bwmorph(BW1,'skel',Inf);
figure, imshow(BW2)

 


In mathematics and, in particular, functional analysis, convolution is a mathematical operation on two functions f and g, producing a third function that is typically viewed as a modified version of one of the original function .In simple word, convolution of image is a process where you scan your image from left to right and top to bottom within local neighborhood defined by user, and do mathematical calculation within the local neighborhood. Here we are going to use it for simply sum the number of pixels which are which are white within 3x3 neighborhood. As shown by above figure, if the point is an intersection grid point then at that point sum should be 5. Any points with less than 5 white pixels are not intersection grid points.

% with block processing and inline function with convolution
tic;
kernel = [0 1 0; ... %# Convolution kernel
1 1 1; ...
0 1 0];
sumX = conv2(double(BW2),kernel,'same');
result=sumX;
% only consider pixels which are in grid image
result (BW2==0)= 0
result(sumX<5)=0;
[r,c] = find(result>0);
toc;
figure,imshow((BW2)), hold on, plot(r,c,'r*');title ('with Convolution')
hold off

Way Two: With Mathematical Morphology (MM)

If you are working in the field of Geo-information and you still saying what the heck this ‘MM’ then seriously you should be acquainted with this field of image processing. You can use MM for classification, edge detection, filtering, segmentation, building detection and many other things. Grab a cup of coffee and Google MM in remote sensing; there is tons of stuff to read.  There are courses in MM taught in different universities which are one semester long, so you got an idea how vast the subject is. If you want to seriously know MM, then there is no better book than ‘ Morphological Image Analysis’ by P Soillie. Here we use ‘Erosion’ method of MM.  Time: 0.011184 seconds.

% method two with morphological analysis
tic;
SE = strel ('disk', 1);
result2 = imerode(BW, SE);
[r,c] = find(result>0);
toc;
figure,imshow((BW2)), hold on, plot(r,c,'b*'), title ('With MM Erosion')
hold off

Way Two:  Mathematical Morphology (MM)

There are many corner detection techniques such as Moravec, Harris, SIFT etc. Here, I am going to use Harris corner detector for intersection grid points. Time: 0.094848 seconds.

% detect corner by harris corner detector
tic;
C = corner(BW2,500 );
timet2 = toc;
toc;
figure,imshow(BW2);
hold on
plot(C(:,1), C(:,2), 'g*'); title('with harris corner detector')
hold off

Way Two:  With Harris Corner Detector

So you have seen there are number of ways to solve a particular problem. All above methods detected intersection points successfully. Among three methods, convolution required longest time for processing and MM required shortest time. The gain in computation cost between MM and Corner detection is 9 folds.  I did all this in MATLAB but it can easily coded in python with scikit-image.