ANN OPENCV error assertion failed - c++

I'm trying to make a simple ANN network with opencv in QT and develop it more later ,
I tried with simple data and i get an error says : OpenCV Error : asserion failed ((unsigned)(i1 *datatype<_tp>::channels)) < unsigned(size.p[1]* channels())) in cv::mat::at
here's the code I wrote
#include <iostream>
#include <opencv2/ml.hpp>
#include <opencv/cv.h>
#include <opencv2/core.hpp>
#include <opencv2/imgcodecs.hpp>
#include <opencv2/highgui/highgui.hpp>
#include "nnet.h"
using namespace std;
using namespace cv;
int main()
{
string filename="data.csv";
Ptr<cv::ml::TrainData> tdata = cv::ml::TrainData::loadFromCSV(filename,0,-1,-1);
Mat trainData = tdata->getTrainSamples();
Mat trainLabels = tdata->getTrainResponses();
int numClasses = 3;
Mat hot(trainLabels.rows, numClasses, CV_32F, 0.0f);
for (int i=0; i<trainLabels.rows; i++) {
int id = (int)trainLabels.at<float>(i);
hot.at<float>(i, id) = 1.0f;
}
int input_neurons = 5;
int hidden_neurons = 5;
int output_neurons = 3;
Mat layerSizes = Mat(3, 1, CV_32SC1);
layerSizes.row(0) = Scalar(input_neurons);
layerSizes.row(1) = Scalar(hidden_neurons);
layerSizes.row(2) = Scalar(output_neurons);
Ptr<cv::ml::ANN_MLP> myNetwork = cv::ml::ANN_MLP::create();
myNetwork->setLayerSizes(layerSizes);
myNetwork->setTrainMethod(ml::ANN_MLP::SIGMOID_SYM);
myNetwork->setTermCriteria(TermCriteria(CV_TERMCRIT_ITER | CV_TERMCRIT_EPS, 1000, 0.00001f));
myNetwork->setTrainMethod(ml::ANN_MLP::BACKPROP,0.1f,0.1f);
myNetwork->setActivationFunction(ml::ANN_MLP::SIGMOID_SYM, 1, 1);
myNetwork->train(trainData, 0, hot);
string testfilename="test-data.csv";
Ptr<cv::ml::TrainData> testdata = cv::ml::TrainData::loadFromCSV(testfilename, 0,0,-1);
Mat testData = testdata->getTrainSamples();
Mat testLabels = testdata->getTrainResponses();
Mat testResults;
myNetwork->predict(testData, testResults);
float accuracy = float(countNonZero(testResults == testLabels)) / testLabels.rows;
printf("%f",accuracy);
return 0;
}
and for the data set i have
data.csv contains
1,2,3,7,2
7,1,7,7,5
9,7,5,3,2
12,21,32,71,8
and data-test.csv contains :
1,2,1,1,2,
9,1,2,12,5,
11,28,14,50,8,
3,1,2,12,5,
11,28,24,20,8,
thank you in advance for your help.

i found the solution to my problem , in the csv file i've i have 3 classes and the response values should be between [0..2] and i gave random numbers 5 and 8 so changing them solved this problem

Related

OpenCV C++ Error with sinusoidal pattern generation - structured_light library

I am trying to use the sinusoidal pattern tool in C++ with Visual Studio. I have placed the code that I am testing this with below. In visual studio everything looks fine bar the red squiggle under params in the following line:
Ptr<structured_light::SinusoidalPattern> sinus = structured_light::SinusoidalPattern::create(params);
When I try to build I get the following error message:
Severity Code Description Project File Line Suppression State Error (active)
no suitable user-defined conversion from
"cv::structured_light::SinusoidalPattern::Params" to
"cv::Ptr<cv::structured_light::SinusoidalPattern::Params>" exists Structured_Light_Test
c:\Users\ianco\Desktop\CPlusPlus_Programming\Structured_Light_Test\Structured_Light_Test\Main.cpp 70
I would be very grateful if anyone could offer some advice on how I could get round this issue or suggest another method.
CODE:
#include <opencv2/highgui.hpp>
#include <vector>
#include <iostream>
#include <fstream>
#include <opencv2/core.hpp>
#include <opencv2/core/utility.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/calib3d.hpp>
#include <opencv2/structured_light.hpp>
#include <opencv2/phase_unwrapping.hpp>
using namespace cv;
using namespace std;
int main(int argc, char **argv)
{
structured_light::SinusoidalPattern::Params params;
params.width = 1080;
params.height = 700;
params.nbrOfPeriods = 5;
params.setMarkers = true;
params.horizontal = false;
params.methodId = 2;
params.shiftValue = static_cast<float>(2 * CV_PI / 3);
params.nbrOfPixelsBetweenMarkers = 70;
String outputPatternPath = "C:/Users/ianco/Desktop/CPlusPlus_Programming";
String outputWrappedPhasePath = "C:/Users/ianco/Desktop/CPlusPlus_Programming";
String outputUnwrappedPhasePath = "C:/Users/ianco/Desktop/CPlusPlus_Programming";
Ptr<structured_light::SinusoidalPattern> sinus = structured_light::SinusoidalPattern::create(params);
// Storage for patterns
vector<Mat> patterns;
//Generate sinusoidal patterns
sinus->generate(patterns);
cv::Mat blue, green, red;
std::vector<cv::Mat> images(3);
// OpenCV works natively with BGR ordering
images.at(0) = patterns[0];
images.at(1) = patterns[1];
images.at(2) = patterns[2];
cv::Mat color;
cv::merge(images, color);
namedWindow("pattern", WINDOW_NORMAL);
setWindowProperty("pattern", WND_PROP_FULLSCREEN, WINDOW_FULLSCREEN);
imshow("pattern", color);
waitKey(3000);
}
The documentation tells you that params should also be a Ptr but you passed the object...
try using makePtr
Change this line:
structured_light::SinusoidalPattern::Params params;
with this:
Ptr<cv::structured_light::SinusoidalPattern::Params> params = makePtr< SinusoidalPattern::Params >();
you will have to change . to -> for each use of params like params.width = 1080; would be params->width = 1080;, since it will be a pointer now.
The rest of the code should be ok.

VTK Volume Visualization Issue

I am using vtk library with C++ to generate and visualize some synthetic voxel data with given color and transparency mapping. An example is shown below:
As shown in the figure, the data is 3D in general, and it works great. However, in specific cases when the data becomes 2D, the visualization windows shows nothing.
I am posting few lines of my code which may be helpful.
imageData = vtkSmartPointer<vtkImageData>::New();
imageData->SetDimensions(X1, X2, X3); //For 2D, one of X1,X2 & X3=1
imageData->AllocateScalars(VTK_INT, 1);
int* I = new int[X1X2X3](); //int X1X2X3 = X1*X2*X3
I = static_cast<int*>(imageData->GetScalarPointer());
Please note that for 2D, either X1=1 or X2=1 or X3=1.
Any suggestions?
EDIT:
I am adding an equivalent code, which will demonstrate the exact problem I am facing:
main.cpp
//#include <vtkAutoInit.h> // if not using CMake to compile, necessary to use this macro
//#define vtkRenderingCore_AUTOINIT 3(vtkInteractionStyle, vtkRenderingFreeType, vtkRenderingOpenGL2)
//#define vtkRenderingVolume_AUTOINIT 1(vtkRenderingVolumeOpenGL2)
//#define vtkRenderingContext2D_AUTOINIT 1(vtkRenderingContextOpenGL2)
#include <vtkSmartPointer.h>
#include <vtkActor.h>
#include <vtkRenderWindow.h>
#include <vtkRenderer.h>
#include <vtkRenderWindowInteractor.h>
#include <vtkSmartVolumeMapper.h>
#include <vtkColorTransferFunction.h>
#include <vtkVolumeProperty.h>
#include <vtkSampleFunction.h>
#include <vtkPiecewiseFunction.h>
#include <vtkImageData.h>
#include <stdlib.h>
using namespace std;
int main()
{
//Declaring Variables
vtkSmartPointer<vtkImageData> imageData;
vtkSmartPointer<vtkVolumeProperty> volumeProperty;
vtkSmartPointer<vtkPiecewiseFunction> compositeOpacity;
vtkSmartPointer<vtkColorTransferFunction> color;
vtkSmartPointer<vtkVolume> volume;
vtkSmartPointer<vtkSmartVolumeMapper> mapper;
vtkSmartPointer<vtkActor> actor;
vtkSmartPointer<vtkRenderer> renderer;
vtkSmartPointer<vtkRenderWindowInteractor> renderWindowInteractor;
vtkSmartPointer<vtkRenderWindow> renderWindow;
int* I;
int X1, X2, X3, X1X2X3;
//Assigning Values , Allocating Memory
X1 = 10;
X2 = 10;
X3 = 10;
X1X2X3 = X1*X2*X3;
I = new int[X1X2X3]();
imageData = vtkSmartPointer<vtkImageData>::New();
volumeProperty = vtkSmartPointer<vtkVolumeProperty>::New();
compositeOpacity = vtkSmartPointer<vtkPiecewiseFunction>::New();
color = vtkSmartPointer<vtkColorTransferFunction>::New();
volume = vtkSmartPointer<vtkVolume>::New();
mapper = vtkSmartPointer<vtkSmartVolumeMapper>::New();
actor = vtkSmartPointer<vtkActor>::New();
renderer = vtkSmartPointer<vtkRenderer>::New();
renderWindowInteractor = vtkSmartPointer<vtkRenderWindowInteractor>::New();
renderWindow = vtkSmartPointer<vtkRenderWindow>::New();
volumeProperty->ShadeOff();
volumeProperty->SetInterpolationType(0);
volumeProperty->SetColor(color);
volumeProperty->SetScalarOpacity(compositeOpacity);
imageData->SetDimensions(X1, X2, X3);
imageData->AllocateScalars(VTK_INT, 1);
I = static_cast<int*>(imageData->GetScalarPointer());
renderWindow->AddRenderer(renderer);
renderWindowInteractor->SetRenderWindow(renderWindow);
renderer->SetBackground(0.5, 0.5, 0.5);
renderWindow->SetSize(800, 800);
mapper->SetBlendModeToComposite();
imageData->UpdateCellGhostArrayCache();
mapper->SetRequestedRenderModeToRayCast();
mapper->SetInputData(imageData);
volume->SetMapper(mapper);
volume->SetProperty(volumeProperty);
renderer->AddViewProp(volume);
volumeProperty->ShadeOff();
//Setting Voxel Data and Its Properties
for (int i = 0; i < X1X2X3; i++)
{
I[i] = i;
compositeOpacity->AddPoint(i, 1);
color->AddRGBPoint(i, double( rand()) / RAND_MAX, double(rand()) / RAND_MAX, double(rand()) / RAND_MAX);
}
renderer->ResetCamera();
renderWindow->Render();
renderWindowInteractor->Start();
getchar();
return 0;
}
CMakeLists.txt
cmake_minimum_required(VERSION 3.0)
project(EvoSim)
set(CMAKE_CXX_STANDARD 14)
set(CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS ON)
set(CMAKE_USE_RELATIVE_PATHS ON)
#GRABBING VTK
find_package(VTK REQUIRED)
include(${VTK_USE_FILE})
add_executable(MAIN main.cpp)
target_link_libraries(MAIN ${VTK_LIBRARIES})
This leads to an output like below (for, X1=X2=X3=10)
However if I make X1=1, the output window is empty.
EDIT:
I just observed that the number of voxels along a certain dimension, displayed on the screen are always one less than the maximum number of voxels in that dimensions. For example, if X1=X2=X3=10, the number of voxels in each dimensions which are displayed on vtkwindow is 9. This is not what I would expect. I think this is the problem with X1=1, which makes 1-1=0 voxel display.
Any suggestions??
This remained unanswered for long. So I am adding my solution/workaround.
I had to add an extra dummy layer in each dimension of imagedata. [See this line in the code imageData->SetDimensions(X1 +1 , X2 + 1, X3 + 1);]. Rest is self explanatory.
#pragma once
//#include <vtkAutoInit.h> // if not using CMake to compile, necessary to use this macro
//#define vtkRenderingCore_AUTOINIT 3(vtkInteractionStyle, vtkRenderingFreeType, vtkRenderingOpenGL2)
//#define vtkRenderingVolume_AUTOINIT 1(vtkRenderingVolumeOpenGL2)
//#define vtkRenderingContext2D_AUTOINIT 1(vtkRenderingContextOpenGL2)
#include <vtkSmartPointer.h>
#include <vtkActor.h>
#include <vtkRenderWindow.h>
#include <vtkRenderer.h>
#include <vtkRenderWindowInteractor.h>
#include <vtkSmartVolumeMapper.h>
#include <vtkColorTransferFunction.h>
#include <vtkVolumeProperty.h>
#include <vtkSampleFunction.h>
#include <vtkPiecewiseFunction.h>
#include <vtkImageData.h>
#include <stdlib.h>
#include <numeric> // std::iota
using namespace std;
int main()
{
//Declaring Variables
vtkSmartPointer<vtkImageData> imageData;
vtkSmartPointer<vtkVolumeProperty> volumeProperty;
vtkSmartPointer<vtkPiecewiseFunction> compositeOpacity;
vtkSmartPointer<vtkColorTransferFunction> color;
vtkSmartPointer<vtkVolume> volume;
vtkSmartPointer<vtkSmartVolumeMapper> mapper;
vtkSmartPointer<vtkActor> actor;
vtkSmartPointer<vtkRenderer> renderer;
vtkSmartPointer<vtkRenderWindowInteractor> renderWindowInteractor;
vtkSmartPointer<vtkRenderWindow> renderWindow;
int X1, X2, X3, X1X2X3;
//Assigning Values , Allocating Memory
X1 = 10;
X2 = 10;
X3 = 10;
X1X2X3 = X1*X2*X3;
imageData = vtkSmartPointer<vtkImageData>::New();
imageData->SetDimensions(X1 + 1, X2 + 1, X3 + 1);
imageData->AllocateScalars(VTK_INT, 1);
volumeProperty = vtkSmartPointer<vtkVolumeProperty>::New();
compositeOpacity = vtkSmartPointer<vtkPiecewiseFunction>::New();
color = vtkSmartPointer<vtkColorTransferFunction>::New();
volume = vtkSmartPointer<vtkVolume>::New();
mapper = vtkSmartPointer<vtkSmartVolumeMapper>::New();
actor = vtkSmartPointer<vtkActor>::New();
renderer = vtkSmartPointer<vtkRenderer>::New();
renderWindowInteractor = vtkSmartPointer<vtkRenderWindowInteractor>::New();
renderWindow = vtkSmartPointer<vtkRenderWindow>::New();
volumeProperty->ShadeOff();
volumeProperty->SetInterpolationType(0);
volumeProperty->SetColor(color);
volumeProperty->SetScalarOpacity(compositeOpacity);
imageData->AllocateScalars(VTK_INT, 1);
renderWindow->AddRenderer(renderer);
renderWindowInteractor->SetRenderWindow(renderWindow);
renderer->SetBackground(0.5, 0.5, 0.5);
renderWindow->SetSize(800, 800);
mapper->SetBlendModeToComposite();
imageData->UpdateCellGhostArrayCache();
mapper->SetRequestedRenderModeToRayCast();
mapper->SetInputData(imageData);
volume->SetMapper(mapper);
volume->SetProperty(volumeProperty);
renderer->AddViewProp(volume);
volumeProperty->ShadeOff();
//I is supposed to store the 3D data which has to be shown as volume visualization. This 3D data is stored
//as a 1D array in which the order of iteration over 3 dimensions is x->y->z, this leads to the following
//3D to 1D index conversion farmula index1D = i + X1*j + X1*X2*k
vector<int> I(X1X2X3,0); // No need to use int* I = new int[X1X2X3] //Vectors are good
std::iota(&I[0], &I[0] + X1X2X3, 1); //Creating dummy data as 1,2,3...X1X2X3
//Setting Voxel Data and Its Properties
for (int k = 0; k < X3 + 1 ; k++)
{
for (int j = 0; j < X2 + 1 ; j++)
{
for (int i = 0; i < X1 + 1 ; i++)
{
int* voxel = static_cast<int*>(imageData->GetScalarPointer(i, j, k));
if (i==X1 || j== X2 || k==X3)
{
//Assigning zeros to dummy voxels, these will not be displayed anyways
voxel[0] = 0;
}
else
{
//copying data from I to imagedata voxel
voxel[0] = I[i + X1*j + X1*X2*k];
}
}
}
}
//Setting Up Display Properties
for (int i = 1; i < X1X2X3; i++)
{
compositeOpacity->AddPoint(i, 1);
color->AddRGBPoint(i, double(rand()) / RAND_MAX, double(rand()) / RAND_MAX, double(rand()) / RAND_MAX);
}
renderer->ResetCamera();
renderWindow->Render();
renderWindowInteractor->Start();
getchar();
return 0;
}
Now the expected number of voxels in each dimensions (10 as per the code above), are correctly seen

Possible armadillo mat bug when saving a mat in an external array?

I have a problem which is like this. I want to create an armadillo matrix backed by an array, which is fine and easy to do. However when I try to save the resulting mat in an array of armadillo mats' changes to the underlying c array no longer changes the mat. Example code:
#include<iostream>
#include<armadillo>
using namespace std;
using namespace arma;
int main() {
Mat<float>* test = (Mat<float>*)malloc(sizeof(Mat<float>));
float *Amem = (float*) malloc(4*sizeof(float));
Amem[0] = 0; Amem[1] = 1; Amem[2] = 2; Amem[3] = 3;
Mat<float> A = Mat<float>(Amem, 2, 2, false, false);
test[0] = A;
test[0].print();
Amem[1] = 100;
test[0].print();
A.print();
free(test);
free(Amem);
return 0;
}
When the following code is run, it results in:
test[0] = 0 2
1 3
test[0] = 0 2
1 3
A = 0 2
100 3
Why isn't A and test[0] the same? Is there anyway to make them the same?

Creating vignette filter in opencv?

How we can make vignette filter in opencv? Do we need to implement any algorithm for it or only to play with the values of BGR ? How we can make this type of filters. I saw its implementation here but i didn't understand it clearly . Anyone with complete algorithms guidance and implementation guidance is highly appriciated.
After Abid rehman K answer I tried this in c++
int main()
{
Mat v;
Mat img = imread ("D:\\2.jpg");
img.convertTo(v, CV_32F);
Mat a,b,c,d,e;
c.create(img.rows,img.cols,CV_32F);
d.create(img.rows,img.cols,CV_32F);
e.create(img.rows,img.cols,CV_32F);
a = getGaussianKernel(img.cols,300,CV_32F);
b = getGaussianKernel(img.rows,300,CV_32F);
c = b*a.t();
double minVal;
double maxVal;
cv::minMaxLoc(c, &minVal, &maxVal);
d = c/maxVal;
e = v*d ; // This line causing error
imshow ("venyiet" , e);
cvWaitKey();
}
d is displaying right but e=v*d line is causing runtime error of
OpenCV Error: Assertion failed (type == B.type() && (type == CV_32FC1 || type ==
CV_64FC1 || type == CV_32FC2 || type == CV_64FC2)) in unknown function, file ..
\..\..\src\opencv\modules\core\src\matmul.cpp, line 711
First of all, Abid Rahman K describes the easiest way to go about this filter. You should seriously study his answer with time and attention. Wikipedia's take on Vignetting is also quite clarifying for those that had never heard about this filter.
Browny's implementation of this filter is considerably more complex. However, I ported his code to the C++ API and simplified it so you can follow the instructions yourself.
#include <math.h>
#include <vector>
#include <cv.hpp>
#include <highgui/highgui.hpp>
// Helper function to calculate the distance between 2 points.
double dist(CvPoint a, CvPoint b)
{
return sqrt(pow((double) (a.x - b.x), 2) + pow((double) (a.y - b.y), 2));
}
// Helper function that computes the longest distance from the edge to the center point.
double getMaxDisFromCorners(const cv::Size& imgSize, const cv::Point& center)
{
// given a rect and a line
// get which corner of rect is farthest from the line
std::vector<cv::Point> corners(4);
corners[0] = cv::Point(0, 0);
corners[1] = cv::Point(imgSize.width, 0);
corners[2] = cv::Point(0, imgSize.height);
corners[3] = cv::Point(imgSize.width, imgSize.height);
double maxDis = 0;
for (int i = 0; i < 4; ++i)
{
double dis = dist(corners[i], center);
if (maxDis < dis)
maxDis = dis;
}
return maxDis;
}
// Helper function that creates a gradient image.
// firstPt, radius and power, are variables that control the artistic effect of the filter.
void generateGradient(cv::Mat& mask)
{
cv::Point firstPt = cv::Point(mask.size().width/2, mask.size().height/2);
double radius = 1.0;
double power = 0.8;
double maxImageRad = radius * getMaxDisFromCorners(mask.size(), firstPt);
mask.setTo(cv::Scalar(1));
for (int i = 0; i < mask.rows; i++)
{
for (int j = 0; j < mask.cols; j++)
{
double temp = dist(firstPt, cv::Point(j, i)) / maxImageRad;
temp = temp * power;
double temp_s = pow(cos(temp), 4);
mask.at<double>(i, j) = temp_s;
}
}
}
// This is where the fun starts!
int main()
{
cv::Mat img = cv::imread("stack-exchange-chefs.jpg");
if (img.empty())
{
std::cout << "!!! Failed imread\n";
return -1;
}
/*
cv::namedWindow("Original", cv::WINDOW_NORMAL);
cv::resizeWindow("Original", img.size().width/2, img.size().height/2);
cv::imshow("Original", img);
*/
What img looks like:
cv::Mat maskImg(img.size(), CV_64F);
generateGradient(maskImg);
/*
cv::Mat gradient;
cv::normalize(maskImg, gradient, 0, 255, CV_MINMAX);
cv::imwrite("gradient.png", gradient);
*/
What maskImg looks like:
cv::Mat labImg(img.size(), CV_8UC3);
cv::cvtColor(img, labImg, CV_BGR2Lab);
for (int row = 0; row < labImg.size().height; row++)
{
for (int col = 0; col < labImg.size().width; col++)
{
cv::Vec3b value = labImg.at<cv::Vec3b>(row, col);
value.val[0] *= maskImg.at<double>(row, col);
labImg.at<cv::Vec3b>(row, col) = value;
}
}
cv::Mat output;
cv::cvtColor(labImg, output, CV_Lab2BGR);
//cv::imwrite("vignette.png", output);
cv::namedWindow("Vignette", cv::WINDOW_NORMAL);
cv::resizeWindow("Vignette", output.size().width/2, output.size().height/2);
cv::imshow("Vignette", output);
cv::waitKey();
return 0;
}
What output looks like:
As stated in the code above, by changing the values of firstPt, radius and power you can achieve stronger/weaker artistic effects.
Good luck!
You can do a simple implementation using Gaussian Kernels available in OpenCV.
Load the image, Get its number of rows and columns
Create two Gaussian Kernels of size rows and columns, say A,B. Its variance depends upon your needs.
C = transpose(A)*B, ie multiply a column vector with a row vector such that result array should be same size as that of the image.
D = C/C.max()
E = img*D
See the implementation below (for a grayscale image):
import cv2
import numpy as np
from matplotlib import pyplot as plt
img = cv2.imread('temp.jpg',0)
row,cols = img.shape
a = cv2.getGaussianKernel(cols,300)
b = cv2.getGaussianKernel(rows,300)
c = b*a.T
d = c/c.max()
e = img*d
cv2.imwrite('vig2.png',e)
Below is my result:
Similarly for Color image:
NOTE : Of course, it is centered. You will need to make additional modifications to move focus to other places.
Similar one close to Abid's Answer. But the code is for the colored image
import cv2
import numpy as np
from matplotlib import pyplot as plt
img = cv2.imread('turtle.jpg',1)
rows,cols = img.shape[:2]
zeros = np.copy(img)
zeros[:,:,:] = 0
a = cv2.getGaussianKernel(cols,900)
b = cv2.getGaussianKernel(rows,900)
c = b*a.T
d = c/c.max()
zeros[:,:,0] = img[:,:,0]*d
zeros[:,:,1] = img[:,:,1]*d
zeros[:,:,2] = img[:,:,2]*d
cv2.imwrite('vig2.png',zeros)
Original Image (Taken from Pexels under CC0 Licence)
After Applying Vignette with a sigma of 900 (i.e `cv2.getGaussianKernel(cols,900))
After Applying Vignette with a sigma of 300 (i.e `cv2.getGaussianKernel(cols,300))
Additionally you can focus the vignette effect to the cordinates of your wish by simply shifting the mean of the gaussian to your focus point as follows.
import cv2
import numpy as np
img = cv2.imread('turtle.jpg',1)
fx,fy = 1465,180 # Add your Focus cordinates here
fx,fy = 145,1000 # Add your Focus cordinates here
sigma = 300 # Standard Deviation of the Gaussian
rows,cols = img.shape[:2]
fxn = fx - cols//2 # Normalised temperory vars
fyn = fy - rows//2
zeros = np.copy(img)
zeros[:,:,:] = 0
a = cv2.getGaussianKernel(2*cols ,sigma)[cols-fx:2*cols-fx]
b = cv2.getGaussianKernel(2*rows ,sigma)[rows-fy:2*rows-fy]
c = b*a.T
d = c/c.max()
zeros[:,:,0] = img[:,:,0]*d
zeros[:,:,1] = img[:,:,1]*d
zeros[:,:,2] = img[:,:,2]*d
zeros = add_alpha(zeros)
cv2.imwrite('vig4.png',zeros)
The size of the turtle image is 1980x1200 (WxH). The following is an example focussing at the cordinate 1465,180 (i.e fx,fy = 1465,180) (Note that I have reduced the variance to exemplify the change in focus)
The following is an example focussing at the cordinate 145,1000 (i.e fx,fy = 145,1000)
Here is my c++ implementation of Vignette filter on Colored Image using opencv. It is faster than the accepted answer.
#include "opencv2/core/core.hpp"
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/imgproc/imgproc.hpp"
#include <iostream>
using namespace cv;
using namespace std;
double fastCos(double x){
x += 1.57079632;
if (x > 3.14159265)
x -= 6.28318531;
if (x < 0)
return 1.27323954 * x + 0.405284735 * x * x;
else
return 1.27323954 * x - 0.405284735 * x * x;
}
double dist(double ax, double ay,double bx, double by){
return sqrt((ax - bx)*(ax - bx) + (ay - by)*(ay - by));
}
int main(int argv, char** argc){
Mat src = cv::imread("filename_of_your_image.jpg");
Mat dst = Mat::zeros(src.size(), src.type());
double radius; //value greater than 0,
//greater the value lesser the visible vignette
//for a medium vignette use a value in range(0.5-1.5)
cin << radius;
double cx = (double)src.cols/2, cy = (double)src.rows/2;
double maxDis = radius * dist(0,0,cx,cy);
double temp;
for (int y = 0; y < src.rows; y++) {
for (int x = 0; x < src.cols; x++) {
temp = fastCos(dist(cx, cy, x, y) / maxDis);
temp *= temp;
dst.at<Vec3b>(y, x)[0] =
saturate_cast<uchar>((src.at<Vec3b>(y, x)[0]) * temp);
dst.at<Vec3b>(y, x)[1] =
saturate_cast<uchar>((src.at<Vec3b>(y, x)[1]) * temp );
dst.at<Vec3b>(y, x)[2] =
saturate_cast<uchar>((src.at<Vec3b>(y, x)[2]) * temp);
}
}
imshow ("Vignetted Image", dst);
waitKey(0);
}
Here is a C++ implementation of Vignetting for Grayscale Image
#include "opencv2/opencv.hpp"
#include "opencv2/core/core.hpp"
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/imgproc/imgproc.hpp"
#include <iostream>
using namespace cv;
using namespace std;
int main(int argv, char** argc)
{
Mat test = imread("test.jpg", IMREAD_GRAYSCALE);
Mat kernel_X = getGaussianKernel(test.cols, 100);
Mat kernel_Y = getGaussianKernel(test.rows, 100);
Mat kernel_X_transpose;
transpose(kernel_X, kernel_X_transpose);
Mat kernel = kernel_Y * kernel_X_transpose;
Mat mask_v, proc_img;
normalize(kernel, mask_v, 0, 1, NORM_MINMAX);
test.convertTo(proc_img, CV_64F);
multiply(mask_v, proc_img, proc_img);
convertScaleAbs(proc_img, proc_img);
imshow ("Vignette", proc_img);
waitKey(0);
return 0;
}

Video Stabilization

I 'm researching about Video Stabilization field. I implement a application using OpenCV.
My progress such as:
Surf points extraction
Matching
estimateRigidTransform
warpAffine
But the result video is not be stable. Can anyone help me this problem or provide me some source code link to improve?
Sample video: Hippo video
Here is my code [EDIT]
#include "stdafx.h"
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/imgproc/imgproc.hpp"
#include <iostream>
#include <stdio.h>
#include <opencv2/nonfree/features2d.hpp>
#include <opencv2/opencv.hpp>
const double smooth_level = 0.7;
using namespace cv;
using namespace std;
struct TransformParam
{
TransformParam() {}
TransformParam(double _dx, double _dy, double _da) {
dx = _dx;
dy = _dy;
da = _da;
}
double dx; // translation x
double dy; // translation y
double da; // angle
};
int main( int argc, char** argv )
{
VideoCapture cap ("test12.avi");
Mat cur, cur_grey;
Mat prev, prev_grey;
cap >> prev;
cvtColor(prev, prev_grey, COLOR_BGR2GRAY);
// Step 1 - Get previous to current frame transformation (dx, dy, da) for all frames
vector <TransformParam> prev_to_cur_transform; // previous to current
int k=1;
int max_frames = cap.get(CV_CAP_PROP_FRAME_COUNT);
VideoWriter writeVideo ("stable.avi",0,30,cvSize(prev.cols,prev.rows),true);
Mat last_T;
double avg_dx = 0, avg_dy = 0, avg_da = 0;
Mat smooth_T(2,3,CV_64F);
while(true) {
cap >> cur;
if(cur.data == NULL) {
break;
}
cvtColor(cur, cur_grey, COLOR_BGR2GRAY);
// vector from prev to cur
vector <Point2f> prev_corner, cur_corner;
vector <Point2f> prev_corner2, cur_corner2;
vector <uchar> status;
vector <float> err;
goodFeaturesToTrack(prev_grey, prev_corner, 200, 0.01, 30);
calcOpticalFlowPyrLK(prev_grey, cur_grey, prev_corner, cur_corner, status, err);
// weed out bad matches
for(size_t i=0; i < status.size(); i++) {
if(status[i]) {
prev_corner2.push_back(prev_corner[i]);
cur_corner2.push_back(cur_corner[i]);
}
}
// translation + rotation only
Mat T = estimateRigidTransform(prev_corner2, cur_corner2, false);
// in rare cases no transform is found. We'll just use the last known good transform.
if(T.data == NULL) {
last_T.copyTo(T);
}
T.copyTo(last_T);
// decompose T
double dx = T.at<double>(0,2);
double dy = T.at<double>(1,2);
double da = atan2(T.at<double>(1,0), T.at<double>(0,0));
prev_to_cur_transform.push_back(TransformParam(dx, dy, da));
avg_dx = (avg_dx * smooth_level) + (dx * (1- smooth_level));
avg_dy = (avg_dy * smooth_level) + (dy * (1- smooth_level));
avg_da = (avg_da * smooth_level) + (da * (1- smooth_level));
smooth_T.at<double>(0,0) = cos(avg_da);
smooth_T.at<double>(0,1) = -sin(avg_da);
smooth_T.at<double>(1,0) = sin(avg_da);
smooth_T.at<double>(1,1) = cos(avg_da);
smooth_T.at<double>(0,2) = avg_dx;
smooth_T.at<double>(1,2) = avg_dy;
Mat stable;
warpAffine(prev,stable,smooth_T,prev.size());
Mat canvas = Mat::zeros(cur.rows, cur.cols*2+10, cur.type());
prev.copyTo(canvas(Range::all(), Range(0, prev.cols)));
stable.copyTo(canvas(Range::all(), Range(prev.cols+10, prev.cols*2+10)));
imshow("before and after", canvas);
waitKey(20);
writeVideo.write(stable);
cur.copyTo(prev);
cur_grey.copyTo(prev_grey);
k++;
}
}
First, you can just blur you image. It will helps a bit. Second, you can easily smooth your matrix by simplest implementation of exponential smooth A(t+1) = a*A(t)+(1-a)*A(t+1) and play with a-value in [0;1] range. Third, you can turn off some type of transformations like rotation, shift etc.
Here is code example:
t = estimateRigidTransform(new, old, 0); // 0 means not all transformations (5 of 6)
if(!t.empty()){
// t(Range(0,2), Range(0,2)) = Mat::eye(2, 2, CV_64FC1); // turning off rotation
// t.at<double>(0,2) = 0; t.at<double>(1,2) = 0; // turning off shift dx and dy
tAvrg = tAvrg*a + t*(1-a); // a - smooth level in [0;1] range, play with it
warpAffine(new, stable, tAvrg, Size(new.cols, new.rows));
}