void ConvolveRow(CImageOf<T> buffer, CFloatImage kernel, T* dst,
int n, T minVal, T maxVal)
{
CShape kShape = kernel.Shape();
int kX = kShape.width;
int kY = kShape.height;
CShape bShape = buffer.Shape();
int nB = bShape.nBands;
for (int i = 0; i < n; i++)
{
for (int b = 0; b < nB; b++)
{
float sum = 0.0f;
for (int k = 0; k < kY; k++)
{
float* kPtr = &kernel.Pixel(0, k, 0);
T* bPtr = &buffer.Pixel(i, k, b);
for (int l = 0; l < kX; l++, bPtr += nB)
sum += kPtr[l] * bPtr[0];
}
*dst++ = (T) __max(minVal, __min(maxVal, sum));
}
}
}
/******************* TO DO 5 *********************
* NormalizeBlend:
* INPUT:
* acc: input image whose alpha channel (4th channel) contains
* normalizing weight values
* img: where output image will be stored
* OUTPUT:
* normalize r,g,b values (first 3 channels) of acc and store it into img
*/
static void NormalizeBlend(CFloatImage& acc, CByteImage& img)
{
// *** BEGIN TODO ***
// fill in this routine..
int width = acc.Shape().width;
int height = acc.Shape().height;
for (int i=0;i<width;i++){
for (int j=0;j<height;j++){
float w = acc.Pixel(i,j,3);
img.Pixel(i,j,3) = 255;
if (w > 0){
img.Pixel(i,j,0) = acc.Pixel(i,j,0) / w;
img.Pixel(i,j,1) = acc.Pixel(i,j,1) / w;
img.Pixel(i,j,2) = acc.Pixel(i,j,2) / w;
} else {
img.Pixel(i,j,0) = 0;
img.Pixel(i,j,1) = 0;
img.Pixel(i,j,2) = 0;
}
}
}
// *** END TODO ***
}
static
void ConvolveRow2D(CFloatImage& buffer, CFloatImage& kernel, float dst[],
int n)
{
CShape kShape = kernel.Shape();
int kX = kShape.width;
int kY = kShape.height;
CShape bShape = buffer.Shape();
int nB = bShape.nBands;
for (int i = 0; i < n; i++)
{
for (int b = 0; b < nB; b++)
{
float sum = 0.0f;
for (int k = 0; k < kY; k++)
{
float* kPtr = &kernel.Pixel(0, k, 0);
float* bPtr = &buffer.Pixel(i, k, b);
for (int l = 0; l < kX; l++, bPtr += nB)
sum += kPtr[l] * bPtr[0];
}
*dst++ = sum;
}
}
}
void Convolve(CImageOf<T> src, CImageOf<T>& dst,
CFloatImage kernel)
{
// Determine the shape of the kernel and source image
CShape kShape = kernel.Shape();
CShape sShape = src.Shape();
// Allocate the result, if necessary
dst.ReAllocate(sShape, false);
if (sShape.width * sShape.height * sShape.nBands == 0)
return;
// Do the convolution
for (int y = 0; y < sShape.height; y++)
for (int x = 0; x < sShape.width; x++)
for (int c = 0; c < sShape.nBands; c++)
{
double sum = 0;
for (int kx = 0; kx < kShape.width; kx++)
for (int ky = 0; ky < kShape.height; ky++)
if ((x-kernel.origin[0]+kx >= 0) && (x-kernel.origin[0]+kx < sShape.width) && (y-kernel.origin[1]+ky >= 0) && (y-kernel.origin[1]+ky < sShape.height))
sum += kernel.Pixel(kx,ky,0) * src.Pixel(x-kernel.origin[0]+kx,y-kernel.origin[1]+ky,c);
dst.Pixel(x,y,c) = (T) __max(dst.MinVal(), __min(dst.MaxVal(), sum));
}
}
void rotation()
{
CFloatImage matrixImage = GetImageFromMatrix((float *)featureMatrix, 10, 10);
CTransform3x3 translationNegative;
CTransform3x3 translationPositive;
CTransform3x3 rotation;
CFloatImage postHomography;
Feature f;
f.x = 6;
f.y = 5;
f.angleRadians = PI;
translationNegative = translationNegative.Translation(f.x,f.y);
translationPositive = translationPositive.Translation(-f.x,-f.y);
rotation = rotation.Rotation(-f.angleRadians * 180/ PI);
WarpGlobal(matrixImage, postHomography, translationNegative*rotation*translationPositive, eWarpInterpLinear, eWarpInterpNearest);
for (int i = 0; i < postHomography.Shape().height; i++)
{
for (int j = 0; j < postHomography.Shape().width; j++)
{
printf("%.0f\t", postHomography.Pixel(j, i, 0));
}
printf("\n");
}
}
// Convert CFloatImage to CByteImage.
void convertToByteImage(CFloatImage &floatImage, CByteImage &byteImage) {
CShape sh = floatImage.Shape();
//printf("%d\n", floatImage.Shape().nBands);
//printf("%d\n", byteImage.Shape().nBands);
assert(floatImage.Shape().nBands == min(byteImage.Shape().nBands, 3));
for (int y=0; y<sh.height; y++) {
for (int x=0; x<sh.width; x++) {
for (int c=0; c<sh.nBands; c++) {
float value = floor(255*floatImage.Pixel(x,y,c) + 0.5f);
if (value < byteImage.MinVal()) {
value = byteImage.MinVal();
}
else if (value > byteImage.MaxVal()) {
value = byteImage.MaxVal();
}
// We have to flip the image and reverse the color
// channels to get it to come out right. How silly!
byteImage.Pixel(x,sh.height-y-1,sh.nBands-c-1) = (uchar) value;
}
}
}
}
// convert float disparity image into a color image using jet colormap
void float2color(CFloatImage fimg, CByteImage &img, float dmin, float dmax)
{
CShape sh = fimg.Shape();
int width = sh.width, height = sh.height;
sh.nBands = 3;
img.ReAllocate(sh);
float scale = 1.0 / (dmax - dmin);
for (int y = 0; y < height; y++) {
for (int x = 0; x < width; x++) {
float f = fimg.Pixel(x, y, 0);
int r = 0;
int g = 0;
int b = 0;
if (f != INFINITY) {
float val = scale * (f - dmin);
jet(val, r, g, b);
}
img.Pixel(x, y, 0) = b;
img.Pixel(x, y, 1) = g;
img.Pixel(x, y, 2) = r;
}
}
}
// Compute silly example features. This doesn't do anything
// meaningful, but may be useful to use as an example.
void dummyComputeFeatures(CFloatImage &image, FeatureSet &features) {
CShape sh = image.Shape();
Feature f;
for (int y=0; y<sh.height; y++) {
for (int x=0; x<sh.width; x++) {
double r = image.Pixel(x,y,0);
double g = image.Pixel(x,y,1);
double b = image.Pixel(x,y,2);
if ((int)(255*(r+g+b)+0.5) % 100 == 1) {
// If the pixel satisfies this meaningless criterion,
// make it a feature.
f.type = 1;
f.id += 1;
f.x = x;
f.y = y;
f.data.resize(1);
f.data[0] = r + g + b;
features.push_back(f);
}
}
}
}
//TO DO---------------------------------------------------------------------
//Loop through the image to compute the harris corner values as described in class
// srcImage: grayscale of original image
// harrisImage: populate the harris values per pixel in this image
void computeHarrisValues(CFloatImage &srcImage, CFloatImage &harrisImage)
{
int h = srcImage.Shape().height;
int w = srcImage.Shape().width;
CFloatImage A(srcImage.Shape());
CFloatImage B(srcImage.Shape());
CFloatImage C(srcImage.Shape());
GetHarrisComponents(srcImage, A, B, C);
for (int y = 0; y < h; y++) {
for (int x = 0; x < w; x++) {
double determinant = A.Pixel(x, y, 0) * C.Pixel(x, y, 0) - B.Pixel(x, y, 0)* B.Pixel(x, y, 0);
double trace = A.Pixel(x, y, 0) + C.Pixel(x, y, 0);
float *pixel = &harrisImage.Pixel(x, y, 0);
if (trace == 0)
{
*pixel = 0;
}
else
{
*pixel = determinant / trace;
}
}
}
}
void ComputeHarrisFeatures(CFloatImage &image, FeatureSet &features)
{
//Create grayscale image used for Harris detection
CFloatImage grayImage=ConvertToGray(image);
//Create image to store Harris values
CFloatImage harrisImage(image.Shape().width,image.Shape().height,1);
//Create image to store local maximum harris values as 1, other pixels 0
CByteImage harrisMaxImage(image.Shape().width,image.Shape().height,1);
//compute Harris values puts harris values at each pixel position in harrisImage.
//You'll need to implement this function.
computeHarrisValues(grayImage, harrisImage);
// Threshold the harris image and compute local maxima. You'll need to implement this function.
computeLocalMaxima(harrisImage,harrisMaxImage);
// Prints out the harris image for debugging purposes
CByteImage tmp(harrisImage.Shape());
convertToByteImage(harrisImage, tmp);
WriteFile(tmp, "harris.tga");
// TO DO--------------------------------------------------------------------
//Loop through feature points in harrisMaxImage and fill in information needed for
//descriptor computation for each point above a threshold. We fill in id, type,
//x, y, and angle.
CFloatImage A(grayImage.Shape());
CFloatImage B(grayImage.Shape());
CFloatImage C(grayImage.Shape());
CFloatImage partialX(grayImage.Shape());
CFloatImage partialY(grayImage.Shape());
GetHarrisComponents(grayImage, A, B, C, &partialX, &partialY);
int featureCount = 0;
for (int y=0;y<harrisMaxImage.Shape().height;y++) {
for (int x=0;x<harrisMaxImage.Shape().width;x++) {
// Skip over non-maxima
if (harrisMaxImage.Pixel(x, y, 0) == 0)
continue;
//TO DO---------------------------------------------------------------------
// Fill in feature with descriptor data here.
Feature f;
f.type = 2;
f.id = featureCount++;
f.x = x;
f.y = y;
f.angleRadians = GetCanonicalOrientation(x, y, A, B, C, partialX, partialY);
//atan(partialY.Pixel(x, y, 0)/partialX.Pixel(x, y, 0));
// Add the feature to the list of features
features.push_back(f);
}
}
}
void MotionToColor(CFloatImage motim, CByteImage &colim, float maxmotion)
{
CShape sh = motim.Shape();
int width = sh.width, height = sh.height;
colim.ReAllocate(CShape(width, height, 3));
int x, y;
// determine motion range:
float maxx = -999, maxy = -999;
float minx = 999, miny = 999;
float maxrad = -1;
for (y = 0; y < height; y++) {
for (x = 0; x < width; x++) {
float fx = motim.Pixel(x, y, 0);
float fy = motim.Pixel(x, y, 1);
if (unknown_flow(fx, fy))
continue;
maxx = __max(maxx, fx);
maxy = __max(maxy, fy);
minx = __min(minx, fx);
miny = __min(miny, fy);
float rad = sqrt(fx * fx + fy * fy);
maxrad = __max(maxrad, rad);
}
}
printf("max motion: %.4f motion range: u = %.3f .. %.3f; v = %.3f .. %.3f\n",
maxrad, minx, maxx, miny, maxy);
if (maxmotion > 0) // i.e., specified on commandline
maxrad = maxmotion;
if (maxrad == 0) // if flow == 0 everywhere
maxrad = 1;
if (verbose)
fprintf(stderr, "normalizing by %g\n", maxrad);
for (y = 0; y < height; y++) {
for (x = 0; x < width; x++) {
float fx = motim.Pixel(x, y, 0);
float fy = motim.Pixel(x, y, 1);
uchar *pix = &colim.Pixel(x, y, 0);
if (unknown_flow(fx, fy)) {
pix[0] = pix[1] = pix[2] = 0;
} else {
computeColor(fx/maxrad, fy/maxrad, pix);
}
}
}
}
void ConvolveSeparable(CImageOf<T> src, CImageOf<T>& dst,
CFloatImage x_kernel, CFloatImage y_kernel,
float scale, float offset,
int decimate, int interpolate)
{
// Allocate the result, if necessary
CShape dShape = src.Shape();
if (decimate > 1)
{
dShape.width = (dShape.width + decimate-1) / decimate;
dShape.height = (dShape.height + decimate-1) / decimate;
}
dst.ReAllocate(dShape, false);
// Allocate the intermediate images
CImageOf<T> tmpImg1(src.Shape());
CImageOf<T> tmpImg2(src.Shape());
// Create a proper vertical convolution kernel
CFloatImage v_kernel(1, y_kernel.Shape().width, 1);
for (int k = 0; k < y_kernel.Shape().width; k++)
v_kernel.Pixel(0, k, 0) = y_kernel.Pixel(k, 0, 0);
v_kernel.origin[1] = y_kernel.origin[0];
// Perform the two convolutions
Convolve(src, tmpImg1, x_kernel, 1.0f, 0.0f);
Convolve(tmpImg1, tmpImg2, v_kernel, scale, offset);
// Downsample or copy
for (int y = 0; y < dShape.height; y++)
{
T* sPtr = &tmpImg2.Pixel(0, y * decimate, 0);
T* dPtr = &dst.Pixel(0, y, 0);
int nB = dShape.nBands;
for (int x = 0; x < dShape.width; x++)
{
for (int b = 0; b < nB; b++)
dPtr[b] = sPtr[b];
sPtr += decimate * nB;
dPtr += nB;
}
}
interpolate++; // to get rid of "unused parameter" warning
}
// get min and max (non-INF) values
void getMinMax(CFloatImage fimg, float& vmin, float& vmax)
{
CShape sh = fimg.Shape();
int width = sh.width, height = sh.height;
vmin = INFINITY;
vmax = -INFINITY;
for (int y = 0; y < height; y++) {
for (int x = 0; x < width; x++) {
float f = fimg.Pixel(x, y, 0);
if (f == INFINITY)
continue;
vmin = min(f, vmin);
vmax = max(f, vmax);
}
}
}
KernelInit::KernelInit()
{
static float k_11[2] = {0.5f, 0.5f};
static float k_121[3] = {0.25f, 0.5f, 0.25f};
static float k_14641[5] = {0.0625f, 0.25f, 0.375f, 0.25f, 0.0625f};
static float k_8ptFP[8] = {-0.044734f, -0.059009f, 0.156544f, 0.449199f,
0.449199f, 0.156544f, -0.059009f, -0.044734f};
// The following are derived as fix-point /256 fractions of the above:
// -12, -15, 40, 115
static float k_8ptI [8] = {-0.04687500f, -0.05859375f, 0.15625000f, 0.44921875f,
0.44921875f, 0.15625000f, -0.05859375f, -0.04687500f};
ConvolveKernel_121.ReAllocate(CShape(3, 1, 1), k_121, false, 3);
ConvolveKernel_121.origin[0] = -1;
ConvolveKernel_14641.ReAllocate(CShape(5, 1, 1), k_14641, false, 5);
ConvolveKernel_14641.origin[0] = -2;
ConvolveKernel_8tapLowPass.ReAllocate(CShape(8, 1, 1), k_8ptI, false, 8);
ConvolveKernel_8tapLowPass.origin[0] = -4;
}
//Loop through the image to determine suitable feature points
// srcImage: image with Harris values
// destImage: Assign 1 to local maximum in 3x3 window that are above a given
// threshold, 0 otherwise
void computeLocalMaxima(CFloatImage &srcImage,CByteImage &destImage)
{
int w = srcImage.Shape().width; // image width
int h = srcImage.Shape().height; // image height
//float threshold = .024;
float threshold = .01; // threshold value for identifying features
// Declare additional variables
float max; // harris value to check as local max
int newX, newY; // (x,y) coordinate for pixel in 5x5 sliding window
int j; // int for iterating through 5x5 window
// Loop through 'srcImage' and determine suitable feature points that
// fit the following criteria:
// - harris value c is greater than a predefined threshold
// - c is a local maximum in a 5x5 neighborhood
for (int y = 0; y < h; y++) {
for (int x = 0; x < w; x++) {
max = srcImage.Pixel(x,y,0);
// If harris value is greater than a predefined threshold check
// if value is a local maximum in a 5x5 neighborhood.
if (max > threshold) {
for (j = 0; j < 25; j++) {
find5x5Index(x,y,j,&newX,&newY);
if(srcImage.Shape().InBounds(newX, newY) && srcImage.Pixel(newX, newY, 0) > max) {
destImage.Pixel(x,y,0) = 0;
break;
}
}
if (j != 25)
continue;
destImage.Pixel(x,y,0) = 1;
} else {
destImage.Pixel(x,y,0) = 0;
}
}
}
}
void ConvolveSeparable(CImageOf<T> src, CImageOf<T>& dst,
CFloatImage x_kernel, CFloatImage y_kernel,
int subsample)
{
// Allocate the result, if necessary
CShape dShape = src.Shape();
if (subsample > 1)
{
dShape.width = (dShape.width + subsample-1) / subsample;
dShape.height = (dShape.height + subsample-1) / subsample;
}
dst.ReAllocate(dShape, false);
// Allocate the intermediate images
CImageOf<T> tmpImg1(src.Shape());
CImageOf<T> tmpImg2(src.Shape());
// Create a proper vertical convolution kernel
CFloatImage v_kernel(1, y_kernel.Shape().width, 1);
for (int k = 0; k < y_kernel.Shape().width; k++)
v_kernel.Pixel(0, k, 0) = y_kernel.Pixel(k, 0, 0);
v_kernel.origin[1] = y_kernel.origin[0];
// Perform the two convolutions
Convolve(src, tmpImg1, x_kernel);
Convolve(tmpImg1, tmpImg2, v_kernel);
// Downsample or copy
for (int y = 0; y < dShape.height; y++)
{
T* sPtr = &tmpImg2.Pixel(0, y * subsample, 0);
T* dPtr = &dst.Pixel(0, y, 0);
int nB = dShape.nBands;
for (int x = 0; x < dShape.width; x++)
{
for (int b = 0; b < nB; b++)
dPtr[b] = sPtr[b];
sPtr += subsample * nB;
dPtr += nB;
}
}
}
CFloatImage GetXWindowAroundPixel(CFloatImage srcImage, int x, int y, int size)
{
float *matrix = new float[size * size];
for(int row=(y-(size-1)/2); row<=(y+(size-1)/2); row++)
{
for(int col=(x-(size-1)/2);col<=(x+(size-1)/2);col++)
{
if(row<0 || row>=srcImage.Shape().height || col<0 || col>=srcImage.Shape().width)
{
matrix[(row-(y-(size-1)/2))*size + (col-(x-(size-1)/2))] = 0.;
}
else
{
matrix[(row-(y-(size-1)/2))*size + (col-(x-(size-1)/2))] = srcImage.Pixel(col, row, 0);
}
}
}
return GetImageFromMatrix(matrix, size, size);
}
// Convert Fl_Image to CFloatImage.
bool convertImage(const Fl_Image *image, CFloatImage &convertedImage) {
if (image == NULL) {
return false;
}
// Let's not handle indexed color images.
if (image->count() != 1) {
return false;
}
int w = image->w();
int h = image->h();
int d = image->d();
// Get the image data.
const char *const *data = image->data();
int index = 0;
for (int y=0; y<h; y++) {
for (int x=0; x<w; x++) {
if (d < 3) {
// If there are fewer than 3 channels, just use the
// first one for all colors.
convertedImage.Pixel(x,y,0) = ((uchar) data[0][index]) / 255.0f;
convertedImage.Pixel(x,y,1) = ((uchar) data[0][index]) / 255.0f;
convertedImage.Pixel(x,y,2) = ((uchar) data[0][index]) / 255.0f;
}
else {
// Otherwise, use the first 3.
convertedImage.Pixel(x,y,0) = ((uchar) data[0][index]) / 255.0f;
convertedImage.Pixel(x,y,1) = ((uchar) data[0][index+1]) / 255.0f;
convertedImage.Pixel(x,y,2) = ((uchar) data[0][index+2]) / 255.0f;
}
index += d;
}
}
return true;
}
void featuresFromImage(Feature* f, CFloatImage img, int width, int height)
{
vector<double, std::allocator<double>>::iterator it;
f->data.clear();
for(int y=0; y<height; y++)
{
for(int x=0; x<width; x++)
{
f->data.push_back(img.Pixel(x,y,0));
}
}
}
/******************* TO DO 5 *********************
* NormalizeBlend:
* INPUT:
* acc: input image whose alpha channel (4th channel) contains
* normalizing weight values
* img: where output image will be stored
* OUTPUT:
* normalize r,g,b values (first 3 channels) of acc and store it into img
*/
static void NormalizeBlend(CFloatImage& acc, CByteImage& img)
{
// BEGIN TODO
// fill in this routine..
// divide the total weight for every pixel
CShape shacc=acc.Shape();
int widthacc=shacc.width;
int heightacc=shacc.height;
for (int ii=0;ii<widthacc;ii++)
{
for (int jj=0;jj<heightacc;jj++)
{
if (acc.Pixel(ii,jj,3)>0)
{
img.Pixel(ii,jj,0)=(int)(acc.Pixel(ii,jj,0)/acc.Pixel(ii,jj,3));
img.Pixel(ii,jj,1)=(int)(acc.Pixel(ii,jj,1)/acc.Pixel(ii,jj,3));
img.Pixel(ii,jj,2)=(int)(acc.Pixel(ii,jj,2)/acc.Pixel(ii,jj,3));
}
else
{
img.Pixel(ii,jj,0)=0;
img.Pixel(ii,jj,1)=0;
img.Pixel(ii,jj,2)=0;
}
}
}
// END TODO
}
void Convolve(CImageOf<T> src, CImageOf<T>& dst,
CFloatImage kernel,
float scale, float offset)
{
// Determine the shape of the kernel and row buffer
CShape kShape = kernel.Shape();
CShape sShape = src.Shape();
CShape bShape(sShape.width + kShape.width, kShape.height, sShape.nBands);
int bWidth = bShape.width * bShape.nBands;
// Allocate the result, if necessary, and the row buffer
dst.ReAllocate(sShape, false);
CFloatImage buffer(bShape);
if (sShape.width * sShape.height * sShape.nBands == 0)
return;
CFloatImage output(CShape(sShape.width, 1, sShape.nBands));
// Fill up the row buffer initially
for (int k = 0; k < kShape.height; k++)
FillRowBuffer(&buffer.Pixel(0, k, 0), src, kernel, k, bWidth);
// Determine if clipping is required
// (we assume up-conversion to float never requires clipping, i.e.,
// floats have the highest dynamic range)
T minVal = dst.MinVal();
T maxVal = dst.MaxVal();
if (minVal <= buffer.MinVal() && maxVal >= buffer.MaxVal())
minVal = maxVal = 0;
// Process each row
for (int y = 0; y < sShape.height; y++)
{
// Do the convolution
ConvolveRow2D(buffer, kernel, &output.Pixel(0, 0, 0),
sShape.width);
// Scale, offset, and type convert
ScaleAndOffsetLine(&output.Pixel(0, 0, 0), &dst.Pixel(0, y, 0),
sShape.width * sShape.nBands,
scale, offset, minVal, maxVal);
// Shift up the row buffer and fill the last line
if (y < sShape.height-1)
{
int k;
for (k = 0; k < kShape.height-1; k++)
memcpy(&buffer.Pixel(0, k, 0), &buffer.Pixel(0, k+1, 0),
bWidth * sizeof(float));
FillRowBuffer(&buffer.Pixel(0, k, 0), src, kernel, y+k+1, bWidth);
}
}
}
double GetCanonicalOrientation(int x, int y, CFloatImage A, CFloatImage B, CFloatImage C, CFloatImage partialX, CFloatImage partialY)
{
float aPixel = A.Pixel(x, y, 0);
float bPixel = B.Pixel(x, y, 0);
float cPixel = C.Pixel(x, y, 0);
/*double a = 1;
double b = -(aPixel+cPixel);
double c = (aPixel * cPixel - pow((double)bPixel, 2.));*/
//double lambda = (- b + sqrt(pow((double)b, 2.) - 4.*a*c)) / (2.*a);
double lambda = 1./2. *((aPixel+cPixel) + sqrt(4.*pow((double)bPixel,2.) + pow(((double)aPixel - cPixel), 2.)));
double yComponent = aPixel - lambda - bPixel;
double xComponent = cPixel - lambda - bPixel;
/*y = -b
x = a - lambd
*/
if (xComponent == 0.)
{
return (partialY.Pixel(x, y, 0) > 0)? PI/2. : -PI/2.;
}
double first = aPixel*xComponent + bPixel*yComponent;
double second = bPixel*xComponent + cPixel*yComponent;
double first_precision = pow((first -lambda * xComponent), 2.);
double second_precision = pow((second - lambda * yComponent), 2.);
//Sanity check for eigenvalues: this confirms our given eigenvalue is
//computed correctly
if (first_precision > .0000001 || second_precision > .0000001 )
{
int z = 3;
}
return (partialX.Pixel(x, y, 0) > 0)? atan(-bPixel/(aPixel-lambda)) : atan(-bPixel/(aPixel-lambda)) + PI;
//return (partialX.Pixel(x, y, 0) > 0)? atan(yComponent/xComponent) : atan(yComponent/xComponent) + PI;
}
void WarpLocal(CImageOf<T> src, CImageOf<T>& dst,
CFloatImage uv, bool relativeCoords,
EWarpInterpolationMode interp, float cubicA)
{
// Check that dst is of the right shape
CShape sh(uv.Shape().width, uv.Shape().height, src.Shape().nBands);
dst.ReAllocate(sh);
// Allocate a row buffer for coordinates
int n = sh.width;
std::vector<float> rowBuf;
rowBuf.resize(n*2);
// Precompute the cubic interpolant
if (interp == eWarpInterpCubic)
InitializeCubicLUT(cubicA);
// Process each row
for (int y = 0; y < sh.height; y++)
{
float *uvP = &uv .Pixel(0, y, 0);
float *xyP = (relativeCoords) ? &rowBuf[0] : uvP;
T *dstP = &dst.Pixel(0, y, 0);
// Convert to absolute coordinates if necessary
if (relativeCoords)
{
for (int x = 0; x < n; x++)
{
xyP[2*x+0] = x + uvP[2*x+0];
xyP[2*x+1] = y + uvP[2*x+1];
}
}
// Resample the line
WarpLine(src, dstP, xyP, n, sh.nBands, interp, src.MinVal(), src.MaxVal());
}
}
cv::Mat FlowIOOpenCVWrapper::read(std::string path) {
CFloatImage flow;
ReadFlowFile(flow, path.c_str());
int rows = flow.Shape().height;
int cols = flow.Shape().width;
assert(rows > 0);
assert(cols > 0);
assert(flow.Shape().nBands == 2);
cv::Mat matFlow(rows, cols, CV_32FC2, cv::Scalar(0, 0));
for (int i = 0; i < rows; i++) {
for (int j = 0; j < cols; j++) {
matFlow.at<cv::Vec2f>(i, j)[0] = flow.Pixel(j, i, 0);
matFlow.at<cv::Vec2f>(i, j)[1] = flow.Pixel(j, i, 1);
}
}
return matFlow;
}
bool isLocalMax(CFloatImage srcImage, int x, int y)
{
int width = srcImage.Shape().width;
int height = srcImage.Shape().height;
float centerPixel = srcImage.Pixel(x, y, 0);
for (int row = 0; row < 5; row++)
{
for (int col = 0; col < 5; col++)
{
int xOffset = x - 2 + col;
int yOffset = y - 2 + row;
if (xOffset == x && yOffset == y)
{
continue;
}
float pixelAtOffset;
if (xOffset < 0 || yOffset < 0 || xOffset >= width || yOffset >= height)
{
pixelAtOffset = 0.;
}
else
{
pixelAtOffset = srcImage.Pixel(xOffset, yOffset, 0);
}
if (pixelAtOffset >= centerPixel)
{
return false;
}
}
}
return true;
}
void subsample(Feature* f, int imgSize, CFloatImage gaussianImage)
{
vector<double, std::allocator<double>>::iterator it;
CFloatImage img = featureToImage(*f, imgSize, imgSize);
CFloatImage blurredImg(img.Shape());
Convolve(img, blurredImg, gaussianImage);
featuresFromImage(f,blurredImg,imgSize,imgSize);
int count = 0;
for(int y=0; y<imgSize; y++)
{
for(int x=0; x<imgSize; x++)
{
if(x%2 == 0 || y%2 == 0)
{
f->data.erase(f->data.begin() + count);
}
else
{
count++;
}
}
}
}
// Compute features using Harris corner detection method
void ComputeHarrisFeatures(CFloatImage &image, FeatureSet &features)
{
// Create grayscale image used for Harris detection
CFloatImage grayImage = ConvertToGray(image);
// Create image to store Harris values
CFloatImage harrisImage(image.Shape().width,image.Shape().height,1);
// Create image to store local maximum harris values as 1, other pixels 0
CByteImage harrisMaxImage(image.Shape().width,image.Shape().height,1);
// Create image to store orientation values
CFloatImage orientationImage(image.Shape().width, image.Shape().height, 1);
// Compute the harris score at each pixel position, storing the result in in harrisImage.
computeHarrisValues(grayImage, harrisImage, orientationImage);
// Threshold the harris image and compute local maxima.
computeLocalMaxima(harrisImage,harrisMaxImage);
// Save images
CByteImage tmp(harrisImage.Shape());
CByteImage tmp2(harrisImage.Shape());
convertToByteImage(harrisImage, tmp);
convertToByteImage(grayImage, tmp2);
WriteFile(tmp2, "grayImg.tga");
WriteFile(tmp, "harris.tga");
WriteFile(harrisMaxImage, "harrisMax.tga");
// Loop through feature points in harrisMaxImage and fill in id, type, x, y, and angle
// information needed for descriptor computation for each feature point, then add them
// to feature set
int id = 0;
for (int y=0; y < harrisMaxImage.Shape().height; y++) {
for (int x=0; x < harrisMaxImage.Shape().width; x++) {
if (harrisMaxImage.Pixel(x, y, 0) == 1) {
Feature f;
f.id = id;
f.type = 2;
f.x = x;
f.y = y;
f.angleRadians = orientationImage.Pixel(x,y,0);
features.push_back(f);
id++;
}
}
}
}
KernelInit::KernelInit()
{
static float k_11[2] = {0.5f, 0.5f};
static float k_121[3] = {0.25f, 0.5f, 0.25f};
static float k_14641[5] = {0.0625f, 0.25f, 0.375f, 0.25f, 0.0625f};
static float k_8ptFP[8] = {-0.044734f, -0.059009f, 0.156544f, 0.449199f,
0.449199f, 0.156544f, -0.059009f, -0.044734f};
// The following are derived as fix-point /256 fractions of the above:
// -12, -15, 40, 115
static float k_8ptI [8] = {-0.04687500f, -0.05859375f, 0.15625000f, 0.44921875f,
0.44921875f, 0.15625000f, -0.05859375f, -0.04687500f};
static float k_7x7[49] = { 1.0, 4.0, 7.0, 10.0, 7.0, 4.0, 1.0,
4.0, 12.0, 26.0, 33.0, 26.0, 12.0, 4.0,
7.0, 26.0, 55.0, 71.0, 55.0, 26.0, 7.0,
10.0, 33.0, 71.0, 91.0, 71.0, 33.0, 10.0,
7.0, 26.0, 55.0, 71.0, 55.0, 26.0, 7.0,
4.0, 12.0, 26.0, 33.0, 26.0, 12.0, 4.0,
1.0, 4.0, 7.0, 10.0, 7.0, 4.0, 1.0 };
for (int i = 0; i < 49; i++) {
k_7x7[i] /= 1115.0;
}
ConvolveKernel_121.ReAllocate(CShape(3, 1, 1), k_121, false, 3);
ConvolveKernel_121.origin[0] = 1;
ConvolveKernel_14641.ReAllocate(CShape(5, 1, 1), k_14641, false, 5);
ConvolveKernel_14641.origin[0] = 2;
ConvolveKernel_8tapLowPass.ReAllocate(CShape(8, 1, 1), k_8ptI, false, 8);
ConvolveKernel_8tapLowPass.origin[0] = 4;
ConvolveKernel_7x7.ReAllocate(CShape(7, 7, 1), k_7x7, false, 7);
/* Sobel filters */
static float k_SobelX[9] = { -1, 0, 1,
-2, 0, 2,
-1, 0, 1 };
static float k_SobelY[9] = { -1, -2, -1,
0, 0, 0,
1, 2, 1 };
ConvolveKernel_SobelX.ReAllocate(CShape(3, 3, 1), k_SobelX, false, 3);
ConvolveKernel_SobelX.origin[0] = 1;
ConvolveKernel_SobelX.origin[1] = 1;
ConvolveKernel_SobelY.ReAllocate(CShape(3, 3, 1), k_SobelY, false, 3);
ConvolveKernel_SobelY.origin[0] = 1;
ConvolveKernel_SobelY.origin[1] = 1;
}
// TO DO---------------------------------------------------------------------
// Loop through the harrisImage to threshold and compute the local maxima in a neighborhood
// srcImage: image with Harris values
// destImage: Assign 1 to a pixel if it is above a threshold and is the local maximum in 3x3 window, 0 otherwise.
// You'll need to find a good threshold to use.
void computeLocalMaxima(CFloatImage &srcImage,CByteImage &destImage)
{
int width = srcImage.Shape().width;
int height = srcImage.Shape().height;
double mean, stdDev;
double sum = 0;
double squareSum = 0;
for (int y = 0; y < height; y++) {
for (int x = 0; x < width; x++) {
float pixel = srcImage.Pixel(x, y, 0);
if (!(pixel >= 0 || pixel < 0))
{
auto error = "TRUE";
}
sum += srcImage.Pixel(x, y, 0);
}
}
mean = sum / (float)(width * height);
for (int y = 0; y < height; y++) {
for (int x = 0; x < width; x++) {
squareSum += pow((srcImage.Pixel(x, y, 0) - mean), 2.);
}
}
stdDev = sqrt(squareSum / (float)(width * height - 1));
int count = 0;
for (int y = 0; y < height; y++) {
for (int x = 0; x < width; x++) {
unsigned char *pixel = &destImage.Pixel(x, y, 0);
if (srcImage.Pixel(x, y, 0) >= 3.*stdDev + mean && isLocalMax(srcImage, x, y))
{
count++;
*pixel = 1;
}
else
{
*pixel = 0;
}
}
}
}
void makeNonoccMask(CFloatImage disp0, CFloatImage disp0y, CFloatImage disp1,
int dir, float thresh, CByteImage &mask)
{
CShape sh = disp0.Shape();
int width = sh.width, height = sh.height;
if (sh != disp1.Shape())
throw CError("shapes differ");
int ydisps = (sh == disp0y.Shape());
mask.ReAllocate(sh);
mask.ClearPixels();
int x, y;
for (y = 0; y < height; y++) {
for (x = 0; x < width; x++) {
float dx = disp0.Pixel(x, y, 0);
float dy = (ydisps ? disp0y.Pixel(x, y, 0) : 0.0);
if (dx == INFINITY) // unknown
continue;
mask.Pixel(x, y, 0) = 128; // occluded
// find nonocc
int x1 = (int)round(x + dir * dx);
int y1 = (int)round(y + dy);
if (x1 < 0 || x1 >= width || y1 < 0 || y1 >= height)
continue;
float dx1 = disp1.Pixel(x1, y1, 0);
float diff = dx - dx1;
if (fabs(diff) > thresh)
continue; // fails cross checking -- occluded
mask.Pixel(x, y, 0) = 255; // cross-checking OK
}
}
}