I am attempting to write a naive implementation of the Short-Time Fourier Transform using consecutive FFT frames in time, calculated using the FFTW library, but I am getting a Segmentation fault and cannot work out why.
My code is as below:
// load in audio
AudioFile<double> audioFile;
audioFile.load ("assets/example-audio/file_example_WAV_1MG.wav");
int N = audioFile.getNumSamplesPerChannel();
// make stereo audio mono
double fileDataMono[N];
if (audioFile.isStereo())
for (int i = 0; i < N; i++)
fileDataMono[i] = ( audioFile.samples[0][i] + audioFile.samples[1][i] ) / 2;
// setup stft
// (test transform, presently unoptimized)
int stepSize = 512;
int M = 2048; // fft size
int noOfFrames = (N-(M-stepSize))/stepSize;
// create Hamming window vector
double w[M];
for (int m = 0; m < M; m++) {
w[m] = 0.53836 - 0.46164 * cos( 2*M_PI*m / M );
}
double* input;
// (pads input array if necessary)
if ( (N-(M-stepSize))%stepSize != 0) {
noOfFrames += 1;
int amountOfZeroPadding = stepSize - (N-(M-stepSize))%stepSize;
double ipt[N + amountOfZeroPadding];
for (int i = 0; i < N; i++) // copy values from fileDataMono into input
ipt[i] = fileDataMono[i];
for (int i = 0; i < amountOfZeroPadding; i++)
ipt[N + i] = 0;
input = ipt;
} else {
input = fileDataMono;
}
// compute stft
fftw_complex* stft[noOfFrames];
double frames[noOfFrames][M];
fftw_plan fftPlan;
for (int i = 0; i < noOfFrames; i++) {
stft[i] = (fftw_complex*)fftw_malloc(sizeof(fftw_complex) * M);
for (int m = 0; m < M; m++)
frames[i][m] = input[i*stepSize + m] * w[m];
fftPlan = fftw_plan_dft_r2c_1d(M, frames[i], stft[i], FFTW_ESTIMATE);
fftw_execute(fftPlan);
}
// compute istft
double* outputFrames[noOfFrames];
double output[N];
for (int i = 0; i < noOfFrames; i++) {
outputFrames[i] = (double*)fftw_malloc(sizeof(double) * M);
fftPlan = fftw_plan_dft_c2r_1d(M, stft[i], outputFrames[i], FFTW_ESTIMATE);
fftw_execute(fftPlan);
for (int m = 0; i < M; m++) {
output[i*stepSize + m] += outputFrames[i][m];
}
}
fftw_destroy_plan(fftPlan);
for (int i = 0; i < noOfFrames; i++) {
fftw_free(stft[i]);
fftw_free(outputFrames[i]);
}
// output audio
AudioFile<double>::AudioBuffer outputBuffer;
outputBuffer.resize (1);
outputBuffer[0].resize(N);
outputBuffer[0].assign(output, output+N);
bool ok = audioFile.setAudioBuffer(outputBuffer);
audioFile.setAudioBufferSize (1, N);
audioFile.setBitDepth (16);
audioFile.setSampleRate (8000);
audioFile.save ("out/audioOutput.wav");
The segfault seems to be being raised by the first fftw_malloc when computing the forward STFT.
Thanks in advance!
The relevant bit of code is:
double* input;
if ( (N-(M-stepSize))%stepSize != 0) {
double ipt[N + amountOfZeroPadding];
//...
input = ipt;
}
//...
input[i*stepSize + m];
Your input pointer points at memory that exists only inside the if statement. The closing brace denotes the end of the lifetime of the ipt array. When dereferencing the pointer later, you are addressing memory that no longer exists.
Related
I am trying to multithread a raytracer, and am trying to write a function to pass into the thread. The function throws a stack overflow error, and when I try to heap allocate, all of a sudden I can't write to the array. Any tips?
std::array<std::array<std::array<int,3>,400>,225> idk(std::array<std::array<std::array<int,3>,400>,225> pc,const int img_start,const camera &cam,const hittableList &world,const int imageWidth,const int img_end,const int maxDepth,const int samplesPerPixel,bool fml){
auto pic = std::array<std::array<std::array<int,3>,400>,225> {};
for (int i = img_start; i >= img_end; --i) {
color pixelColour(0, 0, 0);
for (int j = 0; j < 400; j++) {
for (int k = 0; k < samplesPerPixel; k++) {
double u = double(j + randomDouble()) / (imageWidth - 1);
double v = double(i + randomDouble()) / (img_start - 1);
ray r = cam.get_ray(u, v);
pixelColour += rayColor(r, world, maxDepth);
}
pic[i][j] = writeColour(pixelColour, maxDepth);
}
}
fml = true;
return pic;
}
std::array<std::array<std::array<int,3>,400>,225>* idk(std::array<std::array<std::array<int,3>,400>,225> pc,const int img_start,const camera &cam,const hittableList &world,const int imageWidth,const int img_end,const int maxDepth,const int samplesPerPixel,bool fml){
auto* pic = new std::array<std::array<std::array<int,3>,400>,225> {};
for (int i = img_start; i >= img_end; --i) {
color pixelColour(0, 0, 0);
for (int j = 0; j < 400; j++) {
for (int k = 0; k < samplesPerPixel; k++) {
double u = double(j + randomDouble()) / (imageWidth - 1);
double v = double(i + randomDouble()) / (img_start - 1);
ray r = cam.get_ray(u, v);
pixelColour += rayColor(r, world, maxDepth);
}
//this line doesnt work the = is underlined and says: no viable overloas '='
pic[i][j] = writeColour(pixelColour, maxDepth);
}
}
fml = true;
return pic;
}
The C++ standard library requires that the payload of std::array has the same storage duration as the std::array itself.
In other words, you are attempting to place 400 * 255 * 3 ints on your stack, and that is above a run-time limit.
A fix is to use a multidimensional array from a third party library like Boost.MultiArray (part of www.boost.org).
I recently asked question about how to work with element Edit1 dynamically, now I want to ask something about values, which I received from dynamical arrays. First I try to divide image into sectors:
const n=20;
unsigned short i, j, line_length, w = Image1->Width, h = Image1->Height, l = Left + Image1->Left, t = Top + Image1->Top;
unsigned short border = (Width-ClientWidth)/2, topborder = Height-ClientHeight-border;
Image1->Canvas->Pen->Color = clRed;
for (i = 0; i <= n; i++)
{
Image1->Canvas->MoveTo(0, 0);
line_length = w * tan(M_PI/2*i/n);
if (line_length <= h)
Image1->Canvas->LineTo(w, line_length);
else
{
line_length = h * tan(M_PI/2*(1-1.*i/n));
Image1->Canvas->LineTo(line_length, h);
}
}
Then I use regions to count black dots in each sector and I want to add values to element Memo:
HRGN region[n];
TPoint points[3];
points[0] = Point(l + border, t + topborder);
for (i = 0; i < n; i++)
{
for (j = 0; j <= 1; j++)
{
line_length = w * tan(M_PI/2*(i+j)/n);
if (line_length <= h)
points[j+1] = Point(l + border + w, t + topborder + line_length);
else
{
line_length = h * tan(M_PI/2*(1-1.*(i+j)/n));
points[j+1] = Point(l + border + line_length, t + topborder + h);
}
}
region[i] = CreatePolygonRgn(points, 3, ALTERNATE); // or WINDING ?? as u want
}
Byte k;
unsigned __int64 point_count[n] = {0}, points_count = 0;
for(j = 0; j < h; j++)
for (i = 0; i < w; i++)
if (Image1->Canvas->Pixels[i][j] == clBlack)
{
points_count++;
for (k = 0; k < n; k++)
if (PtInRegion(region[k], l + border + i, t + topborder + j))
point_count[k]++;
}
unsigned __int64 sum = 0;
for (i = 0; i < n; i++)
{
sum += point_count[i];
Memo1->Lines->Add(point_count[i]);
}
As i received an advice from one man, in order to allocate an array using a TEdit to specify the array's count I should use, for example DynamicArray:
#include <sysdyn.h>
DynamicArray<HRGN> region;
...
int n = Edit1-> Text.ToInt();
region.Length = n;
I have made the same changes to point_count array:
Byte k;
DynamicArray<unsigned __int64> point_count;
point_count.Length = n;
unsigned __int64 /*point_count[n] = {0},*/ points_count = 0;
...
The problem is that I received different values if I do it dynamically or statically(n=20).
Statically:
Dynamically:
The problem is that I received different values if I do it dynamically or statically(n=20)
There is no difference whatsoever in accessing elements of a static array vs a dynamic array. Your problem has to be elsewhere.
For instance, your static code is initializing all of the array elements to 0, but your dynamic code is not doing that, so they will have random values before your loop then increments them.
Try this:
DynamicArray<unsigned __int64> point_count;
point_count.Length = n;
for(int i = 0; i < n; ++i) {
point_count[i] = 0;
}
...
Alternatively:
DynamicArray<unsigned __int64> point_count;
point_count.Length = n;
ZeroMemory(&point_count[0], sizeof(unsigned __int64) * n);
...
Also, using the Image1->Canvas->Pixels[][] property is very slow. Consider using the Image1->Picture->Bitmap->ScanLine[] property instead for faster access to the raw pixels.
My code seems to have a bug somewhere but I just can't catch it. I'm passing a 2d array to three sequential functions. First function populates it, second function modifies the values to 1's and 0's, the third function counts the 1's and 0's. I can access the array easily inside the first two functions, but I get an access violation at the first iteration of the third one.
Main
text_image_data = new int*[img_height];
for (i = 0; i < img_height; i++) {
text_image_data[i] = new int[img_width];
}
cav_length = new int[numb_of_files];
// Start processing - load each image and find max cavity length
for (proc = 0; proc < numb_of_files; proc++)
{
readImage(filles[proc], text_image_data, img_height, img_width);
threshold = makeBinary(text_image_data, img_height, img_width);
cav_length[proc] = measureCavity(bullet[0], img_width, bullet[1], img_height, text_image_data);
}
Functions
int makeBinary(int** img, int height, int width)
{
int threshold = 0;
unsigned long int sum = 0;
for (int k = 0; k < width; k++)
{
sum = sum + img[1][k] + img[2][k] + img[3][k] + img[4][k] + img[5][k];
}
threshold = sum / (width * 5);
for (int i = 0; i < height; i++)
{
for (int j = 0; j < width; j++)
{
img[i][j] = img[i][j] > threshold ? 1 : 0;
}
}
return threshold;
}
// Count pixels - find length of cavity here
int measureCavity(int &x, int& width, int &y, int &height, int **img)
{
double mean = 1.;
int maxcount = 0;
int pxcount = 0;
int i = x - 1;
int j;
int pxsum = 0;
for (j = 0; j < height - 2; j++)
{
while (mean > 0.0)
{
for (int ii = i; ii > i - 4; ii--)
{
pxsum = pxsum + img[ii][j] + img[ii][j + 1];
}
mean = pxsum / 4.;
pxcount += 2;
i += 2;
pxsum = 0;
}
maxcount = std::max(maxcount, pxcount);
pxcount = 0;
j++;
}
return maxcount;
}
I keep getting an access violation in the measureCavity() function. I'm passing and accessing the array text_image_data the same way as in makeBinary() and readImage(), and it works just fine for those functions. The size is [550][70], I'm getting the error when trying to access [327][0].
Is there a better, more reliable way to pass this array between the functions?
Here is my code for creating the hough accumulator for lines in image :
void hough_lines_acc(cv::Mat img_a_edges, std::vector<std::vector<int> > &hough_acc) {
for (size_t r = 0; r < img_a_edges.rows; r++) {
for (size_t c = 0; c < img_a_edges.cols; c++) {
int theta = static_cast<int> (std::atan2(r, c) * 180 / M_PI);
int rho = static_cast<int> ((c * cos(theta)) + (r * sin(theta)));
if (theta < -90) theta = -90;
if (theta > 89) theta = 89;
++hough_acc[abs(rho)][theta];
}
}
cv::Mat img_mat(hough_acc.size(), hough_acc[0].size(), CV_8U);
std::cout << hough_acc.size() << " " << hough_acc[0].size() << std::endl;
for (size_t i = 0; i < hough_acc.size(); i++) {
for (size_t j = 0; j < hough_acc[0].size(); j++) {
img_mat.at<int> (i,j) = hough_acc[i][j];
}
}
imwrite("../output/ps1-2-b-1.png", img_mat);
}
theta varies from -90 to 89. I am getting negative rho values. Right now I am just replacing the negative who with a positive one but am not getting a correct answer. What do I do to the negative rho? Please explain the answer.
theta = arctan (y / x)
rho = x * cos(theta) + y * sin(theta)
Edited code :
bool hough_lines_acc(cv::Mat img_a_edges, std::vector<std::vector<int> > &hough_acc,\
std::vector<double> thetas, std::vector<double> rhos, int rho_resolution, int theta_resolution) {
int img_w = img_a_edges.cols;
int img_h = img_a_edges.rows;
int max_votes = 0;
int min_votes = INT_MAX;
for (size_t r = 0; r < img_h; r++) {
for (size_t c = 0; c < img_w; c++) {
if(img_a_edges.at<int>(r, c) == 255) {
for (size_t i = 0; i < thetas.size(); i++) {
thetas[i] = (thetas[i] * M_PI / 180);
double rho = ( (c * cos(thetas[i])) + (r * sin(thetas[i])) );
int buff = ++hough_acc[static_cast<int>(abs(rho))][static_cast<int>(i)];
if (buff > max_votes) {
max_votes = buff;
}
if (buff < min_votes) {
min_votes = buff;
}
}
}
}
}
double div = static_cast<double>(max_votes) / 255;
int threshold = 10;
int possible_edge = round(static_cast<double>(max_votes) / div) - threshold;
props({
{"max votes", max_votes},
{"min votes", min_votes},
{"scale", div}
});
// needed for scaling intensity for contrast
// not sure if I am doing it correctly
for (size_t r = 0; r < hough_acc.size(); r++) {
for (size_t c = 0; c < hough_acc[0].size(); c++) {
double val = hough_acc[r][c] / div;
if (val < 0) {
val = 0;
}
hough_acc[r][c] = static_cast<int>(val);
}
}
cv::Mat img_mat = cv::Mat(hough_acc.size(), hough_acc[0].size(), CV_8UC1, cv::Scalar(0));
for (size_t i = 0; i < hough_acc.size(); i++) {
for (size_t j = 0; j < hough_acc[0].size(); j++) {
img_mat.at<uint8_t> (i,j) = static_cast<uint8_t>(hough_acc[i][j]);
}
}
imwrite("../output/ps1-2-b-1.png", img_mat);
return true;
}
Still not correct output. What is the error here?
atan2 of two positive numbers... should not be giving you negative angles, it should only be giving you a range of 0-90
also for the hough transform, I think you want everything relative to one point (ie 0,0 in this case). I think for that you would actually want to make theta=90-atan2(r,c)
Admittedly though, I am a bit confused as I thought you had to encode line direction, rather than just "edge pt". ie I thought at each edge point you had to provide a discrete array of guessed line trajectories and calculate rho and theta for each one and throw all of those into your accumulator. As is... I am not sure what you are calculating.
I am trying to make an alphatrimmed filter in openCV library. My code is not working properly and the resultant image is not looking as image after filtering.
The filter should work in the following way.
Chossing some (array) of pixels in my example it is 9 pixels '3x3' window.
Ordering them in increasing way.
Cutting our 'array' both sides for alpha-2.
calculating arithmetic mean of remaining pixels and inserting them in proper place.
int alphatrimmed(Mat img, int alpha)
{
Mat img9 = img.clone();
const int start = alpha/2 ;
const int end = 9 - (alpha/2);
//going through whole image
for (int i = 1; i < img.rows - 1; i++)
{
for (int j = 1; j < img.cols - 1; j++)
{
uchar element[9];
Vec3b element3[9];
int k = 0;
int a = 0;
//selecting elements for window 3x3
for (int m = i -1; m < i + 2; m++)
{
for (int n = j - 1; n < j + 2; n++)
{
element3[a] = img.at<Vec3b>(m*img.cols + n);
a++;
for (int c = 0; c < img.channels(); c++)
{
element[k] += img.at<Vec3b>(m*img.cols + n)[c];
}
k++;
}
}
//comparing and sorting elements in window (uchar element [9])
for (int b = 0; b < end; b++)
{
int min = b;
for (int d = b + 1; d < 9; d++)
{
if (element[d] < element[min])
{
min = d;
const uchar temp = element[b];
element[b] = element[min];
element[min] = temp;
const Vec3b temporary = element3[b];
element3[b] = element3[min];
element3[min] = temporary;
}
}
}
// index in resultant image( after alpha-trimmed filter)
int result = (i - 1) * (img.cols - 2) + j - 1;
for (int l = start ; l < end; l++)
img9.at<Vec3b>(result) += element3[l];
img9.at<Vec3b>(result) /= (9 - alpha);
}
}
namedWindow("AlphaTrimmed Filter", WINDOW_AUTOSIZE);
imshow("AlphaTrimmed Filter", img9);
return 0;
}
Without actual data, it's somewhat of a guess, but an uchar can't hold the sum of 3 channels. It works modulo 256 (at least on any platform OpenCV supports).
The proper solution is std::sort with a proper comparator for your Vec3b :
void L1(Vec3b a, Vec3b b) { return a[0]+a[1]+a[2] < b[0]+b[1]+b[2]; }