As I mentioned in title do you know how to flip an ID3D10Texture2D object horizontal/vertical ?
I used this code to take screenshot and save it to a file.
ID3D10Resource *backbufferRes;
renderTargetView->GetResource(&backbufferRes);
ID3D10Texture2D *mRenderedTexture;
// Create our texture
D3D10_TEXTURE2D_DESC texDesc;
texDesc.ArraySize = 1;
texDesc.BindFlags = 0;
texDesc.CPUAccessFlags = 0;
texDesc.Format = DXGI_FORMAT_R8G8B8A8_UNORM;
texDesc.Width = 640; // must be same as backbuffer
texDesc.Height = 480; // must be same as backbuffer
texDesc.MipLevels = 1;
texDesc.MiscFlags = 0;
texDesc.SampleDesc.Count = 1;
texDesc.SampleDesc.Quality = 0;
texDesc.Usage = D3D10_USAGE_DEFAULT;
d3d10Device->CreateTexture2D(&texDesc, 0, &mRenderedTexture);
d3d10Device->CopyResource(mRenderedTexture, backbufferRes);
D3DX10FilterTexture(mRenderedTexture, 0, D3DX10_FILTER_MIRROR_U);
D3DX10SaveTextureToFile(mRenderedTexture, D3DX10_IFF_PNG, L"test.png");
D3DX10FilterTexture(mRenderedTexture, 0, D3DX10_FILTER_MIRROR_U); line doesnt mirror my texture. Any suggestions ?
In your shader do 1-u to flip horizontally or 1-v to flip vertically.
Edit: If you aren't actually doing any rendering then there are far better ways to do image manipulation. However if you want to do it manually you will have to use map and flip the data round yourself.
You could do that as follows (The code is not tested so please excuse any compile errors):
D3D10Resource *backbufferRes;
renderTargetView->GetResource(&backbufferRes);
ID3D10Texture2D *mRenderedTexture;
// Create our texture
D3D10_TEXTURE2D_DESC texDesc;
texDesc.ArraySize = 1;
texDesc.BindFlags = 0;
texDesc.CPUAccessFlags = 0;
texDesc.Format = DXGI_FORMAT_R8G8B8A8_UNORM;
texDesc.Width = 640; // must be same as backbuffer
texDesc.Height = 480; // must be same as backbuffer
texDesc.MipLevels = 1;
texDesc.MiscFlags = 0;
texDesc.SampleDesc.Count = 1;
texDesc.SampleDesc.Quality = 0;
texDesc.Usage = D3D10_USAGE_DEFAULT;
d3d10Device->CreateTexture2D(&texDesc, 0, &mRenderedTexture);
d3d10Device->CopyResource(mRenderedTexture, backbufferRes);
D3D10_MAPPED_TEXTURE2D d3d10MT = { 0 };
mRenderedTexture->Map( 0, D3D10_MAP_READ_WRITE, 0, &d3d10MT );
unsigned int* pPix = (unsigned int)d3d10MT.pData;
int rows = 0;
int rowsMax = height;
while( rows < rowsMax )
{
unsigned int* pRowStart = pPix + (rows * width);
unsigned int* pRowEnd = pRowStart + width;
std::reverse( pRowStart, pRowEnd );
rows++;
}
mRenderedTexture->Unmap();
D3DX10SaveTextureToFile(mRenderedTexture, D3DX10_IFF_PNG, L"test.png");
From the doc btw:
D3DX10_FILTER_MIRROR_U Pixels off the edge of the texture on the
u-axis should be mirrored, not wrapped.
So that only counts for the pixels round the edge when you are filtering the image.
Related
I want to calculate perimeter of a white blob in a 512*512 dimension binary image. Image will have only one blob. I used following code earlier in OpenCV 3 but somehow it doesn't work in OpenCV 4.2. IplImage
is deprecated in latest version. And I cannot pass Mat object directly to cvFindContours function. I am new to opencv and I don't know how does it work. Other related questions regarding perimeter are still unanswered.
To summaries, following works in opencv 3 but does not work in current opencv version (4.2).
int getPerimeter(unsigned char* inImagePtr, int inW, int inH)
{
int sumEven = 0; int sumOdd = 0;
int sumCorner = 0; int prevCode = 0;
//create a mat input Image
cv::Mat inImage(inH, inW, CV_8UC1, inImagePtr);
//create four connected structuring element
cv::Mat element = cv::Mat::zeros(3, 3, CV_8UC1);
element.data[1] = 1; element.data[3] = 1;
element.data[4] = 1; element.data[5] = 1;
element.data[7] = 1;
//erode input image
cv::Mat erodeImage;
erode(inImage, erodeImage, element);
//Invert eroded Image
cv::threshold(erodeImage, erodeImage, 0, 255, THRESH_BINARY_INV);
//multiply with original binary Image to get the edge Image
cv::Mat edge = erodeImage.mul(inImage);
//Get chain code of the blob
CvChain* chain = 0;
CvMemStorage* storage = 0;
storage = cvCreateMemStorage(0);
auto temp = new IplImage(edge);
cvFindContours(temp, storage, (CvSeq**)(&chain), sizeof(*chain), CV_RETR_EXTERNAL, CV_CHAIN_CODE);
delete temp;
for (; chain != NULL; chain = (CvChain*)chain->h_next)
{
CvSeqReader reader;
int i, total = chain->total;
cvStartReadSeq((CvSeq*)chain, &reader, 0);
for (i = 0; i < total; i++)
{
char code;
CV_READ_SEQ_ELEM(code, reader);
if (code % 2 == 0)
sumEven++;
else
sumOdd++;
if (i > 0) {
if (code != prevCode)
sumCorner++;
}
prevCode = code;
}
}
float perimeter = (float)sumEven*0.980 + (float)sumOdd*1.406 - (float)sumCorner*0.091;
return (roundf(perimeter));
}
This worked just fine for me!
int getPerimeter(unsigned char* inImagePtr, int inW, int inH) {
// create a mat input Image
cv::Mat inImage(inH, inW, CV_8UC1, inImagePtr);
// create four connected structuring element
cv::Mat element = cv::Mat::zeros(3, 3, CV_8UC1);
element.data[1] = 1;
element.data[3] = 1;
element.data[4] = 1;
element.data[5] = 1;
element.data[7] = 1;
// erode input image
cv::Mat erodeImage;
erode(inImage, erodeImage, element);
// Invert eroded Image
cv::threshold(erodeImage, erodeImage, 0, 255, THRESH_BINARY_INV);
// multiply with original binary Image to get the edge Image
cv::Mat edge = erodeImage.mul(inImage);
vector<vector<Point>> contours;
findContours(edge, contours, RETR_EXTERNAL, CHAIN_APPROX_SIMPLE); // Retrieve only external contour
int preValue[2];
int nextValue[2];
int sumEven = 0;
int sumOdd = 0;
//vector<Point>::iterator itr;
for (int ii = 0; ii < contours[0].size(); ii++) {
Point pt = contours[0].at(ii);
preValue[0] = pt.x;
preValue[1] = pt.y;
if (ii != contours[0].size() - 1) {
Point pt_next = contours[0].at(ii + 1);
nextValue[0] = pt_next.x;
nextValue[1] = pt_next.y;
} else {
Point pt_next = contours[0].at(0);
nextValue[0] = pt_next.x;
nextValue[1] = pt_next.y;
}
if ((preValue[0] == nextValue[0]) or (preValue[1] == nextValue[1])) {
sumEven = sumEven + abs(nextValue[0] - preValue[0]) + abs(nextValue[1] - preValue[1]);
} else {
sumOdd = sumOdd + abs(nextValue[0] - preValue[0]);
}
}
int sumCorner = contours[0].size() - 1;
float perimeter = round(sumEven * 0.980 + sumOdd * 1.406 - sumCorner * 0.091);
return (roundf(perimeter));
}
i am learning directx11 these days. and i have been stuck in compute shader section.
so i made four resource and three corresponding view.
immutable input buffer = {1,1,1,1,1} / SRV
immutable input buffer = {2,2,2,2,2} / SRV
output buffer / UAV
staging buffer for reading / No View
and i succeeded to create all things, and dispatch cs function, and copy data from output buffer to staging buffer, and i read/check data.
// INPUT BUFFER1--------------------------------------------------
const int dataSize = 5;
D3D11_BUFFER_DESC vb_dest;
vb_dest.ByteWidth = sizeof(float) * dataSize;
vb_dest.StructureByteStride = sizeof(float);
vb_dest.BindFlags = D3D11_BIND_SHADER_RESOURCE;
vb_dest.Usage = D3D11_USAGE_IMMUTABLE;
vb_dest.CPUAccessFlags = 0;
vb_dest.MiscFlags = 0;
float v1_float[dataSize] = { 1,1,1,1,1 };
D3D11_SUBRESOURCE_DATA v1_data;
v1_data.pSysMem = static_cast<void*>(v1_float);
device->CreateBuffer(
&vb_dest,
&v1_data,
valueBuffer1.GetAddressOf());
D3D11_SHADER_RESOURCE_VIEW_DESC srv_desc;
srv_desc.Format = DXGI_FORMAT_R32_FLOAT;
srv_desc.ViewDimension = D3D11_SRV_DIMENSION_BUFFER;
srv_desc.Buffer.FirstElement = 0;
srv_desc.Buffer.NumElements = dataSize;
srv_desc.Buffer.ElementWidth = sizeof(float);
device->CreateShaderResourceView(
valueBuffer1.Get(),
&srv_desc,
inputSRV1.GetAddressOf());
// INPUT BUFFER2-----------------------------------------------------------
float v2_float[dataSize] = { 2,2,2,2,2 };
D3D11_SUBRESOURCE_DATA v2_data;
v2_data.pSysMem = static_cast<void*>(v2_float);
device->CreateBuffer(
&vb_dest,
&v2_data,
valueBuffer2.GetAddressOf());
device->CreateShaderResourceView(
valueBuffer2.Get(),
&srv_desc,
inputSRV2.GetAddressOf());
// OUTPUT BUFFER-----------------------------------------------------------
D3D11_BUFFER_DESC ov_desc;
ov_desc.ByteWidth = sizeof(float) * dataSize;
ov_desc.StructureByteStride = sizeof(float);
ov_desc.BindFlags = D3D11_BIND_UNORDERED_ACCESS;
ov_desc.Usage = D3D11_USAGE_DEFAULT;
ov_desc.CPUAccessFlags = 0;
ov_desc.MiscFlags = 0;
device->CreateBuffer(
&ov_desc,
nullptr,
outputResource.GetAddressOf());
D3D11_UNORDERED_ACCESS_VIEW_DESC outputUAV_desc;
outputUAV_desc.Format = DXGI_FORMAT_R32_FLOAT;
outputUAV_desc.ViewDimension = D3D11_UAV_DIMENSION_BUFFER;
outputUAV_desc.Buffer.FirstElement = 0;
outputUAV_desc.Buffer.NumElements = dataSize;
outputUAV_desc.Buffer.Flags = 0;
device->CreateUnorderedAccessView(
outputResource.Get(),
&outputUAV_desc,
outputUAV.GetAddressOf());
// BUFFER FOR COPY-----------------------------------------------------------
D3D11_BUFFER_DESC rb_desc;
rb_desc.ByteWidth = sizeof(float) * dataSize;
rb_desc.StructureByteStride = sizeof(float);
rb_desc.Usage = D3D11_USAGE_STAGING;
rb_desc.CPUAccessFlags = D3D11_CPU_ACCESS_READ;
rb_desc.BindFlags = 0;
rb_desc.MiscFlags = 0;
device->CreateBuffer(
&rb_desc,
nullptr,
readResource.GetAddressOf());
// DISPATCH and COPY and GET DATA
dContext->CSSetShaderResources(0, 1, inputSRV1.GetAddressOf());
dContext->CSSetShaderResources(1, 1, inputSRV2.GetAddressOf());
dContext->CSSetUnorderedAccessViews(0, 1, outputUAV.GetAddressOf(), nullptr);
dContext->CSSetShader(cs.Get(), nullptr, 0);
dContext->Dispatch(1, 1, 1);
dContext->CopyResource(readResource.Get(), outputResource.Get());
D3D11_MAPPED_SUBRESOURCE mappedResource2;
ZeroMemory(&mappedResource2, sizeof(D3D11_MAPPED_SUBRESOURCE));
R_CHECK(dContext->Map(readResource.Get(), 0, D3D11_MAP_READ, 0, &mappedResource2));
float* data = static_cast<float*>(mappedResource2.pData);
for (int i = 0; i < 5; ++i)
{
int a = data[i];
}
and this is compute shader code
StructuredBuffer<float> inputA : register(t0);
StructuredBuffer<float> inputB : register(t1);
RWStructuredBuffer<float> output : register(u0);
[numthreads(5, 1, 1)]
void main(int3 id : SV_DispatchThreadID)
{
output[id.x] = inputA[id.x] + inputB[id.x];
}
in CS, it's adding two input buffer data and store into output buffer.
so expected answer would be {3,3,3,3,3}.
but the result is {3,0,0,0,0} only first idx has proper answer.
any advice would be amazing.
dContext->CopyResource(readResource.Get(), outputResource.Get());
D3D11_MAPPED_SUBRESOURCE mappedResource2;
ZeroMemory(&mappedResource2, sizeof(D3D11_MAPPED_SUBRESOURCE));
R_CHECK(dContext->Map(readResource.Get(), 0, D3D11_MAP_READ, 0, &mappedResource2));
float* data = static_cast<float*>(mappedResource2.pData);
for (int i = 0; i < 5; ++i)
{
int a = data[i];
}
this code should be like this.
CopyResource();
Map();
Declare and allocate 'data'
zeromemory(data);
memcopy(data, resource's pointer);
unMap();
for some reason, i have to use the memcopy instead of just reading resource directly with the pointer that i get from mapping.
I have a buffer and the vertices have a stride. How do I specify this in metal? I cannot seem to find any example.
Thanks!
Check out MTLVertexBufferLayoutDescriptor, which is part of MTLRenderPipelineDescriptor. It has the stride member.
Below is the example of settings up three vertex attributes stored in one vertex buffer in the interleaved fashion. The stride is set next to the end: vertexDescriptor.layouts[0].stride = 32;
MTLRenderPipelineDescriptor *pipelineDescriptor = [[MTLRenderPipelineDescriptor alloc] init];
MTLVertexDescriptor *vertexDescriptor = [MTLVertexDescriptor vertexDescriptor];
vertexDescriptor.attributes[0].offset = 0;
vertexDescriptor.attributes[0].format = MTLVertexFormatFloat3; // position
vertexDescriptor.attributes[0].bufferIndex = 0;
vertexDescriptor.attributes[1].offset = 12;
vertexDescriptor.attributes[1].format = MTLVertexFormatFloat3; // normal
vertexDescriptor.attributes[1].bufferIndex = 0;
vertexDescriptor.attributes[2].offset = 24;
vertexDescriptor.attributes[2].format = MTLVertexFormatFloat2; // texCoords
vertexDescriptor.attributes[2].bufferIndex = 0;
vertexDescriptor.layouts[0].stepRate = 1;
vertexDescriptor.layouts[0].stepFunction = MTLVertexStepFunctionPerVertex;
vertexDescriptor.layouts[0].stride = 32;
pipelineDescriptor.vertexDescriptor = vertexDescriptor;
I want to apply on OpenCV a K Means to a region of an image not squared or a rectangle. For example the source image is:
now I select a custom mask:
and apply K Means with K = 3:
Obviously without considering the bounds (white).
Instead, what I can do with OpenCV is K Means but considering the bounds:
And that messes out my final image because black is considered one colour.
Do you have any clue?
Thank you in advance.
Quick and dirty solution.
vector<Vec3b> points;
vector<Point> locations;
for( int y = 0; y < src.rows; y++) {
for( int x = 0; x < src.cols; x++) {
if ( (int)mask.at<unsigned char>(y,x) != 0 ) {
points.push_back(src.at<Vec3b>(y,x));
locations.push_back(Point(x,y));
}
}
}
Mat kmeanPoints(points.size(), 3, CV_32F);
for( int y = 0; y < points.size(); y++ ) {
for( int z = 0; z < 3; z++) {
kmeanPoints.at<float>(y, z) = points[y][z];
}
}
Mat labels;
Mat centers;
kmeans(kmeanPoints, 4, labels, TermCriteria(CV_TERMCRIT_ITER|CV_TERMCRIT_EPS, 10, 0.1), 10, cv::KMEANS_PP_CENTERS, centers);
Mat final = Mat::zeros( src.size(), src.type() );
Vec3b tempColor;
for(int i = 0; i<locations.size(); i++) {
int cluster_idx = labels.at<int>(i,0);
tempColor[0] = centers.at<float>(cluster_idx, 0);
tempColor[1] = centers.at<float>(cluster_idx, 1);
tempColor[2] = centers.at<float>(cluster_idx, 2);
final.at<Vec3b>(locations[i]) = tempColor;
}
Assuming that you have an input RGB image called img(here) and a one-channel mask called mask(here), here is the snippet to prepare your k-means computation :
int nbClasses = 3; // or whatever you want
cv::TermCriteria myCriteria(cv::TermCriteria::MAX_ITER + cv::TermCriteria::EPS, 10, 1.0);
cv::Mat labels, centers, result;
img.convertTo(data, CV_32F);
// reshape into 3 columns (one per channel, in BGR order) and as many rows as the total number of pixels in img
data = data.reshape(1, data.total());
If you want to apply a normal k-means (without mask) :
// apply k-means
cv::kmeans(data, nbClasses, labels, myCriteria, 3, cv::KMEANS_PP_CENTERS, centers);
// reshape both to a single column of Vec3f pixels
centers = centers.reshape(3, centers.rows);
data = data.reshape(3, data.rows);
// replace pixel values with their center value
cv::Vec3f *p = data.ptr<cv::Vec3f>();
for (size_t i = 0; i < data.rows; i++)
{
int center_id = labels.at<int>(i);
p[i] = centers.at<cv::Vec3f>(center_id);
}
// back to 2D image
data = data.reshape(3, img.rows);
// optional conversion to uchar
data.convertTo(result, CV_8U);
The result is here.
But, if you want instead to apply a masked k-means :
int nbWhitePixels = cv::countNonZero(mask);
cv::Mat dataMasked = cv::Mat(nbWhitePixels, 3, CV_32F, cv::Scalar(0));
cv::Mat maskFlatten = mask.reshape(1, mask.total());
// filter data by the mask
int idx = 0;
for (int k = 0; k < mask.total(); k++)
{
int val = maskFlatten.at<uchar>(k, 0);
if (val != 0)
{
float val0 = data.at<float>(k, 0);
float val1 = data.at<float>(k, 1);
float val2 = data.at<float>(k, 2);
dataMasked.at<float>(idx,0) = val0;
dataMasked.at<float>(idx,1) = val1;
dataMasked.at<float>(idx,2) = val2;
idx++;
}
}
// apply k-means
cv::kmeans(dataMasked, nbClasses, labels, myCriteria, 3, cv::KMEANS_PP_CENTERS, centers);
// reshape to a single column of Vec3f pixels
centers = centers.reshape(3, centers.rows);
dataMasked = dataMasked.reshape(3, dataMasked.rows);
data = data.reshape(3, data.rows);
// replace pixel values with their center value, only for pixels in mask
cv::Vec3f *p = data.ptr<cv::Vec3f>();
idx = 0;
for (size_t i = 0; i < data.rows; i++)
{
if (maskFlatten.at<uchar>(i, 0) != 0)
{
int center_id = labels.at<int>(idx);
p[i] = centers.at<cv::Vec3f>(center_id);
idx++;
}
//else
// p[i] = cv::Vec3f(0, 0, 0);
}
// back to 2d, and uchar
data = data.reshape(3, img.rows);
data.convertTo(result, CV_8U);
You will have now this result.
If you let commented the else part, you will keep initial pixels outside the mask, whereas if you uncomment it, you will convert them into black pixels, like here.
I am in the process of implementing Lucas-Kanade algorithm using OpenCv. Even though my intention is to track facial features, as a first cut i am getting all the good features using cvGoodFeatures api and using this points as the input, i am trying to track the points using Lucas-Kanade algorithm.
Now the scenario is if i start moving the objects captured by camera near to the edges of the frame(not out of the frame) what i observe is that LK algorithm starts giving me points that are either outside the frame or having negative values.
Please let me know whether i am doing a wrong implementation or is this behavior expected from LK tracking method. Also i am attaching my code at the end of this post for reference.
Regards,
Sujil C
IplImage *image = 0,
*grey = 0,
*prev_grey = 0,
*pyramid = 0,
*prev_pyramid = 0,
*swap_temp = 0,
*velx = 0,
*vely = 0;
const int MAX_COUNT = 20;
CvPoint2D32f* points[2] = {0,0}, *swap_points;
char* status = 0;
int lkcount = 0;
int detectGoodFeature = 0;
int flags = 0;
CvPoint pt;
CvSize currentFrameSize;
CvPoint2D32f* processLKFrame(IplImage* frame, int &pointCount)
{
int win_size = 15;
int level = 5;
int i, k;
// If frame size has changed, release all resources (they will be reallocated further on)
if ( (grey && ((currentFrameSize.width != cvGetSize(frame).width) || (currentFrameSize.height != cvGetSize(frame).height))))
{
// Release images
cvReleaseImage(&grey);
cvReleaseImage(&prev_grey);
cvReleaseImage(&pyramid);
cvReleaseImage(&prev_pyramid);
cvReleaseImage(&velx);
cvReleaseImage(&vely);
// Release buffers
cvFree(&(points[0]));
cvFree(&(points[1]));
cvFree(&status);
// Zerofiy grey so initialization will occur
grey = NULL;
}
// Initialize
if( !grey )
{
/* allocate all the buffers */
currentFrameSize = cvGetSize(frame);
grey = cvCreateImage( currentFrameSize, 8, 1 );
prev_grey = cvCreateImage( currentFrameSize, 8, 1 );
pyramid = cvCreateImage( currentFrameSize, 8, 1 );
prev_pyramid = cvCreateImage( currentFrameSize, 8, 1 );
velx = cvCreateImage(currentFrameSize, 32, 1);
vely = cvCreateImage(currentFrameSize, 32, 1);
points[0] = (CvPoint2D32f*)cvAlloc(MAX_COUNT*sizeof(points[0][0]));
points[1] = (CvPoint2D32f*)cvAlloc(MAX_COUNT*sizeof(points[0][0]));
status = (char*)cvAlloc(MAX_COUNT);
flags = 0;
}
printf("Current Frame Size : Width:%d Height:%d\n", currentFrameSize.width, currentFrameSize.height );
cvCopy( frame, grey, 0 );
if (detectGoodFeature) {
/* automatic initialization */
IplImage* eig = cvCreateImage( cvGetSize(grey), 32, 1 );
IplImage* temp = cvCreateImage( cvGetSize(grey), 32, 1 );
double quality = 0.01;
double min_distance = 10;
lkcount = MAX_COUNT;
cvGoodFeaturesToTrack( grey, eig, temp, points[1], &lkcount,
quality, min_distance, 0, 3, 0, 0.04 );
cvFindCornerSubPix( grey, points[1], lkcount,
cvSize(win_size,win_size), cvSize(-1,-1),
cvTermCriteria(CV_TERMCRIT_ITER|CV_TERMCRIT_EPS,20,0.03));
cvReleaseImage( &eig );
cvReleaseImage( &temp );
}
else if( lkcount > 0 )
{
//For debugging points
printf("==============================================================================================================\n");
printf("Input Points:");
for (int i = 0; i < lkcount; i++) {
printf("(%f, %f)", points[0][i].x, points[0][i].y);
}
printf("\n");
// Calc movement of tracked points
cvCalcOpticalFlowPyrLK( prev_grey, grey, prev_pyramid, pyramid,
points[0], points[1], lkcount, cvSize(win_size,win_size), level, status, 0,
cvTermCriteria(CV_TERMCRIT_ITER|CV_TERMCRIT_EPS,20,0.03), 0 );
//For debugging points
printf("Tracked Points:");
for (int i = 0; i < lkcount; i++) {
printf("(%f, %f),", points[1][i].x, points[1][i].y);
}
printf("\n");
printf("==============================================================================================================\n");
}
CV_SWAP( prev_grey, grey, swap_temp );
CV_SWAP( prev_pyramid, pyramid, swap_temp );
CV_SWAP( points[0], points[1], swap_points );
detectGoodFeature = 0;
pointCount = lkcount;
return points[0];
}