The below code helps me to convert OpenGL output to JPEG image using libjpg but the resultant image is flipped vertical...
The code works perfect but the final image is flipped I dont know why ?!
unsigned char *pdata = new unsigned char[width*height*3];
glReadPixels(0, 0, width, height, GL_RGB, GL_UNSIGNED_BYTE, pdata);
FILE *outfile;
if ((outfile = fopen("sample.jpeg", "wb")) == NULL) {
printf("can't open %s");
exit(1);
}
struct jpeg_compress_struct cinfo;
struct jpeg_error_mgr jerr;
cinfo.err = jpeg_std_error(&jerr);
jpeg_create_compress(&cinfo);
jpeg_stdio_dest(&cinfo, outfile);
cinfo.image_width = width;
cinfo.image_height = height;
cinfo.input_components = 3;
cinfo.in_color_space = JCS_RGB;
jpeg_set_defaults(&cinfo);
/*set the quality [0..100] */
jpeg_set_quality (&cinfo, 100, true);
jpeg_start_compress(&cinfo, true);
JSAMPROW row_pointer;
int row_stride = width * 3;
while (cinfo.next_scanline < cinfo.image_height) {
row_pointer = (JSAMPROW) &pdata[cinfo.next_scanline*row_stride];
jpeg_write_scanlines(&cinfo, &row_pointer, 1);
}
jpeg_finish_compress(&cinfo);
fclose(outfile);
jpeg_destroy_compress(&cinfo);
OpenGL's coordinate system has the origin in the lower left corner of the image. LIBJPEG assumes that the origin of the image is in the upper left corner of the image. Make the following change to fix your code:
while (cinfo.next_scanline < cinfo.image_height)
{
row_pointer = (JSAMPROW) &pdata[(cinfo.image_height-1-cinfo.next_scanline)*row_stride];
jpeg_write_scanlines(&cinfo, &row_pointer, 1);
}
Related
I have to fill the ffmpeg AVFrame->data from a cairo surface pixel data. I have this code:
/* Image info and pixel data */
width = cairo_image_surface_get_width( surface );
height = cairo_image_surface_get_height( surface );
stride = cairo_image_surface_get_stride( surface );
pix = cairo_image_surface_get_data( surface );
for( row = 0; row < height; row++ )
{
data = pix + row * stride;
for( col = 0; col < width; col++ )
{
img->video_frame->data[0][row * img->video_frame->linesize[0] + col] = data[0];
img->video_frame->data[1][row * img->video_frame->linesize[1] + col] = data[1];
//img->video_frame->data[2][row * img->video_frame->linesize[2] + col] = data[2];
data += 4;
}
img->video_frame->pts++;
}
But the colors in the exported video are wrong. The original heart is red. Can someone point me in the right direction? The encode.c example is useless sadly and on the Internet there is a lot of confusion about Y, Cr and Cb which I really don't understand. Please feel free to ask for more details. Many thanks.
You need to use libswscale to convert the source image data from RGB24 to YUV420P.
Something like:
int width = cairo_image_surface_get_width( surface );
int height = cairo_image_surface_get_height( surface );
int stride = cairo_image_surface_get_stride( surface );
uint8_t *pix = cairo_image_surface_get_data( surface );
uint8_t *data[1] = { pix };
int linesize[1] = { stride };
struct SwsContext *sws_ctx = sws_getContext(width, height, AV_PIX_FMT_RGB24 ,
width, height, AV_PIX_FMT_YUV420P,
SWS_BILINEAR, NULL, NULL, NULL);
sws_scale(sws_ctx, data, linesize, 0, height,
img->video_frame->data, img->video_frame->linesize);
sws_freeContext(sws_ctx);
See the example here: scaling_video
I have currently the problem that a library creates a DX11 texture with BGRA pixel format.
But the displaying library can only display RGBA correctly. (This means the colors are swapped in the rendered image)
After looking around I found a simple for-loop to solve the problem, but the performance is not very good and scales bad with higher resolutions. I'm new to DirectX and maybe I just missed a simple function to do the converting.
// Get the image data
unsigned char* pDest = view->image->getPixels();
// Prepare source texture
ID3D11Texture2D* pTexture = static_cast<ID3D11Texture2D*>( tex );
// Get context
ID3D11DeviceContext* pContext = NULL;
dxDevice11->GetImmediateContext(&pContext);
// Copy data, fast operation
pContext->CopySubresourceRegion(texStaging, 0, 0, 0, 0, tex, 0, nullptr);
// Create mapping
D3D11_MAPPED_SUBRESOURCE mapped;
HRESULT hr = pContext->Map( texStaging, 0, D3D11_MAP_READ, 0, &mapped );
if ( FAILED( hr ) )
{
return;
}
// Calculate size
const size_t size = _width * _height * 4;
// Access pixel data
unsigned char* pSrc = static_cast<unsigned char*>( mapped.pData );
// Offsets
int offsetSrc = 0;
int offsetDst = 0;
int rowOffset = mapped.RowPitch % _width;
// Loop through it, BRGA to RGBA conversation
for (int row = 0; row < _height; ++row)
{
for (int col = 0; col < _width; ++col)
{
pDest[offsetDst] = pSrc[offsetSrc+2];
pDest[offsetDst+1] = pSrc[offsetSrc+1];
pDest[offsetDst+2] = pSrc[offsetSrc];
pDest[offsetDst+3] = pSrc[offsetSrc+3];
offsetSrc += 4;
offsetDst += 4;
}
// Adjuste offset
offsetSrc += rowOffset;
}
// Unmap texture
pContext->Unmap( texStaging, 0 );
Solution:
Texture2D txDiffuse : register(t0);
SamplerState texSampler : register(s0);
struct VSScreenQuadOutput
{
float4 Position : SV_POSITION;
float2 TexCoords0 : TEXCOORD0;
};
float4 PSMain(VSScreenQuadOutput input) : SV_Target
{
return txDiffuse.Sample(texSampler, input.TexCoords0).rgba;
}
Obviously iterating over a texture on you CPU is not the most effective way. If you know that colors in a texture are always swapped like that and you don't want to modify the texture itself in your C++ code, the most straightforward way would be to do it in the pixel shader. When you sample the texture, simply swap colors there. You won't even notice any performance drop.
I want to resize a screen captured using the Desktop Duplication API in SharpDX. I am using the Screen Capture sample code from the SharpDX Samples repository, relevant portion follows:.
SharpDX.DXGI.Resource screenResource;
OutputDuplicateFrameInformation duplicateFrameInformation;
// Try to get duplicated frame within given time
duplicatedOutput.AcquireNextFrame(10000, out duplicateFrameInformation, out screenResource);
if (i > 0)
{
// copy resource into memory that can be accessed by the CPU
using (var screenTexture2D = screenResource.QueryInterface<Texture2D>())
device.ImmediateContext.CopyResource(screenTexture2D, screenTexture);
// Get the desktop capture texture
var mapSource = device.ImmediateContext.MapSubresource(screenTexture, 0, MapMode.Read, MapFlags.None);
System.Diagnostics.Debug.WriteLine(watch.Elapsed);
// Create Drawing.Bitmap
var bitmap = new System.Drawing.Bitmap(width, height, PixelFormat.Format32bppArgb);
var boundsRect = new System.Drawing.Rectangle(0, 0, width, height);
// Copy pixels from screen capture Texture to GDI bitmap
var mapDest = bitmap.LockBits(boundsRect, ImageLockMode.WriteOnly, bitmap.PixelFormat);
var sourcePtr = mapSource.DataPointer;
var destPtr = mapDest.Scan0;
for (int y = 0; y < height; y++)
{
// Iterate and write to bitmap...
I would like to resize the image much smaller than the actual screen size before processing it as a byte array. I do not need to save the image, just get at the bytes. I would like to do this relatively quickly and efficiently (e.g. leveraging GPU if possible).
I'm not able to scale during CopyResource, as the output dimensions are required to be the same as the input dimensions. Can I perform another copy from my screenTexture2D to scale? How exactly do I scale the resource - do I use a Swap Chain, Matrix transform, or something else?
If you are fine resizing to a power of two from the screen, you can do it by:
Create a smaller texture with RenderTarget/ShaderResource usage, and options GenerateMipMaps, same size of screen, mipcount > 1 (2 for having size /2, 3 for having /4...etc.).
Copy the first mipmap of the screen texture to the smaller texture
DeviceContext.GenerateMipMaps on the smaller texture
Copy the selected mimap of the smaller texture (1: /2, 2: /4...etc.) to the staging texture (that should also be declared smaller, i.e. same size as the mipmap that is going to be used)
A quick hack on the original code to generate a /2 texture would be like this:
[STAThread]
private static void Main()
{
// # of graphics card adapter
const int numAdapter = 0;
// # of output device (i.e. monitor)
const int numOutput = 0;
const string outputFileName = "ScreenCapture.bmp";
// Create DXGI Factory1
var factory = new Factory1();
var adapter = factory.GetAdapter1(numAdapter);
// Create device from Adapter
var device = new Device(adapter);
// Get DXGI.Output
var output = adapter.GetOutput(numOutput);
var output1 = output.QueryInterface<Output1>();
// Width/Height of desktop to capture
int width = output.Description.DesktopBounds.Width;
int height = output.Description.DesktopBounds.Height;
// Create Staging texture CPU-accessible
var textureDesc = new Texture2DDescription
{
CpuAccessFlags = CpuAccessFlags.Read,
BindFlags = BindFlags.None,
Format = Format.B8G8R8A8_UNorm,
Width = width/2,
Height = height/2,
OptionFlags = ResourceOptionFlags.None,
MipLevels = 1,
ArraySize = 1,
SampleDescription = { Count = 1, Quality = 0 },
Usage = ResourceUsage.Staging
};
var stagingTexture = new Texture2D(device, textureDesc);
// Create Staging texture CPU-accessible
var smallerTextureDesc = new Texture2DDescription
{
CpuAccessFlags = CpuAccessFlags.None,
BindFlags = BindFlags.RenderTarget | BindFlags.ShaderResource,
Format = Format.B8G8R8A8_UNorm,
Width = width,
Height = height,
OptionFlags = ResourceOptionFlags.GenerateMipMaps,
MipLevels = 4,
ArraySize = 1,
SampleDescription = { Count = 1, Quality = 0 },
Usage = ResourceUsage.Default
};
var smallerTexture = new Texture2D(device, smallerTextureDesc);
var smallerTextureView = new ShaderResourceView(device, smallerTexture);
// Duplicate the output
var duplicatedOutput = output1.DuplicateOutput(device);
bool captureDone = false;
for (int i = 0; !captureDone; i++)
{
try
{
SharpDX.DXGI.Resource screenResource;
OutputDuplicateFrameInformation duplicateFrameInformation;
// Try to get duplicated frame within given time
duplicatedOutput.AcquireNextFrame(10000, out duplicateFrameInformation, out screenResource);
if (i > 0)
{
// copy resource into memory that can be accessed by the CPU
using (var screenTexture2D = screenResource.QueryInterface<Texture2D>())
device.ImmediateContext.CopySubresourceRegion(screenTexture2D, 0, null, smallerTexture, 0);
// Generates the mipmap of the screen
device.ImmediateContext.GenerateMips(smallerTextureView);
// Copy the mipmap 1 of smallerTexture (size/2) to the staging texture
device.ImmediateContext.CopySubresourceRegion(smallerTexture, 1, null, stagingTexture, 0);
// Get the desktop capture texture
var mapSource = device.ImmediateContext.MapSubresource(stagingTexture, 0, MapMode.Read, MapFlags.None);
// Create Drawing.Bitmap
var bitmap = new System.Drawing.Bitmap(width/2, height/2, PixelFormat.Format32bppArgb);
var boundsRect = new System.Drawing.Rectangle(0, 0, width/2, height/2);
// Copy pixels from screen capture Texture to GDI bitmap
var mapDest = bitmap.LockBits(boundsRect, ImageLockMode.WriteOnly, bitmap.PixelFormat);
var sourcePtr = mapSource.DataPointer;
var destPtr = mapDest.Scan0;
for (int y = 0; y < height/2; y++)
{
// Copy a single line
Utilities.CopyMemory(destPtr, sourcePtr, width/2 * 4);
// Advance pointers
sourcePtr = IntPtr.Add(sourcePtr, mapSource.RowPitch);
destPtr = IntPtr.Add(destPtr, mapDest.Stride);
}
// Release source and dest locks
bitmap.UnlockBits(mapDest);
device.ImmediateContext.UnmapSubresource(stagingTexture, 0);
// Save the output
bitmap.Save(outputFileName);
// Capture done
captureDone = true;
}
screenResource.Dispose();
duplicatedOutput.ReleaseFrame();
}
catch (SharpDXException e)
{
if (e.ResultCode.Code != SharpDX.DXGI.ResultCode.WaitTimeout.Result.Code)
{
throw e;
}
}
}
// Display the texture using system associated viewer
System.Diagnostics.Process.Start(Path.GetFullPath(Path.Combine(Environment.CurrentDirectory, outputFileName)));
// TODO: We should cleanp up all allocated COM objects here
}
You need to take your original source surface in GPU memory and Draw() it on to a smaller surface. This involves simple vector/pixel shaders, which some folks with simple needs would rather bypass.
I would look to see if someone made a sprite lib for sharpdx. It should be a common "thing"...or using Direct2D (which is much more fun). Since D2D is just a user-mode library over D3D, it interops with D3D very easily.
I've never used SharpDx, but fFrom memory you would do something like this:
1.) Create an ID2D1Device, wrapping your existing DXGI Device (make sure your dxgi device creation flag has D3D11_CREATE_DEVICE_BGRA_SUPPORT)
2.) Get the ID2D1DeviceContext from your ID2D1Device
3.) Wrap your source and destination DXGI surfaces into D2D bitmaps with ID2D1DeviceContext::CreateBitmapFromDxgiSurface
4.) ID2D1DeviceContext::SetTarget of your destination surface
5.) BeginDraw, ID2D1DeviceContext::DrawBitmap, passing your source D2D bitmap. EndDraw
6.) Save your destination
Here is a pixelate example...
d2d_device_context_h()->BeginDraw();
d2d_device_context_h()->SetTarget(mp_ppBitmap1.Get());
D2D1_SIZE_F rtSize = mp_ppBitmap1->GetSize();
rtSize.height *= (1.0f / cbpx.iPixelsize.y);
rtSize.width *= (1.0f / cbpx.iPixelsize.x);
D2D1_RECT_F rtRect = { 0.0f, 0.0f, rtSize.width, rtSize.height };
D2D1_SIZE_F rsSize = mp_ppBitmap0->GetSize();
D2D1_RECT_F rsRect = { 0.0f, 0.0f, rsSize.width, rsSize.height };
d2d_device_context_h()->DrawBitmap(mp_ppBitmap0.Get(), &rtRect, 1.0f,
D2D1_BITMAP_INTERPOLATION_MODE_LINEAR, &rsRect);
d2d_device_context_h()->SetTarget(mp_ppBitmap0.Get());
d2d_device_context_h()->DrawBitmap(mp_ppBitmap1.Get(), &rsRect, 1.0f,
D2D1_BITMAP_INTERPOLATION_MODE_NEAREST_NEIGHBOR, &rtRect);
d2d_device_context_h()->EndDraw();
Where iPixelsize.xy is the size of the "pixelated pixel", note that i just use linear interpolation when shrinking the bmp and NOT when i reenlarge. This will generate a pixelation effect.
I am new to OpenCV and trying to find contours and draw rectangle on them, here's my code but its throwing cv::Exception when it comes to accumulatedweighted().
i tried to make both src(Original Image) and dst(background) by converting to CV_32FC3 and then finding avg using accumulatedweighted.
#include "opencv2/video/tracking.hpp"
#include "opencv2/imgproc/imgproc.hpp"
#include "opencv2/imgproc/imgproc_c.h"
#include "opencv2/highgui/highgui.hpp"
#include <iostream>
#include <ctype.h>
using namespace cv;
using namespace std;
static void help()
{
cout << "\nThis is a Example to implement CAMSHIFT to detect multiple motion objects.\n";
}
Rect rect;
VideoCapture capture;
Mat currentFrame, currentFrame_grey, differenceImg, oldFrame_grey,background;
vector<vector<Point> > contours;
vector<Vec4i> hierarchy;
bool first = true;
int main(int argc, char* argv[])
{
//Create a new movie capture object.
capture.open(0);
if(!capture.isOpened())
{
//error in opening the video input
cerr << "Unable to open video file: " /*<< videoFilename*/ << endl;
exit(EXIT_FAILURE);
}
//capture current frame from webcam
capture >> currentFrame;
//Size of the image.
CvSize imgSize;
imgSize.width = currentFrame.size().width; //img.size().width
imgSize.height = currentFrame.size().height; ////img.size().height
//Images to use in the program.
currentFrame_grey.create( imgSize, IPL_DEPTH_8U);//image.create().
while(1)
{
capture >> currentFrame;//VideoCapture& VideoCapture::operator>>(Mat& image)
//Convert the image to grayscale.
cvtColor(currentFrame,currentFrame_grey,CV_RGB2GRAY);//cvtColor()
currentFrame.convertTo(currentFrame,CV_32FC3);
background = Mat::zeros(currentFrame.size(), CV_32FC3);
accumulateWeighted(currentFrame,background,1.0,NULL);
imshow("Background",background);
if(first) //Capturing Background for the first time
{
differenceImg = currentFrame_grey.clone();//img1 = img.clone()
oldFrame_grey = currentFrame_grey.clone();//img2 = img.clone()
convertScaleAbs(currentFrame_grey, oldFrame_grey, 1.0, 0.0);//convertscaleabs()
first = false;
continue;
}
//Minus the current frame from the moving average.
absdiff(oldFrame_grey,currentFrame_grey,differenceImg);//absDiff()
//bluring the differnece image
blur(differenceImg, differenceImg, imgSize);//blur()
//apply threshold to discard small unwanted movements
threshold(differenceImg, differenceImg, 25, 255, CV_THRESH_BINARY);//threshold()
//find contours
findContours(differenceImg,contours,hierarchy,CV_RETR_TREE, CV_CHAIN_APPROX_SIMPLE, Point(0, 0)); //findcontours()
//draw bounding box around each contour
//for(; contours! = 0; contours = contours->h_next)
for(int i = 0; i < contours.size(); i++)
{
rect = boundingRect(contours[i]); //extract bounding box for current contour
//drawing rectangle
rectangle(currentFrame, cvPoint(rect.x, rect.y), cvPoint(rect.x+rect.width, rect.y+rect.height), cvScalar(0, 0, 255, 0), 2, 8, 0);
}
//New Background
convertScaleAbs(currentFrame_grey, oldFrame_grey, 1.0, 0.0);
//display colour image with bounding box
imshow("Output Image", currentFrame);//imshow()
//display threshold image
imshow("Difference image", differenceImg);//imshow()
//clear memory and contours
//cvClearMemStorage( storage );
//contours = 0;
contours.clear();
//background = currentFrame;
//press Esc to exit
char c = cvWaitKey(33);
if( c == 27 ) break;
}
// Destroy All Windows.
destroyAllWindows();
return 0;
}
Please Help to solve this.
you might want to RTFM before asking here.
so, you missed the alpha param as well as the dst Mat in your call to addWeighted
Mat dst;
accumulateWeighted(currentFrame, 0.5 background, 0.5, 0, dst);
also, no idea, what the whole thing should achieve. adding up the current frame before diffing it does not make any sense to me.
if you planned to do background separation, throw it all away, and use one of the builtin backgroundsubtractors instead
I'm using UpdateLayeredWindow to display an application window. I have created my own custom buttons and i would like to create my own static text. The problem is that when i try to draw the text on the hdc, the DrawText or TextOut functions overwrite the alpha channel of my picture and the text will become transparent. I tried to find a solution to this but i could not find any. My custom controls are designed in such way that they will do all the drawing in a member function called Draw(HDC hDc), so they can only access the hdc. I would like to keep this design. Can anyone help me? I am using MFC and i would want to achieve the desired result without the use of GDI+.
I know this is an old post ... but I just had this very same problem ... and it was driving me CRAZY.
Eventually, I stumbled upon this post by Mike Sutton to the microsoft.public.win32.programmer.gdi newsgroup ... from almost 7 years ago!
Basically, the DrawText (and TextOut) do not play nicely with the alpha channel and UpdateLayeredWindow ... and you need to premultiply the R, G, and B channels with the alpha channel.
In Mike's post, he shows how he creates another DIB (device independent bitmap) upon which he draws the text ... and alpha blends that into the other bitmap.
After doing this, my text looked perfect!
Just in case, the link to the newsgroup post dies ... I am going to include the code here. All credit goes to Mike Sutton (#mikedsutton).
Here is the code that creates the alpha blended bitmap with the text on it:
HBITMAP CreateAlphaTextBitmap(LPCSTR inText, HFONT inFont, COLORREF inColour)
{
int TextLength = (int)strlen(inText);
if (TextLength <= 0) return NULL;
// Create DC and select font into it
HDC hTextDC = CreateCompatibleDC(NULL);
HFONT hOldFont = (HFONT)SelectObject(hTextDC, inFont);
HBITMAP hMyDIB = NULL;
// Get text area
RECT TextArea = {0, 0, 0, 0};
DrawText(hTextDC, inText, TextLength, &TextArea, DT_CALCRECT);
if ((TextArea.right > TextArea.left) && (TextArea.bottom > TextArea.top))
{
BITMAPINFOHEADER BMIH;
memset(&BMIH, 0x0, sizeof(BITMAPINFOHEADER));
void *pvBits = NULL;
// Specify DIB setup
BMIH.biSize = sizeof(BMIH);
BMIH.biWidth = TextArea.right - TextArea.left;
BMIH.biHeight = TextArea.bottom - TextArea.top;
BMIH.biPlanes = 1;
BMIH.biBitCount = 32;
BMIH.biCompression = BI_RGB;
// Create and select DIB into DC
hMyDIB = CreateDIBSection(hTextDC, (LPBITMAPINFO)&BMIH, 0, (LPVOID*)&pvBits, NULL, 0);
HBITMAP hOldBMP = (HBITMAP)SelectObject(hTextDC, hMyDIB);
if (hOldBMP != NULL)
{
// Set up DC properties
SetTextColor(hTextDC, 0x00FFFFFF);
SetBkColor(hTextDC, 0x00000000);
SetBkMode(hTextDC, OPAQUE);
// Draw text to buffer
DrawText(hTextDC, inText, TextLength, &TextArea, DT_NOCLIP);
BYTE* DataPtr = (BYTE*)pvBits;
BYTE FillR = GetRValue(inColour);
BYTE FillG = GetGValue(inColour);
BYTE FillB = GetBValue(inColour);
BYTE ThisA;
for (int LoopY = 0; LoopY < BMIH.biHeight; LoopY++) {
for (int LoopX = 0; LoopX < BMIH.biWidth; LoopX++) {
ThisA = *DataPtr; // Move alpha and pre-multiply with RGB
*DataPtr++ = (FillB * ThisA) >> 8;
*DataPtr++ = (FillG * ThisA) >> 8;
*DataPtr++ = (FillR * ThisA) >> 8;
*DataPtr++ = ThisA; // Set Alpha
}
}
// De-select bitmap
SelectObject(hTextDC, hOldBMP);
}
}
// De-select font and destroy temp DC
SelectObject(hTextDC, hOldFont);
DeleteDC(hTextDC);
// Return DIBSection
return hMyDIB;
}
Here is the code that drives the CreateAlphaTextBitmap method:
void TestAlphaText(HDC inDC, int inX, int inY)
{
const char *DemoText = "Hello World!\0";
RECT TextArea = {0, 0, 0, 0};
HFONT TempFont = CreateFont(50, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, "Arial\0");
HBITMAP MyBMP = CreateAlphaTextBitmap(DemoText, TempFont, 0xFF);
DeleteObject(TempFont);
if (MyBMP)
{
// Create temporary DC and select new Bitmap into it
HDC hTempDC = CreateCompatibleDC(inDC);
HBITMAP hOldBMP = (HBITMAP)SelectObject(hTempDC, MyBMP);
if (hOldBMP)
{
// Get Bitmap image size
BITMAP BMInf;
GetObject(MyBMP, sizeof(BITMAP), &BMInf);
// Fill blend function and blend new text to window
BLENDFUNCTION bf;
bf.BlendOp = AC_SRC_OVER;
bf.BlendFlags = 0;
bf.SourceConstantAlpha = 0x80;
bf.AlphaFormat = AC_SRC_ALPHA;
AlphaBlend(inDC, inX, inY, BMInf.bmWidth, BMInf.bmHeight, hTempDC, 0, 0, BMInf.bmWidth, BMInf.bmHeight, bf);
// Clean up
SelectObject(hTempDC, hOldBMP);
DeleteObject(MyBMP);
DeleteDC(hTempDC);
}
}
}