Here is a code that decodes a WebM frame and put them in a buffer
image->planes[p] = pointer to the top left pixel
image->linesize[p] = strides betwen rows
framesArray = vector of unsigned char*
while ( videoDec->getImage(*image) == VPXDecoder::NO_ERROR)
{
const int w = image->getWidth(p);
const int h = image->getHeight(p);
int offset = 0;
for (int y = 0; y < h; y++)
{
// fwrite(image->planes[p] + offset, 1, w, pFile);
for(int i=0;i<w;i++){
framesArray.at(count)[i+(w*y)] = *(image->planes[p]+offset+ i) ;
}
offset += image->linesize[p];
}
}
.............................
How can I write intro buffer line by line not pixel by pixel or optimize the writing of frame intro buffer?
if the source image and destination buffer share the same Width, Height and bit per pixel, you can use std::copy to copy the whole image into it.
std::copy(image->planes[p] + offset, image->planes[p] + (image->getHeight(p) * image->linesize[p], framesArray.begin()) ;
if it is same bit per pixel but different width and height, you can use std::copy by line.
Related
I have this code:
QImage grayImage = image.convertToFormat(QImage::Format_Grayscale8);
int size = grayImage.width() * grayImage.height();
QRgb *data = new QRgb[size];
memmove(data, grayImage.constBits(), size * sizeof(QRgb));
QRgb *ptr = data;
QRgb *end = ptr + size;
for (; ptr < end; ++ptr) {
int gray = qGray(*ptr);
}
delete[] data;
It is based on this: https://stackoverflow.com/a/40740985/8257882
How can I set the color of a pixel using that pointer?
In addition, using qGray() and loading a "bigger" image seem to crash this.
This works:
int width = image.width();
int height = image.height();
for (int y = 0; y < height; ++y) {
for (int x = 0; x < width; ++x) {
image.setPixel(x, y, qRgba(0, 0, 0, 255));
}
}
But it is slow when compared to explicitly manipulating the image data.
Edit
Ok, I have this code now:
for (int y = 0; y < height; ++y) {
uchar *line = grayImage.scanLine(y);
for (int x = 0; x < width; ++x) {
int gray = qGray(line[x]);
*(line + x) = uchar(gray);
qInfo() << gray;
}
}
And it seems to work. However, when I use an image that has only black and white colors and print the gray value, black color gives me 0 and white gives 39. How can I get the gray value in a range of 0-255?
First of all you are copying too much data in this line:
memmove(data, grayImage.constBits(), size * sizeof(QRgb));
The size ob Qrgb is 4 bytes, but according to the documentation, the size of a Format_Grayscale8 pixel is only 8 bits or 1 byte. If you remove sizeof(QRgb) you should be copying the correct amount of bytes, assuming all the lines in the bitmap are consecutive (which, according to the documentation, they are not -- they are aligned to at minimum 32-bits, so you would have to account for that in size). The array data should not be of type Qrgb[size] but ucahr[size]. You can then modify data as you like. Finally, you will probably have to create a new QImage with one of the constructors that accept image bits as uchar and assign the new image to the old image:
auto newImage = QImage( data, image.width(), image.height(), QImage::Format_Grayscale8, ...);
grayImage = std::move( newImage );
But instead of copying image data, you could probably just modify grayImage directly by accessing its data through bits(), or even better, through scanLine(), maybe something like this:
int line, column;
auto pLine = grayImage.scanLine(line);
*(pLine + column) = uchar(grayValue);
EDIT:
According to scanLine documentation, the image is at least 32-bit aligned. So if your 8-bit grayScale image is 3 pixels wide, a new scan line will start every 4 bytes. If you have a 3x3 image, the total size of the memory required to hold the image pixels will be 12. The following code shows the required memory size:
int main() {
auto image = QImage(3, 3, QImage::Format_Grayscale8);
std::cout << image.bytesPerLine() * image.height() << "\n";
return 0;
}
The fill method (setting all gray values to 0xC0) could be implemented like this:
auto image = QImage(3, 3, QImage::Format_Grayscale8);
uchar gray = 0xc0;
for ( int i = 0; i < image.height(); ++i ) {
auto pLine = image.scanLine( i );
for ( int j = 0; j < image.width(); ++j )
*pLine++ = gray;
}
I have input from captured camera frame as CMSampleBufferRef and I need to get the raw pixels preferably in C type uint8_t[].
I also need to find the color scheme of the input image.
I know how to convert CMSampleBufferRef to UIImage and then to NSData with png format but I dont know how to get the raw pixels from there. Perhaps I could get it already from CMSampleBufferRef/CIImage`?
This code shows the need and the missing bits.
Any thoughts where to start?
int convertCMSampleBufferToPixelArray (CMSampleBufferRef sampleBuffer)
{
// inputs
CVImageBufferRef imageBuffer = CMSampleBufferGetImageBuffer(sampleBuffer);
CIImage *ciImage = [CIImage imageWithCVPixelBuffer:imageBuffer];
CIContext *imgContext = [CIContext new];
CGImageRef cgImage = [imgContext createCGImage:ciImage fromRect:ciImage.extent];
UIImage *uiImage = [UIImage imageWithCGImage:cgImage];
NSData *nsData = UIImagePNGRepresentation(uiImage);
// Need to fill this gap
uint8_t* data = XXXXXXXXXXXXXXXX;
ImageFormat format = XXXXXXXXXXXXXXXX; // one of: GRAY8, RGB_888, YV12, BGRA_8888, ARGB_8888
// sample showing expected data values
// this routine converts the image data to gray
//
int width = uiImage.size.width;
int height = uiImage.size.height;
const int size = width * height;
std::unique_ptr<uint8_t[]> new_data(new uint8_t[size]);
for (int i = 0; i < size; ++i) {
new_data[i] = uint8_t(data[i * 3] * 0.299f + data[i * 3 + 1] * 0.587f +
data[i * 3 + 2] * 0.114f + 0.5f);
}
return 1;
}
Some pointers you can use to search for more info. It's nicely documented and you shouldn't have an issue.
int convertCMSampleBufferToPixelArray (CMSampleBufferRef sampleBuffer) {
CVImageBufferRef imageBuffer = CMSampleBufferGetImageBuffer(sampleBuffer);
if (imageBuffer == NULL) {
return -1;
}
// Get address of the image buffer
CVPixelBufferLockBaseAddress(imageBuffer, 0);
uint8_t* data = CVPixelBufferGetBaseAddress(imageBuffer);
// Get size
size_t width = CVPixelBufferGetWidth(imageBuffer);
size_t height = CVPixelBufferGetHeight(imageBuffer);
// Get bytes per row
size_t bytesPerRow = CVPixelBufferGetBytesPerRow(imageBuffer);
// At `data` you have a bytesPerRow * height bytes of the image data
// To get pixel info you can call CVPixelBufferGetPixelFormatType, ...
// you can call CVImageBufferGetColorSpace and inspect it, ...
// When you're done, unlock the base address
CVPixelBufferUnlockBaseAddress(imageBuffer, 0);
return 0;
}
There're couple of things you should be aware of.
First one is that it can be planar. Check the CVPixelBufferIsPlanar, CVPixelBufferGetPlaneCount, CVPixelBufferGetBytesPerRowOfPlane, etc.
Second one is that you have to calculate pixel size based on CVPixelBufferGetPixelFormatType. Something like:
CVPixelBufferGetPixelFormatType(imageBuffer)
size_t pixelSize;
switch (pixelFormat) {
case kCVPixelFormatType_32BGRA:
case kCVPixelFormatType_32ARGB:
case kCVPixelFormatType_32ABGR:
case kCVPixelFormatType_32RGBA:
pixelSize = 4;
break;
// + other cases
}
Let's say that the buffer is not planar and:
CVPixelBufferGetWidth returns 200 (pixels)
Your pixelSize is 4 (calcuated bytes per row is 200 * 4 = 800)
CVPixelBufferGetBytesPerRow can return anything >= 800
In other words, the pointer you have is not a pointer to a contiguous buffer. If you need row data you have to do something like this:
uint8_t* data = CVPixelBufferGetBaseAddress(imageBuffer);
// Get size
size_t width = CVPixelBufferGetWidth(imageBuffer);
size_t height = CVPixelBufferGetHeight(imageBuffer);
size_t pixelSize = 4; // Let's pretend it's calculated pixel size
size_t realRowSize = width * pixelSize;
size_t bytesPerRow = CVPixelBufferGetBytesPerRow(imageBuffer);
for (int row = 0 ; row < height ; row++) {
// bytesPerRow acts like an offset where the next row starts
// bytesPerRow can be >= realRowSize
uint8_t *rowData = data + row * bytesPerRow;
// realRowSize = how many bytes are available for this row
// copy them somewhere
}
You have to allocate a buffer and copy these row data there if you'd like to have contiguous buffer. How many bytes to allocate? CVPixelBufferGetDataSize.
I am trying to encode an MP4 video using raw YUV frames data, but I am not sure how can I fill the plane data (preferably without using other libraries like ffmpeg)
The frame data is already encoded in I420, and does not need conversion.
Here is what I am trying to do:
const char *frameData = /* Raw frame data */;
x264_t *encoder = x264_encoder_open(¶m);
x264_picture_t imgInput, imgOutput;
x264_picture_alloc(&imgInput, X264_CSP_I420, width, height);
// how can I fill the struct data of imgInput
x264_nal_t *nals;
int i_nals;
int frameSize = x264_encoder_encode(encoder, &nals, &i_nals, &imgInput, &imgOutput);
The equivalent command line that I have found is :
x264 --output video.mp4 --fps 15 --input-res 1280x800 imgdata_01.raw
But I could not figure out how the app does it.
Thanks.
Look at libx264 API usage example. This example use fread() to fill frame allocated by x264_picture_alloc() with actual i420 data from stdin. If you already have i420 data in memory and want to skip memcpy step than instead of it you can:
Use x264_picture_init() instead of x264_picture_alloc() and x264_picture_clean(). Because you don't need allocate memory on heap for frame data.
Fill x264_picture_t.img struct fields:
i_csp = X264_CSP_I420;
i_plane = 3;
plane[0] = pointer to Y-plane;
i_stride[0] = stride in bytes for Y-plane;
plane[1] = pointer to U-plane;
i_stride[1] = stride in bytes for U-plane;
plane[2] = pointer to V-plane;
i_stride[2] = stride in bytes for V-plane;
To complete the answer above, this is an example to fill an x264_picture_t image.
int fillImage(uint8_t* buffer, int width, int height, x264_picture_t*pic){
int ret = x264_picture_alloc(pic, X264_CSP_I420, width, height);
if (ret < 0) return ret;
pic->img.i_plane = 3; // Y, U and V
pic->img.i_stride[0] = width;
// U and V planes are half the size of Y plane
pic->img.i_stride[1] = width / 2;
pic->img.i_stride[2] = width / 2;
int uvsize = ((width + 1) >> 1) * ((height + 1) >> 1);
pic->img.plane[0] = buffer; // Y Plane pointer
pic->img.plane[1] = buffer + (width * height); // U Plane pointer
pic->img.plane[2] = pic->img.plane[1] + uvsize; // V Plane pointer
return ret;
}
I have a TGA file and a library that allready has everything that I need to read TGA and use them.
This class has a method called pixels(), that returns a pointer that is pointed to the memory area where pixel are stored as RGBRGBRGB...
My question is, how can I take the pixel value?
Cause if I make something like this:
img.load("foo.tga");
printf ("%i", img.pixels());
It gives back to me what is proprably the address.
I've found this code on this site:
struct Pixel2d
{
static const int SIZE = 50;
unsigned char& operator()( int nCol, int nRow, int RGB)
{
return pixels[ ( nCol* SIZE + nRow) * 3 + RGB];
}
unsigned char pixels[SIZE * SIZE * 3 ];
};
int main()
{
Pixel2d p2darray;
glReadPixels(50,50, 1, 1, GL_RGB, GL_UNSIGNED_BYTE, &p.pixels);
for( int i = 0; i < Pixel2d::SIZE ; ++i )
{
for( int j = 0; j < Pixel2d::SIZE ; ++j )
{
unsigned char rpixel = p2darray(i , j , 0);
unsigned char gpixel = p2darray(i , j , 1);
unsigned char bpixel = p2darray(i , j , 2);
}
}
}
I think that It can work great for me, but how can I tell the program to read from my img?
Tga supports different pixel depths. And we don't know what library you're using. But generally speaking pixels() should return a pointer to a buffer containing pixels. Say for sake of argument it unpacks the pixels into 8-bit per channel subpixels, then each pixel is represented by 3 bytes.
So to access a pixel at a given offset in the buffer:
const u8* pixelBuffer = img.pixels():
u8 red = pixelBuffer[(offset*3)+0];
u8 green = pixelBuffer[(offset*3)+1];
u8 blue = pixelBuffer[(offset*3)+2];
If you know the width of the image buffer then you can get a pixel by its x and y coordinates:
u8 red = pixelBuffer[((x+(y*width))*3)+0];
I need to create a CImage from a byte array (actually, its an array of unsigned char, but I can cast to whatever form is necessary). The byte array is in the form "RGBRGBRGB...". The new image needs to contain a copy of the image bytes, rather than using the memory of the byte array itself.
I have tried many different ways of achieving this -- including going through various HBITMAP creation functions, trying to use BitBlt -- and nothing so far has worked.
To test whether the function works, it should pass this test:
BYTE* imgBits;
int width;
int height;
int Bpp; // BYTES per pixel (e.g. 3)
getImage(&imgBits, &width, &height, &Bpp); // get the image bits
// This is the magic function I need!!!
CImage img = createCImage(imgBits, width, height, Bpp);
// Test the image
BYTE* data = img.GetBits(); // data should now have the same data as imgBits
All implementations of createCImage() so far have ended up with data pointing to an empty (zero filled) array.
CImage supports DIBs quite neatly and has a SetPixel() method so you could presumably do something like this (uncompiled, untested code ahead!):
CImage img;
img.Create(width, height, 24 /* bpp */, 0 /* No alpha channel */);
int nPixel = 0;
for(int row = 0; row < height; row++)
{
for(int col = 0; col < width; col++)
{
BYTE r = imgBits[nPixel++];
BYTE g = imgBits[nPixel++];
BYTE b = imgBits[nPixel++];
img.SetPixel(row, col, RGB(r, g, b));
}
}
Maybe not the most efficient method but I should think it is the simplest approach.
Use memcpy to copy the data, then SetDIBits or SetDIBitsToDevice depending on what you need to do. Take care though, the scanlines of the raw image data are aligned on 4-byte boundaries (IIRC, it's been a few years since I did this) so the data you get back from GetDIBits will never be exactly the same as the original data (well it might, depending on the image size).
So most likely you will need to memcpy scanline by scanline.
Thanks everyone, I managed to solve it in the end with your help. It mainly involved #tinman and #Roel's suggestion to use SetDIBitsToDevice(), but it involved a bit of extra bit-twiddling and memory management, so I thought I'd share my end-point here.
In the code below, I assume that width, height and Bpp (Bytes per pixel) are set, and that data is a pointer to the array of RGB pixel values.
// Create the header info
bmInfohdr.biSize = sizeof(BITMAPINFOHEADER);
bmInfohdr.biWidth = width;
bmInfohdr.biHeight = -height;
bmInfohdr.biPlanes = 1;
bmInfohdr.biBitCount = Bpp*8;
bmInfohdr.biCompression = BI_RGB;
bmInfohdr.biSizeImage = width*height*Bpp;
bmInfohdr.biXPelsPerMeter = 0;
bmInfohdr.biYPelsPerMeter = 0;
bmInfohdr.biClrUsed = 0;
bmInfohdr.biClrImportant = 0;
BITMAPINFO bmInfo;
bmInfo.bmiHeader = bmInfohdr;
bmInfo.bmiColors[0].rgbBlue=255;
// Allocate some memory and some pointers
unsigned char * p24Img = new unsigned char[width*height*3];
BYTE *pTemp,*ptr;
pTemp=(BYTE*)data;
ptr=p24Img;
// Convert image from RGB to BGR
for (DWORD index = 0; index < width*height ; index++)
{
unsigned char r = *(pTemp++);
unsigned char g = *(pTemp++);
unsigned char b = *(pTemp++);
*(ptr++) = b;
*(ptr++) = g;
*(ptr++) = r;
}
// Create the CImage
CImage im;
im.Create(width, height, 24, NULL);
HDC dc = im.GetDC();
SetDIBitsToDevice(dc, 0,0,width,height,0,0, 0, height, p24Img, &bmInfo, DIB_RGB_COLORS);
im.ReleaseDC();
delete[] p24Img;
Here is a simpler solution. You can use GetPixelAddress(...) instead of all this BITMAPHEADERINFO and SedDIBitsToDevice. Another problem I have solved was with 8-bit images, which need to have the color table defined.
CImage outImage;
outImage.Create(width, height, channelCount * 8);
int lineSize = width * channelCount;
if (channelCount == 1)
{
// Define the color table
RGBQUAD* tab = new RGBQUAD[256];
for (int i = 0; i < 256; ++i)
{
tab[i].rgbRed = i;
tab[i].rgbGreen = i;
tab[i].rgbBlue = i;
tab[i].rgbReserved = 0;
}
outImage.SetColorTable(0, 256, tab);
delete[] tab;
}
// Copy pixel values
// Warining: does not convert from RGB to BGR
for ( int i = 0; i < height; i++ )
{
void* dst = outImage.GetPixelAddress(0, i);
const void* src = /* put the pointer to the i'th source row here */;
memcpy(dst, src, lineSize);
}