LibVLC empty image - c++

I'm trying to use LibVLC to decode a video file and render it to a texture.
The code for opening and start playing works, the audio plays perfectly, but the pixel buffer is always filled with 0xCD. The videos I try to render work on VLC, and even in a C# implementation I did they work, but with this new code in C I can't manage to get it working...
I'm using the x64 version of the vlc libs and the program is compiled for x64 if this makes any difference.
Here is my code:
#include "stdafx.h"
#include "video.h"
#include <string.h>
#include <vlc\libvlc.h>
#include <vlc\libvlc_media.h>
#include <vlc\libvlc_media_player.h>
libvlc_instance_t* instance;
libvlc_media_t* media;
libvlc_media_player_t* player;
struct videoContext
{
unsigned char *pixeldata;
unsigned char currentFrame;
int width;
int height;
};
struct videoContext mainContext;
bool gotData = false;
int width;
int height;
static void *lock(void *data, void **p_pixels)
{
videoContext* context = (videoContext*)data;
*p_pixels = context->pixeldata;
return NULL;
}
static void unlock(void *data, void *id, void *const *p_pixels)
{
mainContext.currentFrame++;
//If I check here mainContext.pixeldata is filled with 0xCD
}
static void display(void *data, void *id)
{
}
static unsigned int formatSetup(void **opaque, char *chroma, unsigned *w, unsigned *h, unsigned *pitches, unsigned *lines)
{
chroma = "RV24";
width = *w;
height = *h;
mainContext.pixeldata = (unsigned char*)malloc(width * height * 3);
mainContext.width = width;
mainContext.height = height;
return 1;
}
void getVideoSize(int* w, int* h, int* bpp)
{
*w = width;
*h = height;
*bpp = 3 * 8;
}
videoContext* initVideo(const char* fileName)
{
mainContext.pixeldata = 0;
instance = libvlc_new(0, NULL);
media = libvlc_media_new_location(instance, fileName);
player = libvlc_media_player_new_from_media(media);
libvlc_video_set_callbacks(player, lock, unlock, display, &mainContext);
libvlc_video_set_format_callbacks(player, formatSetup, NULL);
libvlc_media_player_play(player);
return &mainContext;
}
UPDATE:
It seems that nothing is being written to the buffer as anything I set is left there.
UPDATE2:
If I remove the format setup callback and I hardcode libvlc_video_set_format with the "RV24" chroma mode and the resolution it works, so, did I understood wrongly what libvlc_video_set_format_callbacks does?
According to the documentation on the format setup callback the params can be changed to enable transcoding but even if I just leave the format as is whenever I set the format setup callback it doesn't works...

Ok, so, the problem was extrmely stupid. First, the pitches and lines must be set so libvlc to know the allocated sizes. Second, can't just assign chroma with a const char, it seems as the const char has an extra "\0x00" at the end liblvc counts it and then doesn't finds the decoder.
The final callback is this:
static unsigned int formatSetup(void **opaque, char *chroma, unsigned *w, unsigned *h, unsigned *pitches, unsigned *lines)
{
memcpy(chroma, "RV24", sizeof("RV24") - 1);
width = *w;
height = *h;
*pitches = width * 3;
*lines = height;
mainContext.pixeldata = (unsigned char*)malloc(width * height * 4);
mainContext.width = width;
mainContext.height = height;
return 1;
}

Related

How to prefer font that is loaded by AddFontMemResourceEx than system?

I'm developing game application on windows by C++ with the font that is included in resource.
I can load the font by AddFontMemResourceEx and CreateFont.
And, I can render text with loaded font correctly in my environment that doesn't install any special font.
But, several version of the font exists in the world.
If other version was already installed in system, CreateFont will find font by the font name(pszFaceName) and prefer system font inconveniently.
Is there anyway to prefer private font that is loaded by AddFontMemResourceEx?
FYI, The return value of AddFontMemResourceEx is HANDLE, but I can't find any code that use it for CreateFont.
Probably, edit font family on private font can avoid conflict.
But, I want to resolve by programming if I can.
HANDLE handle = AddFontMemResourceEx(data, readBytes, NULL, &fontNum);
hFont = CreateFont(24, 0, 0, 0, FW_NORMAL, FALSE, FALSE, FALSE, SHIFTJIS_CHARSET, OUT_TT_ONLY_PRECIS,
CLIP_DEFAULT_PRECIS, PROOF_QUALITY, DEFAULT_PITCH | FF_DONTCARE, L"UmePlus CL Gothic");
Thank you for comments!
I've replaced font name in memory based on comment.
But, this code has bit complicacy by difference of endian.
Caution: newFontName must be shorter than oldFontName.
#pragma pack(1)
typedef struct {
short version;
long numTables;
short searchRange;
short entrySelector;
short rangeShift;
} TTF_HEADER;
typedef struct {
char name[4];
long checksum;
long offset;
long length;
} TTF_OFFSET_TABLE;
typedef struct {
short format;
short count;
short stringOffset;
} TTF_NAME_TABLE_HEADER;
typedef struct {
short platformId;
short specificId;
short languageId;
short nameId;
short length;
short offset;
} TTF_NAME_TABLE_ENTRY;
#pragma pack()
void copySwappedWchar(const wchar_t* src, wchar_t* dest, int length) {
for (int i = 0; i < length; i++) {
dest[i] = _byteswap_ushort(src[i]);
}
}
void renameLocalFont(unsigned char* data, const wchar_t* oldFontName, const wchar_t* newFontName) {
TTF_HEADER* header = (TTF_HEADER*)data;
unsigned char* offsetTableBase = data + sizeof(TTF_HEADER);
for (int i = 0; i < _byteswap_ulong(header->numTables); i++) {
TTF_OFFSET_TABLE* table = (TTF_OFFSET_TABLE*)(offsetTableBase + sizeof(TTF_OFFSET_TABLE) * i);
if (memcmp(table->name, "name", 4) != 0) continue;
TTF_NAME_TABLE_HEADER* nameTable = (TTF_NAME_TABLE_HEADER*)(data + _byteswap_ulong(table->offset));
unsigned char* entryBase = data + _byteswap_ulong(table->offset) + sizeof(TTF_NAME_TABLE_HEADER);
for (int j = 0; j < _byteswap_ushort(nameTable->count); j++) {
TTF_NAME_TABLE_ENTRY* entry = (TTF_NAME_TABLE_ENTRY*)(entryBase + sizeof(TTF_NAME_TABLE_ENTRY) * j);
wchar_t* dest = new wchar_t[_byteswap_ushort(entry->length) + 1];
wchar_t* src = (wchar_t*)(data + _byteswap_ulong(table->offset) + _byteswap_ushort(nameTable->stringOffset) + _byteswap_ushort(entry->offset));
copySwappedWchar((const wchar_t*)src, dest, _byteswap_ushort(entry->length) + 1);
if (wcscmp(dest, oldFontName) == 0) {
copySwappedWchar(newFontName, src, wcslen(newFontName) + 1);
}
}
}
}

Play a memory buffer with libvlc

I want to play a buffer in libvlc which is filled by a signal/slot from another thread. I've used read_callbacks of libvlc but it can be compiled with mingw and compiling it for msvc is a hard process (see here).(I want to compile my program in msvc2012). so I want to use imem option and I wrote the following code but it crashed and do not show anything.
#include <QMainWindow>
#include <QFile>
#include <vlc/vlc.h>
#include <vlc/libvlc_media_player.h>
#include <vlc/libvlc_media.h>
using namespace std ;
const int len = (820 * 600 * 4) + 31;
int imemGetCallback (void *data, const char *cookie,int64_t *dts, int64_t *pts,unsigned *flags, size_t * bufferSize, void ** buffer);
int imemReleaseCallback (void *data, const char *cookie, size_t bufferSize, void * buffer);
int main(){
char smem_options1[2000];
char venc_options[1000];
sprintf(venc_options,"bframes=6,ref=6");
char str_imem_get[100], str_imem_release[100],str_imem_data[100];
sprintf(str_imem_get, "--imem-get=%ld", imemGetCallback);
sprintf(str_imem_release, "--imem-release=%ld", imemReleaseCallback);
const char * const vlc_args[] = {
"-I","dummy",
"--ignore-config",
"--demux","rawvideo",
"--rawvid-fps","30",
"--rawvid-width","820",
"--rawvid-height","600",
"--rawvid-chroma","RV24",
"--imem-channels=1",
"--imem-data=0",
"--imem-cat=4",
"--imem-fps=30",
"--imem-codec=none",
str_imem_get,
str_imem_release
};
libvlc_instance_t * inst_broadcast =libvlc_new(sizeof(vlc_args) / sizeof(vlc_args[0]), vlc_args);;// libvlc_new(vlc_argc, vlc_argv);
libvlc_media_t * m = libvlc_media_new_location(inst_broadcast, "imem://");
auto _vlcmp = libvlc_media_player_new_from_media(m);
libvlc_media_player_play(_vlcmp);
}
int imemGetCallback (void *data, const char *cookie,int64_t *dts, int64_t *pts,unsigned *flags, size_t * bufferSize, void ** buffer)
{
int64_t uS = 33333; // 30 fps
static int index=0;
*bufferSize = len;
*buffer = buf;
*dts = *pts = 33333;
return 1;
}
int imemReleaseCallback (void *data, const char *cookie, size_t bufferSize, void * buffer)
{
return 0;
}
how can I use imem option to do the job?

C/CUDA: Only every fourth element in CudaArray can be indexed

This is my first post, so I am thrilled to get some new insights and enlarge my knowledge. Currently I am working on a C-project where a binary raw file with 3d-data is loaded, processed in CUDA and saved in a new binary raw file.
This is based on the simpleTexture3D project from CUDA Samples:
This is my cpp
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <math.h>
// includes, cuda
#include <vector_types.h>
#include <driver_functions.h>
#include <cuda_runtime.h>
// CUDA utilities and system includes
#include <helper_cuda.h>
#include <helper_functions.h>
#include <vector_types.h>
typedef unsigned int uint;
typedef unsigned char uchar;
const char *sSDKsample = "simpleTexture3D";
const char *volumeFilename = "Bucky.raw";
const cudaExtent volumeSize = make_cudaExtent(32, 32, 32);
const uint width = 64, height = 64, depth=64;
//const char *volumeFilename = "TestOCT.raw";
//const cudaExtent volumeSize = make_cudaExtent(1024, 512, 512);
//
//const uint width = 1024, height = 512, depth=512;
const dim3 blockSize(8, 8, 8);
const dim3 gridSize(width / blockSize.x, height / blockSize.y, depth / blockSize.z);
uint *d_output = NULL;
int *pArgc = NULL;
char **pArgv = NULL;
extern "C" void cleanup();
extern "C" void initCuda(const uchar *h_volume, cudaExtent volumeSize);
extern "C" void render_kernel(dim3 gridSize, dim3 blockSize, uint *d_output, uint imageW, uint imageH, uint imageD);
void loadVolumeData(char *exec_path);
// render image using CUDA
void render()
{
// call CUDA kernel
render_kernel(gridSize, blockSize, d_output, width, height, depth);
getLastCudaError("render_kernel failed");
}
void cleanup()
{
// cudaDeviceReset causes the driver to clean up all state. While
// not mandatory in normal operation, it is good practice. It is also
// needed to ensure correct operation when the application is being
// profiled. Calling cudaDeviceReset causes all profile data to be
// flushed before the application exits
checkCudaErrors(cudaDeviceReset());
}
// Load raw data from disk
uchar *loadRawFile(const char *filename, size_t size)
{
FILE *fp = fopen(filename, "rb");
if (!fp)
{
fprintf(stderr, "Error opening file '%s'\n", filename);
return 0;
}
uchar *data = (uchar *) malloc(size);
size_t read = fread(data, 1, size, fp);
fclose(fp);
printf("Read '%s', %lu bytes\n", filename, read);
return data;
}
// write raw data to disk
int writeRawFile(const char *filename, uchar *data, size_t size)
{
int returnState=0;
// cut file extension from filename
char *a=strdup(filename); //via strdup you dumb a const char to char, you must free it yourself
int len = strlen(a);
a[len-4] = '\0'; //deletes '.raw'
//printf("%s\n",a);
char b[50];
sprintf(b, "_%dx%dx%d_out.raw", width, height, depth);
//char b[]="_out.raw"; //Add suffix out to filename
char buffer[256]; // <- danger, only storage for 256 characters.
strncpy(buffer, a, sizeof(buffer));
strncat(buffer, b, sizeof(buffer));
free(a);
FILE *fp = fopen(buffer, "wb"); //Open or create file for writing as binary, all existing data is cleared
if (!fp)
{
fprintf(stderr, "Error opening or creating file '%s'\n", buffer);
return 0;
}
size_t write = fwrite(data, 1, size, fp);
fclose(fp);
if (write==size)
{
printf("Wrote %lu bytes to '%s'\n", write, buffer);
return 0;
}
else
{
printf("Error writing data to file '%s'\n", buffer);
return 1;
}
}
// General initialization call for CUDA Device
int chooseCudaDevice(int argc, char **argv)
{
int result = 0;
result = findCudaDevice(argc, (const char **)argv);
return result;
}
void runAutoTest(char *exec_path, char *PathToFile)
{
// set path
char *path;
if (PathToFile == NULL)
{
path = sdkFindFilePath(volumeFilename, exec_path);
}
else
{
path = PathToFile;
}
if (path == NULL)
{
fprintf(stderr, "Error unable to find 3D Volume file: '%s'\n", volumeFilename);
exit(EXIT_FAILURE);
}
// Allocate output memory
checkCudaErrors(cudaMalloc((void **)&d_output, width*height*depth*sizeof(uchar)));
// zero out the output array with cudaMemset
cudaMemset(d_output, 0, width*height*depth*sizeof(uchar));
// render the volumeData
render_kernel(gridSize, blockSize, d_output, width, height, depth);
checkCudaErrors(cudaDeviceSynchronize());
getLastCudaError("render_kernel failed");
uchar *h_output = (uchar*)malloc(width*height*depth);
checkCudaErrors(cudaMemcpy(h_output, d_output, width*height*depth*sizeof(uchar), cudaMemcpyDeviceToHost));
int wState=writeRawFile(path,h_output,width*height*depth);
checkCudaErrors(cudaFree(d_output));
free(h_output);
// cudaDeviceReset causes the driver to clean up all state. While
// not mandatory in normal operation, it is good practice. It is also
// needed to ensure correct operation when the application is being
// profiled. Calling cudaDeviceReset causes all profile data to be
// flushed before the application exits
cudaDeviceReset();
//exit(bTestResult ? EXIT_SUCCESS : EXIT_FAILURE);
}
void loadVolumeData(char *exec_path, char *PathToFile)
{
char *path;
// load volume data
if (PathToFile == NULL)
{
path = sdkFindFilePath(volumeFilename, exec_path);
}
else
{
path = PathToFile;
}
if (path == NULL)
{
fprintf(stderr, "Error unable to find 3D Volume file: '%s'\n", volumeFilename);
exit(EXIT_FAILURE);
}
size_t size = volumeSize.width*volumeSize.height*volumeSize.depth;
uchar *h_volume = loadRawFile(path, size);
//int wState=writeRawFile(path,h_volume,size);
initCuda(h_volume, volumeSize);
free(h_volume);
}
////////////////////////////////////////////////////////////////////////////////
// Program main
////////////////////////////////////////////////////////////////////////////////
int
main(int argc, char **argv)
{
pArgc = &argc;
pArgv = argv;
char *image_file = NULL;
printf("%s Starting...\n\n", sSDKsample);
if (checkCmdLineFlag(argc, (const char **)argv, "file")) //Note cmd line argument is -file "PathToFile/File.raw"
{ // for example -file "C:\ProgramData\NVIDIA Corporation\CUDA Samples\v7.0\2_Graphics\simpleTexture3D_FanBeamCorr\data\TestOCT_Kopie.raw"
getCmdLineArgumentString(argc, (const char **)argv, "file", &image_file);
}
if (image_file)
{
chooseCudaDevice(argc, argv);
loadVolumeData(argv[0],image_file);
runAutoTest(argv[0],image_file);
}
else
{
// use command-line specified CUDA device, otherwise use device with highest Gflops/s
chooseCudaDevice(argc, argv);
loadVolumeData(argv[0],NULL);
runAutoTest(argv[0],NULL);
}
printf("I am finished...\n"
"Can I get some ice cream please\n");
exit(EXIT_SUCCESS);
}
And this is my .cu
#ifndef _SIMPLETEXTURE3D_KERNEL_CU_
#define _SIMPLETEXTURE3D_KERNEL_CU_
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <math.h>
#include <helper_cuda.h>
#include <helper_math.h>
typedef unsigned int uint;
typedef unsigned char uchar;
texture<uchar, 3, cudaReadModeNormalizedFloat> tex; // 3D texture
cudaArray *d_volumeArray = 0;
__global__ void
d_render(uint *d_output, uint imageW, uint imageH, uint imageD)
{
uint x = __umul24(blockIdx.x, blockDim.x) + threadIdx.x;
uint y = __umul24(blockIdx.y, blockDim.y) + threadIdx.y;
uint z = __umul24(blockIdx.z, blockDim.z) + threadIdx.z;
// float u = x / (float) imageW;
// float v = y / (float) imageH;
//float w = z / (float) imageD;
// // read from 3D texture
// float voxel = tex3D(tex, u, v, w);
uint ps=__umul24(imageW,imageH);
if ((x < imageW) && (y < imageH) && (z < imageD))
{
// write output color
uint i = __umul24(z,ps) +__umul24(y, imageW) + x;
d_output[1] = (uchar) 255;//+0*voxel*255;
}
}
extern "C"
void initCuda(const uchar *h_volume, cudaExtent volumeSize)
{
// create 3D array
cudaChannelFormatDesc channelDesc = cudaCreateChannelDesc<uchar>();
checkCudaErrors(cudaMalloc3DArray(&d_volumeArray, &channelDesc, volumeSize));
// copy data to 3D array
cudaMemcpy3DParms copyParams = {0};
copyParams.srcPtr = make_cudaPitchedPtr((void *)h_volume, volumeSize.width*sizeof(uchar), volumeSize.width, volumeSize.height);
copyParams.dstArray = d_volumeArray;
copyParams.extent = volumeSize;
copyParams.kind = cudaMemcpyHostToDevice;
checkCudaErrors(cudaMemcpy3D(&copyParams));
// set texture parameters
tex.normalized = true; // access with normalized texture coordinates
tex.filterMode = cudaFilterModeLinear; // linear interpolation
tex.addressMode[0] = cudaAddressModeBorder; // wrap texture coordinates
tex.addressMode[1] = cudaAddressModeBorder;
tex.addressMode[2] = cudaAddressModeBorder;
// bind array to 3D texture
checkCudaErrors(cudaBindTextureToArray(tex, d_volumeArray, channelDesc));
}
extern "C"
void render_kernel(dim3 gridSize, dim3 blockSize, uint *d_output, uint imageW, uint imageH, uint imageD)
{
d_render<<<gridSize, blockSize>>>(d_output, imageW, imageH, imageD);
}
#endif // #ifndef _SIMPLETEXTURE3D_KERNEL_CU_
As you can see, currently, I set all values to zero except the index = 1, which is set to 255. Yet when I now open the image stack in Fiji, I see that the fourth pixel on the first slide is white. If I use index=i instead, I get white vertical lines across the image stack periodically every four columns. Generally spoken, it seems that only every fourth element is beeing indexed in the CudaArray. So I am wondering if there is somekind of error here resulting from sizeof(uchar)=1 and sizeof(uint)=4. There would obviously be the factor 4 :)
I am eager to here from you experts
Cheers Mika
I figured it out by myself. The kernel works with uint* d_output while the copy to the host is written into a uchar* h_output
uchar *h_output = (uchar*)malloc(width*height*depth);
checkCudaErrors(cudaMemcpy(h_output, d_output, width*height*depth*sizeof(uchar), cudaMemcpyDeviceToHost));
This led to this strange behavior

Flip and crop a bitmap

I'm getting a bytearray (32 bit or 16 bit) from a source.
If the size width is odd, the last pixel in each row needs to be dropped.
If the height is odd, the last row needs to be dropped.
If the height is negative the bitmap needs to be flipped vertically.
Here is my code so far:
m_pbmiLast = new BITMAPINFO(*m_pbmi);
m_pbmiLast->bmiHeader.biWidth = abs(m_pbmiLast->bmiHeader.biWidth) - (abs(m_pbmiLast->bmiHeader.biWidth) % 2);
m_pbmiLast->bmiHeader.biHeight = abs(m_pbmiLast->bmiHeader.biHeight) - (abs(m_pbmiLast->bmiHeader.biHeight) % 2);
int biWidth = m_pbmiLast->bmiHeader.biWidth;
int biHeight = m_pbmiLast->bmiHeader.biHeight;
int iAdjustedStride = ((((biWidth * m_pbmiLast->bmiHeader.biBitCount) + 31) & ~31) >> 3);
int iRealStride = ((((m_pbmi->bmiHeader.biWidth * m_pbmi->bmiHeader.biBitCount) + 31) & ~31) >> 3);
if (m_pbmi->bmiHeader.biHeight < 0) {
/* Copy the actual data */
int iLineOffsetSource = 0;
int iLineOffsetDest = (biHeight - 1) * iRealStride;
for (int i = 0; i < biHeight; ++i) {
memcpy(&pData[iLineOffsetDest], &m_inputBuffer[iLineOffsetSource], iAdjustedStride);
iLineOffsetSource += iRealStride;
iLineOffsetDest -= iRealStride;
}
} else {
int iLineOffset = 0;
for (int i = 0; i < biHeight; ++i) {
memcpy(&pData[iLineOffset], &m_inputBuffer[iLineOffset], iAdjustedStride);
iLineOffset += iRealStride;
}
}
It doesn't flip the bitmap, and when the bitmap is an odd width, it slants the bitmap.
Can be done like so.. I include the reading and writing just to make it an SSCCE. It has little to no error.
As for my comment about new BITMAPINFO. I was saying that you don't have to allocate such a small structure on the HEAP. Ditch the new part. The only allocation you need for a bitmap is the pixels. The header and other info does not need an allocation at all.
See the Flip function below.
#include <iostream>
#include <fstream>
#include <cstring>
#include <windows.h>
typedef struct
{
BITMAPFILEHEADER Header;
BITMAPINFO Info;
unsigned char* Pixels;
} BITMAPDATA;
void LoadBmp(const char* path, BITMAPDATA* Data)
{
std::ifstream hFile(path, std::ios::in | std::ios::binary);
if(hFile.is_open())
{
hFile.read((char*)&Data->Header, sizeof(Data->Header));
hFile.read((char*)&Data->Info, sizeof(Data->Info));
hFile.seekg(Data->Header.bfOffBits, std::ios::beg);
Data->Pixels = new unsigned char[Data->Info.bmiHeader.biSizeImage];
hFile.read((char*)Data->Pixels, Data->Info.bmiHeader.biSizeImage);
hFile.close();
}
}
void SaveBmp(const char* path, BITMAPDATA* Data)
{
std::ofstream hFile(path, std::ios::out | std::ios::binary);
if (hFile.is_open())
{
hFile.write((char*)&Data->Header, sizeof(Data->Header));
hFile.write((char*)&Data->Info, sizeof(Data->Info));
hFile.seekp(Data->Header.bfOffBits, std::ios::beg);
hFile.write((char*)Data->Pixels, Data->Info.bmiHeader.biSizeImage);
hFile.close();
}
}
void Flip(BITMAPDATA* Data)
{
unsigned short bpp = Data->Info.bmiHeader.biBitCount;
unsigned int width = std::abs(Data->Info.bmiHeader.biWidth);
unsigned int height = std::abs(Data->Info.bmiHeader.biHeight);
unsigned char* out = new unsigned char[Data->Info.bmiHeader.biSizeImage];
unsigned long chunk = (bpp > 24 ? width * 4 : width * 3 + width % 4);
unsigned char* dst = out;
unsigned char* src = Data->Pixels + chunk * (height - 1);
while(src != Data->Pixels)
{
std::memcpy(dst, src, chunk);
dst += chunk;
src -= chunk;
}
std::memcpy(dst, src, chunk); //for 24-bit.
std::swap(Data->Pixels, out);
delete[] out;
}
int main()
{
BITMAPDATA Data;
LoadBmp("C:/Users/Brandon/Desktop/Bar.bmp", &Data);
Flip(&Data);
SaveBmp("C:/Users/Brandon/Desktop/Foo.bmp", &Data);
delete[] Data.Pixels;
return 0;
}

Examples or tutorials of using libjpeg-turbo's TurboJPEG

The instructions for libjpeg-turbo here describes the TurboJPEG API thus: "This API wraps libjpeg-turbo and provides an easy-to-use interface for compressing and decompressing JPEG images in memory". Great, but are there some solid examples of using this API available? Just looking to decompress a fairly vanilla jpeg in memory.
I've found a few bits such as https://github.com/erlyvideo/jpeg/blob/master/c_src/jpeg.c, which appears to be using the TurboJPEG API, but are there any more solid/varied examples?
The source for libjpeg-turbo is well documented, so that does help.
Ok, I know that you did already solve your problem, but as some people, just like me, could be searching some simple example I will share what I created.
It is an example, compressing and decompressing an RGB image. Otherwise I think that the API documentation of TurboJPEG is quite easy to understand!
Compression:
#include <turbojpeg.h>
const int JPEG_QUALITY = 75;
const int COLOR_COMPONENTS = 3;
int _width = 1920;
int _height = 1080;
long unsigned int _jpegSize = 0;
unsigned char* _compressedImage = NULL; //!< Memory is allocated by tjCompress2 if _jpegSize == 0
unsigned char buffer[_width*_height*COLOR_COMPONENTS]; //!< Contains the uncompressed image
tjhandle _jpegCompressor = tjInitCompress();
tjCompress2(_jpegCompressor, buffer, _width, 0, _height, TJPF_RGB,
&_compressedImage, &_jpegSize, TJSAMP_444, JPEG_QUALITY,
TJFLAG_FASTDCT);
tjDestroy(_jpegCompressor);
//to free the memory allocated by TurboJPEG (either by tjAlloc(),
//or by the Compress/Decompress) after you are done working on it:
tjFree(&_compressedImage);
After that you have the compressed image in _compressedImage.
To decompress you have to do the following:
Decompression:
#include <turbojpeg.h>
long unsigned int _jpegSize; //!< _jpegSize from above
unsigned char* _compressedImage; //!< _compressedImage from above
int jpegSubsamp, width, height;
unsigned char buffer[width*height*COLOR_COMPONENTS]; //!< will contain the decompressed image
tjhandle _jpegDecompressor = tjInitDecompress();
tjDecompressHeader2(_jpegDecompressor, _compressedImage, _jpegSize, &width, &height, &jpegSubsamp);
tjDecompress2(_jpegDecompressor, _compressedImage, _jpegSize, buffer, width, 0/*pitch*/, height, TJPF_RGB, TJFLAG_FASTDCT);
tjDestroy(_jpegDecompressor);
Some random thoughts:
I just came back over this as I am writing my bachelor thesis, and I noticed that if you run the compression in a loop it is preferable to store the biggest size of the JPEG buffer to not have to allocate a new one every turn. Basically, instead of doing:
long unsigned int _jpegSize = 0;
tjCompress2(_jpegCompressor, buffer, _width, 0, _height, TJPF_RGB,
&_compressedImage, &_jpegSize, TJSAMP_444, JPEG_QUALITY,
TJFLAG_FASTDCT);
we would add an object variable, holding the size of the allocated memory long unsigned int _jpegBufferSize = 0; and before every compression round we would set the jpegSize back to that value:
long unsigned int jpegSize = _jpegBufferSize;
tjCompress2(_jpegCompressor, buffer, _width, 0, _height, TJPF_RGB,
&_compressedImage, &jpegSize, TJSAMP_444, JPEG_QUALITY,
TJFLAG_FASTDCT);
_jpegBufferSize = _jpegBufferSize >= jpegSize? _jpegBufferSize : jpegSize;
after the compression one would compare the memory size with the actual jpegSize and set it to the jpegSize if it is higher than the previous memory size.
I ended up using below code as a working example for both JPEG encoding and decoding. Best example that I can find, it's self-contained that initializes a dummy image and output the encoded image to a local file.
Below code is NOT my own, credit goes to https://sourceforge.net/p/libjpeg-turbo/discussion/1086868/thread/e402d36f/#8722 . Posting it here again to help anyone finds it's difficult to get libjpeg turbo working.
#include "turbojpeg.h"
#include <iostream>
#include <string.h>
#include <errno.h>
using namespace std;
int main(void)
{
unsigned char *srcBuf; //passed in as a param containing pixel data in RGB pixel interleaved format
tjhandle handle = tjInitCompress();
if(handle == NULL)
{
const char *err = (const char *) tjGetErrorStr();
cerr << "TJ Error: " << err << " UNABLE TO INIT TJ Compressor Object\n";
return -1;
}
int jpegQual =92;
int width = 128;
int height = 128;
int nbands = 3;
int flags = 0;
unsigned char* jpegBuf = NULL;
int pitch = width * nbands;
int pixelFormat = TJPF_GRAY;
int jpegSubsamp = TJSAMP_GRAY;
if(nbands == 3)
{
pixelFormat = TJPF_RGB;
jpegSubsamp = TJSAMP_411;
}
unsigned long jpegSize = 0;
srcBuf = new unsigned char[width * height * nbands];
for(int j = 0; j < height; j++)
{
for(int i = 0; i < width; i++)
{
srcBuf[(j * width + i) * nbands + 0] = (i) % 256;
srcBuf[(j * width + i) * nbands + 1] = (j) % 256;
srcBuf[(j * width + i) * nbands + 2] = (j + i) % 256;
}
}
int tj_stat = tjCompress2( handle, srcBuf, width, pitch, height,
pixelFormat, &(jpegBuf), &jpegSize, jpegSubsamp, jpegQual, flags);
if(tj_stat != 0)
{
const char *err = (const char *) tjGetErrorStr();
cerr << "TurboJPEG Error: " << err << " UNABLE TO COMPRESS JPEG IMAGE\n";
tjDestroy(handle);
handle = NULL;
return -1;
}
FILE *file = fopen("out.jpg", "wb");
if (!file) {
cerr << "Could not open JPEG file: " << strerror(errno);
return -1;
}
if (fwrite(jpegBuf, jpegSize, 1, file) < 1) {
cerr << "Could not write JPEG file: " << strerror(errno);
return -1;
}
fclose(file);
//write out the compress date to the image file
//cleanup
int tjstat = tjDestroy(handle); //should deallocate data buffer
handle = 0;
}
In the end I used a combination of random code found on the internet (e.g. https://github.com/erlyvideo/jpeg/blob/master/c_src/jpeg.c) and the .c and header files for libjeg-turbo, which are well documented.
This official API is a good information source aswell.
Here's a fragment of code what I use to load jpeg's from memory. Maybe it will require a bit of fixing, because I extracted it from different files in my project. It will load both - grayscale and rgb images (bpp will be set either to 1 or to 3).
struct Image
{
int bpp;
int width;
int height;
unsigned char* data;
};
struct jerror_mgr
{
jpeg_error_mgr base;
jmp_buf jmp;
};
METHODDEF(void) jerror_exit(j_common_ptr jinfo)
{
jerror_mgr* err = (jerror_mgr*)jinfo->err;
longjmp(err->jmp, 1);
}
METHODDEF(void) joutput_message(j_common_ptr)
{
}
bool Image_LoadJpeg(Image* image, unsigned char* img_data, unsigned int img_size)
{
jpeg_decompress_struct jinfo;
jerror_mgr jerr;
jinfo.err = jpeg_std_error(&jerr.base);
jerr.base.error_exit = jerror_exit;
jerr.base.output_message = joutput_message;
jpeg_create_decompress(&jinfo);
image->data = NULL;
if (setjmp(jerr.jmp)) goto bail;
jpeg_mem_src(&jinfo, img_data, img_size);
if (jpeg_read_header(&jinfo, TRUE) != JPEG_HEADER_OK) goto bail;
jinfo.dct_method = JDCT_FLOAT; // change this to JDCT_ISLOW on Android/iOS
if (!jpeg_start_decompress(&jinfo)) goto bail;
if (jinfo.num_components != 1 && jinfo.num_components != 3) goto bail;
image->data = new (std::nothrow) unsigned char [jinfo.output_width * jinfo.output_height * jinfo.output_components];
if (!image->data) goto bail;
{
JSAMPROW ptr = image->data;
while (jinfo.output_scanline < jinfo.output_height)
{
if (jpeg_read_scanlines(&jinfo, &ptr, 1) != 1) goto bail;
ptr += jinfo.output_width * jinfo.output_components;
}
}
if (!jpeg_finish_decompress(&jinfo)) goto bail;
image->bpp = jinfo.output_components;
image->width = jinfo.output_width;
image->height = jinfo.output_height;
jpeg_destroy_decompress(&jinfo);
return true;
bail:
jpeg_destroy_decompress(&jinfo);
if (image->data) delete [] data;
return false;
}