Converting uint8_t data to AVFrame with FFmpeg - c++

Question

I am currently working in C++ with the Autodesk 3DStudio Max 2014 SDK (toolset 100) and the Ffmpeg library in Visual Studio 2015 and trying to convert a DIB (Device Independent Bitmap) to uint8_t pointer array and then convert these data to an AVFrame.
I don't have any errors, but my video is still black and without meta data.
(no time display, etc)
I made approximatively the same with a Visual Studio Console application to convert jpeg image sequence from disk and this is working fine.
(The only difference is that instead of converting jpeg to AVFrame with the Ffmpeg library, I try to convert raw data to an AVFrame.)
So I think the problem could be either on the DIB conversion to the uint8_t data or the uint8_t data to the AVFrame.
(The second is more plausible, because I used the SFML library to display a window with my rgb uint8_t* data for debuging and it is working fine.)
I first initialize the ffmpeg library :
This function is called once at the beginning.
int Converter::Initialize(AVCodecID codec_id, int width, int height, int fps, const char *filename)
{
avcodec_register_all();
av_register_all();
AVCodec *codec;
inputFrame = NULL;
codecContext = NULL;
pkt = NULL;
file = NULL;
outputFilename = new char[strlen(filename)]();
*outputFilename = '\0';
strcpy(outputFilename, filename);
int ret;
//Initializing AVCodecContext and getting PixelFormat supported by encoder
codec = avcodec_find_encoder(codec_id);
if (!codec)
return 1;
AVPixelFormat pixFormat = codec->pix_fmts[0];
codecContext = avcodec_alloc_context3(codec);
if (!codecContext)
return 1;
codecContext->bit_rate = 400000;
codecContext->width = width;
codecContext->height = height;
codecContext->time_base.num = 1;
codecContext->time_base.den = fps;
codecContext->gop_size = 10;
codecContext->max_b_frames = 1;
codecContext->pix_fmt = pixFormat;
if (codec_id == AV_CODEC_ID_H264)
av_opt_set(codecContext->priv_data, "preset", "slow", 0);
//Actually opening the encoder
if (avcodec_open2(codecContext, codec, NULL) < 0)
return 1;
file = fopen(outputFilename, "wb");
if (!file)
return 1;
inputFrame = av_frame_alloc();
inputFrame->format = codecContext->pix_fmt;
inputFrame->width = codecContext->width;
inputFrame->height = codecContext->height;
ret = av_image_alloc(inputFrame->data, inputFrame->linesize, codecContext->width, codecContext->height, codecContext->pix_fmt, 32);
if (ret < 0)
return 1;
return 0;
}
Then for each frame, I get the DIB and convert to a uint8_t* it with this function :
uint8_t* Util::ToUint8_t(RGBQUAD *data, int width, int height)
{
uint8_t* buf = (uint8_t*)data;
int imageSize = width * height;
size_t rgbquad_size = sizeof(RGBQUAD);
size_t total_bytes = imageSize * rgbquad_size;
uint8_t * pCopyBuffer = new uint8_t[total_bytes];
for (int x = 0; x < width; x++)
{
for (int y = 0; y < height; y++)
{
int index = (x + width * y) * rgbquad_size;
int invertIndex = (x + width* (height - y - 1)) * rgbquad_size;
//BGRA to RGBA
pCopyBuffer[index] = buf[invertIndex + 2];
pCopyBuffer[index + 1] = buf[invertIndex + 1];
pCopyBuffer[index + 2] = buf[invertIndex];
pCopyBuffer[index + 3] = 0xFF;
}
}
return pCopyBuffer;
}
void GetDIBBuffer(Interface* ip, BITMAPINFO *bmi, uint8_t** outBuffer)
{
int size;
ViewExp& view = ip->GetActiveViewExp();
view.getGW()->getDIB(NULL, &size);
bmi = (BITMAPINFO *)malloc(size);
BITMAPINFOHEADER *bmih = (BITMAPINFOHEADER *)bmi;
view.getGW()->getDIB(bmi, &size);
uint8_t * pCopyBuffer = Util::ToUint8_t(bmi->bmiColors, bmih->biWidth, bmih->biHeight);
*outBuffer = pCopyBuffer;
}
This function is used to get the DIB :
void GetViewportDIB(Interface* ip, BITMAPINFO *bmi, BITMAPINFOHEADER *bmih, BitmapInfo biFile, Bitmap *map)
{
int size;
if (!biFile.Name()[0])
return;
ViewExp& view = ip->GetActiveViewExp();
view.getGW()->getDIB(NULL, &size);
bmi = (BITMAPINFO *)malloc(size);
bmih = (BITMAPINFOHEADER *)bmi;
view.getGW()->getDIB(bmi, &size);
biFile.SetWidth((WORD)bmih->biWidth);
biFile.SetHeight((WORD)bmih->biHeight);
biFile.SetType(BMM_TRUE_32);
map = TheManager->Create(&biFile);
map->OpenOutput(&biFile);
map->FromDib(bmi);
map->Write(&biFile);
map->Close(&biFile);
}
And after the conversion to AVFrame and video encoding :
The EncodeFromMem function is call each frame.
int Converter::EncodeFromMem(const char *outputDir, int frameNumber, uint8_t* data)
{
int ret;
inputFrame->pts = frameNumber;
EncodeFrame(data, codecContext, inputFrame, &pkt, file);
return 0;
}
static void RgbToYuv(uint8_t *rgb, AVCodecContext *c, AVFrame *frame)
{
struct SwsContext *swsCtx = NULL;
const int in_linesize[1] = { 3 * c->width };// RGB stride
swsCtx = sws_getCachedContext(swsCtx, c->width, c->height, AV_PIX_FMT_RGB24, c->width, c->height, AV_PIX_FMT_YUV420P, 0, 0, 0, 0);
sws_scale(swsCtx, (const uint8_t * const *)&rgb, in_linesize, 0, c->height, frame->data, frame->linesize);
}
static void EncodeFrame(uint8_t *rgb, AVCodecContext *c, AVFrame *frame, AVPacket **pkt, FILE *file)
{
int ret, got_output;
RgbToYuv(rgb, c, frame);
*pkt = av_packet_alloc();
av_init_packet(*pkt);
(*pkt)->data = NULL;
(*pkt)->size = 0;
ret = avcodec_encode_video2(c, *pkt, frame, &got_output);
if (ret < 0)
{
fprintf(stderr, "Error encoding frame/n");
exit(1);
}
if (got_output)
{
fwrite((*pkt)->data, 1, (*pkt)->size, file);
av_packet_unref(*pkt);
}
}
To finish I have a function that write the packets and free the memory :
This function is called once at the end of the time range.
int Converter::Finalize()
{
int ret, got_output;
uint8_t endcode[] = { 0, 0, 1, 0xb7 };
/* get the delayed frames */
do
{
fflush(stdout);
ret = avcodec_encode_video2(codecContext, pkt, NULL, &got_output);
if (ret < 0)
{
fprintf(stderr, "Error encoding frame/n");
return 1;
}
if (got_output)
{
fwrite(pkt->data, 1, pkt->size, file);
av_packet_unref(pkt);
}
} while (got_output);
fwrite(endcode, 1, sizeof(endcode), file);
fclose(file);
avcodec_close(codecContext);
av_free(codecContext);
av_frame_unref(inputFrame);
av_frame_free(&inputFrame);
//av_freep(&inputFrame->data[0]); //Crash
delete outputFilename;
outputFilename = 0;
return 0;
}
EDIT :
I modify my RgbToYuv function and create another one to convert back the yuv frame to an rgb one.
This not really solve the problem, but maybe focus the problem on the conversion from YuvToRgb.
This is the result of the conversion from YUV to RGB :
![YuvToRgb result]: https://img42.com/kHqpt+
static void YuvToRgb(AVCodecContext *c, AVFrame *frame)
{
struct SwsContext *img_convert_ctx = sws_getContext(c->width, c->height, AV_PIX_FMT_YUV420P, c->width, c->height, AV_PIX_FMT_RGB24, SWS_BICUBIC, NULL, NULL, NULL);
AVFrame * rgbPictInfo = av_frame_alloc();
avpicture_fill((AVPicture*)rgbPictInfo, *(frame)->data, AV_PIX_FMT_RGB24, c->width, c->height);
sws_scale(img_convert_ctx, frame->data, frame->linesize, 0, c->height, rgbPictInfo->data, rgbPictInfo->linesize);
Util::DebugWindow(c->width, c->height, rgbPictInfo->data[0]);
}
static void RgbToYuv(uint8_t *rgb, AVCodecContext *c, AVFrame *frame)
{
AVFrame * rgbPictInfo = av_frame_alloc();
avpicture_fill((AVPicture*)rgbPictInfo, rgb, AV_PIX_FMT_RGBA, c->width, c->height);
struct SwsContext *swsCtx = sws_getContext(c->width, c->height, AV_PIX_FMT_RGBA, c->width, c->height, AV_PIX_FMT_YUV420P, SWS_BICUBIC, NULL, NULL, NULL);
avpicture_fill((AVPicture*)frame, rgb, AV_PIX_FMT_YUV420P, c->width, c->height);
sws_scale(swsCtx, rgbPictInfo->data, rgbPictInfo->linesize, 0, c->height, frame->data, frame->linesize);
YuvToRgb(c, frame);
}