Estoy tratando de transmitir el escritorio (superficie DirectX en formato NV12) como video H264 sobre transmisión RTP usando el codificador de hardware de Live555 y Windows Media Foundation en Windows10, y espero que sea renderizado por ffplay (ffmpeg 4.2). Pero solo obteniendo una pantalla verde como la siguiente,
Me he referido mediafoundation-muestra MFWebCamToRTP y Codificación DirectX superficie usando MFT de hardware para la implementación de FramedSource live555 y cambiar la fuente de entrada a DirectX superficie en lugar de cámara web.
Aquí hay un extracto de mi implementación para la devolución de llamada doGetNextFrame de Live555 para alimentar muestras de entrada desde la superficie de directX:
virtual void doGetNextFrame()
{
if (!_isInitialised)
{
if (!initialise()) {
printf("Video device initialisation failed, stopping.");
return;
}
else {
_isInitialised = true;
}
}
//if (!isCurrentlyAwaitingData()) return;
DWORD processOutputStatus = 0;
HRESULT mftProcessOutput = S_OK;
MFT_OUTPUT_STREAM_INFO StreamInfo;
IMFMediaBuffer *pBuffer = NULL;
IMFSample *mftOutSample = NULL;
DWORD mftOutFlags;
bool frameSent = false;
bool bTimeout = false;
// Create sample
CComPtr<IMFSample> videoSample = NULL;
// Create buffer
CComPtr<IMFMediaBuffer> inputBuffer;
// Get next event
CComPtr<IMFMediaEvent> event;
HRESULT hr = eventGen->GetEvent(0, &event);
CHECK_HR(hr, "Failed to get next event");
MediaEventType eventType;
hr = event->GetType(&eventType);
CHECK_HR(hr, "Failed to get event type");
switch (eventType)
{
case METransformNeedInput:
{
hr = MFCreateDXGISurfaceBuffer(__uuidof(ID3D11Texture2D), surface, 0, FALSE, &inputBuffer);
CHECK_HR(hr, "Failed to create IMFMediaBuffer");
hr = MFCreateSample(&videoSample);
CHECK_HR(hr, "Failed to create IMFSample");
hr = videoSample->AddBuffer(inputBuffer);
CHECK_HR(hr, "Failed to add buffer to IMFSample");
if (videoSample)
{
_frameCount++;
CHECK_HR(videoSample->SetSampleTime(mTimeStamp), "Error setting the video sample time.\n");
CHECK_HR(videoSample->SetSampleDuration(VIDEO_FRAME_DURATION), "Error getting video sample duration.\n");
// Pass the video sample to the H.264 transform.
hr = _pTransform->ProcessInput(inputStreamID, videoSample, 0);
CHECK_HR(hr, "The resampler H264 ProcessInput call failed.\n");
mTimeStamp += VIDEO_FRAME_DURATION;
}
}
break;
case METransformHaveOutput:
{
CHECK_HR(_pTransform->GetOutputStatus(&mftOutFlags), "H264 MFT GetOutputStatus failed.\n");
if (mftOutFlags == MFT_OUTPUT_STATUS_SAMPLE_READY)
{
MFT_OUTPUT_DATA_BUFFER _outputDataBuffer;
memset(&_outputDataBuffer, 0, sizeof _outputDataBuffer);
_outputDataBuffer.dwStreamID = outputStreamID;
_outputDataBuffer.dwStatus = 0;
_outputDataBuffer.pEvents = NULL;
_outputDataBuffer.pSample = nullptr;
mftProcessOutput = _pTransform->ProcessOutput(0, 1, &_outputDataBuffer, &processOutputStatus);
if (mftProcessOutput != MF_E_TRANSFORM_NEED_MORE_INPUT)
{
if (_outputDataBuffer.pSample) {
//CHECK_HR(_outputDataBuffer.pSample->SetSampleTime(mTimeStamp), "Error setting MFT sample time.\n");
//CHECK_HR(_outputDataBuffer.pSample->SetSampleDuration(VIDEO_FRAME_DURATION), "Error setting MFT sample duration.\n");
IMFMediaBuffer *buf = NULL;
DWORD bufLength;
CHECK_HR(_outputDataBuffer.pSample->ConvertToContiguousBuffer(&buf), "ConvertToContiguousBuffer failed.\n");
CHECK_HR(buf->GetCurrentLength(&bufLength), "Get buffer length failed.\n");
BYTE * rawBuffer = NULL;
fFrameSize = bufLength;
fDurationInMicroseconds = 0;
gettimeofday(&fPresentationTime, NULL);
buf->Lock(&rawBuffer, NULL, NULL);
memmove(fTo, rawBuffer, fFrameSize);
FramedSource::afterGetting(this);
buf->Unlock();
SafeRelease(&buf);
frameSent = true;
_lastSendAt = GetTickCount();
_outputDataBuffer.pSample->Release();
}
if (_outputDataBuffer.pEvents)
_outputDataBuffer.pEvents->Release();
}
//SafeRelease(&pBuffer);
//SafeRelease(&mftOutSample);
break;
}
}
break;
}
if (!frameSent)
{
envir().taskScheduler().triggerEvent(eventTriggerId, this);
}
return;
done:
printf("MediaFoundationH264LiveSource doGetNextFrame failed.\n");
envir().taskScheduler().triggerEvent(eventTriggerId, this);
}
Método de inicialización:
bool initialise()
{
HRESULT hr;
D3D11_TEXTURE2D_DESC desc = { 0 };
HDESK CurrentDesktop = nullptr;
CurrentDesktop = OpenInputDesktop(0, FALSE, GENERIC_ALL);
if (!CurrentDesktop)
{
// We do not have access to the desktop so request a retry
return false;
}
// Attach desktop to this thread
bool DesktopAttached = SetThreadDesktop(CurrentDesktop) != 0;
CloseDesktop(CurrentDesktop);
CurrentDesktop = nullptr;
if (!DesktopAttached)
{
printf("SetThreadDesktop failed\n");
}
UINT32 activateCount = 0;
// h264 output
MFT_REGISTER_TYPE_INFO info = { MFMediaType_Video, MFVideoFormat_H264 };
UINT32 flags =
MFT_ENUM_FLAG_HARDWARE |
MFT_ENUM_FLAG_SORTANDFILTER;
// ------------------------------------------------------------------------
// Initialize D3D11
// ------------------------------------------------------------------------
// Driver types supported
D3D_DRIVER_TYPE DriverTypes[] =
{
D3D_DRIVER_TYPE_HARDWARE,
D3D_DRIVER_TYPE_WARP,
D3D_DRIVER_TYPE_REFERENCE,
};
UINT NumDriverTypes = ARRAYSIZE(DriverTypes);
// Feature levels supported
D3D_FEATURE_LEVEL FeatureLevels[] =
{
D3D_FEATURE_LEVEL_11_0,
D3D_FEATURE_LEVEL_10_1,
D3D_FEATURE_LEVEL_10_0,
D3D_FEATURE_LEVEL_9_1
};
UINT NumFeatureLevels = ARRAYSIZE(FeatureLevels);
D3D_FEATURE_LEVEL FeatureLevel;
// Create device
for (UINT DriverTypeIndex = 0; DriverTypeIndex < NumDriverTypes; ++DriverTypeIndex)
{
hr = D3D11CreateDevice(nullptr, DriverTypes[DriverTypeIndex], nullptr,
D3D11_CREATE_DEVICE_VIDEO_SUPPORT,
FeatureLevels, NumFeatureLevels, D3D11_SDK_VERSION, &device, &FeatureLevel, &context);
if (SUCCEEDED(hr))
{
// Device creation success, no need to loop anymore
break;
}
}
CHECK_HR(hr, "Failed to create device");
// Create device manager
UINT resetToken;
hr = MFCreateDXGIDeviceManager(&resetToken, &deviceManager);
CHECK_HR(hr, "Failed to create DXGIDeviceManager");
hr = deviceManager->ResetDevice(device, resetToken);
CHECK_HR(hr, "Failed to assign D3D device to device manager");
// ------------------------------------------------------------------------
// Create surface
// ------------------------------------------------------------------------
desc.Format = DXGI_FORMAT_NV12;
desc.Width = surfaceWidth;
desc.Height = surfaceHeight;
desc.MipLevels = 1;
desc.ArraySize = 1;
desc.SampleDesc.Count = 1;
hr = device->CreateTexture2D(&desc, NULL, &surface);
CHECK_HR(hr, "Could not create surface");
hr = MFTEnumEx(
MFT_CATEGORY_VIDEO_ENCODER,
flags,
NULL,
&info,
&activateRaw,
&activateCount
);
CHECK_HR(hr, "Failed to enumerate MFTs");
CHECK(activateCount, "No MFTs found");
// Choose the first available encoder
activate = activateRaw[0];
for (UINT32 i = 0; i < activateCount; i++)
activateRaw[i]->Release();
// Activate
hr = activate->ActivateObject(IID_PPV_ARGS(&_pTransform));
CHECK_HR(hr, "Failed to activate MFT");
// Get attributes
hr = _pTransform->GetAttributes(&attributes);
CHECK_HR(hr, "Failed to get MFT attributes");
// Unlock the transform for async use and get event generator
hr = attributes->SetUINT32(MF_TRANSFORM_ASYNC_UNLOCK, TRUE);
CHECK_HR(hr, "Failed to unlock MFT");
eventGen = _pTransform;
CHECK(eventGen, "Failed to QI for event generator");
// Get stream IDs (expect 1 input and 1 output stream)
hr = _pTransform->GetStreamIDs(1, &inputStreamID, 1, &outputStreamID);
if (hr == E_NOTIMPL)
{
inputStreamID = 0;
outputStreamID = 0;
hr = S_OK;
}
CHECK_HR(hr, "Failed to get stream IDs");
// ------------------------------------------------------------------------
// Configure hardware encoder MFT
// ------------------------------------------------------------------------
CHECK_HR(_pTransform->ProcessMessage(MFT_MESSAGE_SET_D3D_MANAGER, reinterpret_cast<ULONG_PTR>(deviceManager.p)), "Failed to set device manager.\n");
// Set low latency hint
hr = attributes->SetUINT32(MF_LOW_LATENCY, TRUE);
CHECK_HR(hr, "Failed to set MF_LOW_LATENCY");
hr = MFCreateMediaType(&outputType);
CHECK_HR(hr, "Failed to create media type");
hr = outputType->SetGUID(MF_MT_MAJOR_TYPE, MFMediaType_Video);
CHECK_HR(hr, "Failed to set MF_MT_MAJOR_TYPE on H264 output media type");
hr = outputType->SetGUID(MF_MT_SUBTYPE, MFVideoFormat_H264);
CHECK_HR(hr, "Failed to set MF_MT_SUBTYPE on H264 output media type");
hr = outputType->SetUINT32(MF_MT_AVG_BITRATE, TARGET_AVERAGE_BIT_RATE);
CHECK_HR(hr, "Failed to set average bit rate on H264 output media type");
hr = MFSetAttributeSize(outputType, MF_MT_FRAME_SIZE, desc.Width, desc.Height);
CHECK_HR(hr, "Failed to set frame size on H264 MFT out type");
hr = MFSetAttributeRatio(outputType, MF_MT_FRAME_RATE, TARGET_FRAME_RATE, 1);
CHECK_HR(hr, "Failed to set frame rate on H264 MFT out type");
hr = outputType->SetUINT32(MF_MT_INTERLACE_MODE, 2);
CHECK_HR(hr, "Failed to set MF_MT_INTERLACE_MODE on H.264 encoder MFT");
hr = outputType->SetUINT32(MF_MT_ALL_SAMPLES_INDEPENDENT, TRUE);
CHECK_HR(hr, "Failed to set MF_MT_ALL_SAMPLES_INDEPENDENT on H.264 encoder MFT");
hr = _pTransform->SetOutputType(outputStreamID, outputType, 0);
CHECK_HR(hr, "Failed to set output media type on H.264 encoder MFT");
hr = MFCreateMediaType(&inputType);
CHECK_HR(hr, "Failed to create media type");
for (DWORD i = 0;; i++)
{
inputType = nullptr;
hr = _pTransform->GetInputAvailableType(inputStreamID, i, &inputType);
CHECK_HR(hr, "Failed to get input type");
hr = inputType->SetGUID(MF_MT_MAJOR_TYPE, MFMediaType_Video);
CHECK_HR(hr, "Failed to set MF_MT_MAJOR_TYPE on H264 MFT input type");
hr = inputType->SetGUID(MF_MT_SUBTYPE, MFVideoFormat_NV12);
CHECK_HR(hr, "Failed to set MF_MT_SUBTYPE on H264 MFT input type");
hr = MFSetAttributeSize(inputType, MF_MT_FRAME_SIZE, desc.Width, desc.Height);
CHECK_HR(hr, "Failed to set MF_MT_FRAME_SIZE on H264 MFT input type");
hr = MFSetAttributeRatio(inputType, MF_MT_FRAME_RATE, TARGET_FRAME_RATE, 1);
CHECK_HR(hr, "Failed to set MF_MT_FRAME_RATE on H264 MFT input type");
hr = _pTransform->SetInputType(inputStreamID, inputType, 0);
CHECK_HR(hr, "Failed to set input type");
break;
}
CheckHardwareSupport();
CHECK_HR(_pTransform->ProcessMessage(MFT_MESSAGE_COMMAND_FLUSH, NULL), "Failed to process FLUSH command on H.264 MFT.\n");
CHECK_HR(_pTransform->ProcessMessage(MFT_MESSAGE_NOTIFY_BEGIN_STREAMING, NULL), "Failed to process BEGIN_STREAMING command on H.264 MFT.\n");
CHECK_HR(_pTransform->ProcessMessage(MFT_MESSAGE_NOTIFY_START_OF_STREAM, NULL), "Failed to process START_OF_STREAM command on H.264 MFT.\n");
return true;
done:
printf("MediaFoundationH264LiveSource initialisation failed.\n");
return false;
}
HRESULT CheckHardwareSupport()
{
IMFAttributes *attributes;
HRESULT hr = _pTransform->GetAttributes(&attributes);
UINT32 dxva = 0;
if (SUCCEEDED(hr))
{
hr = attributes->GetUINT32(MF_SA_D3D11_AWARE, &dxva);
}
if (SUCCEEDED(hr))
{
hr = attributes->SetUINT32(CODECAPI_AVDecVideoAcceleration_H264, TRUE);
}
#if defined(CODECAPI_AVLowLatencyMode) // Win8 only
hr = _pTransform->QueryInterface(IID_PPV_ARGS(&mpCodecAPI));
if (SUCCEEDED(hr))
{
VARIANT var = { 0 };
// FIXME: encoder only
var.vt = VT_UI4;
var.ulVal = 0;
hr = mpCodecAPI->SetValue(&CODECAPI_AVEncMPVDefaultBPictureCount, &var);
var.vt = VT_BOOL;
var.boolVal = VARIANT_TRUE;
hr = mpCodecAPI->SetValue(&CODECAPI_AVEncCommonLowLatency, &var);
hr = mpCodecAPI->SetValue(&CODECAPI_AVEncCommonRealTime, &var);
hr = attributes->SetUINT32(CODECAPI_AVLowLatencyMode, TRUE);
if (SUCCEEDED(hr))
{
var.vt = VT_UI4;
var.ulVal = eAVEncCommonRateControlMode_Quality;
hr = mpCodecAPI->SetValue(&CODECAPI_AVEncCommonRateControlMode, &var);
// This property controls the quality level when the encoder is not using a constrained bit rate. The AVEncCommonRateControlMode property determines whether the bit rate is constrained.
VARIANT quality;
InitVariantFromUInt32(50, &quality);
hr = mpCodecAPI->SetValue(&CODECAPI_AVEncCommonQuality, &quality);
}
}
#endif
return hr;
}
comando ffplay:
ffplay -protocol_whitelist file,udp,rtp -i test.sdp -x 800 -y 600 -profile:v baseline
PARTIDO SOCIALDEMÓCRATA:
v=0
o=- 0 0 IN IP4 127.0.0.1
s=No Name
t=0 0
c=IN IP4 127.0.0.1
m=video 1234 RTP/AVP 96
a=rtpmap:96 H264/90000
a=fmtp:96 packetization-mode=1
No sé qué me estoy perdiendo, he estado tratando de arreglar esto durante casi una semana sin ningún progreso, e intenté casi todo lo que pude. Además, los recursos en línea para codificar una superficie DirectX como video son muy limitados.
Cualquier ayuda sería apreciada.