[英]Getting green screen in ffplay: Streaming desktop (DirectX surface) as H264 video over RTP stream using Live555
I'm trying to stream the desktop(DirectX surface in NV12 format) as H264 video over RTP stream using Live555 & Windows media foundation's hardware encoder on Windows10, and expecting it to be rendered by ffplay (ffmpeg 4.2). 但只得到一个像下面这样的绿屏,
我参考了 MFWebCamToRTP mediafoundation-sample & Encoding DirectX surface using hardware MFT来实现 live555 的 FramedSource 并将输入源更改为 DirectX surface 而不是 webCam。
这是我对 Live555 的 doGetNextFrame 回调的实现的摘录,以从 directX 表面提供输入样本:
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);
}
初始化方法:
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;
}
ffplay 命令:
ffplay -protocol_whitelist file,udp,rtp -i test.sdp -x 800 -y 600 -profile:v baseline
发展规划署:
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
我不知道我错过了什么,我已经尝试解决这个问题将近一个星期没有任何进展,并且尝试了几乎所有我能做的事情。 此外,用于将 DirectX 表面编码为视频的在线资源非常有限。
任何帮助,将不胜感激。
这比看起来更难。
如果你想像你一样使用编码器,通过直接调用IMFTransform接口,你必须将RGB帧转换为NV12。 如果你想要好的性能,你应该在 GPU 上做。 可以使用像素着色器,渲染 2 帧,全尺寸一到 DXGI_FORMAT_R8_UNORM 渲染目标的亮度,半尺寸到 DXGI_FORMAT_R8G8_UNORM 目标的颜色,并写入两个像素着色器以产生 NV12 值。 两个渲染目标都可以渲染到相同 NV12 纹理的 2 个平面中,但仅从 Windows 8 开始。
其他方法是使用sink writer 。 它可以同时托管多个 MFT,因此您可以在 VRAM 中提供 RGB 纹理,接收器写入器将首先使用一个 MFT 将它们转换为 NV12(这可能是由 GPU 驱动程序实现的专有硬件,就像编码器一样),然后传递给编码器 MFT。 编码成 mp4 文件相对容易,使用MFCreateSinkWriterFromURL API 来创建 writer。 但是,从接收器写入器中获取原始样本要困难得多,您必须实现自定义媒体接收器,自定义 stream 接收器的视频 stream 接收器,并调用MFCreateSinkWriterFromMediaSink来创建写入器。
还有更多。
无论采用何种编码方法,您都不能重用帧纹理。 从 DD 获得的每一帧,都应该创建一个新纹理并将其传递给 MF。
视频编码器期望恒定的帧速率。 DD 不会给你那个,它每次屏幕上发生变化时都会给你一个框架。 如果您有游戏显示器,则可以为 144 FPS,如果唯一的变化是闪烁 cursor,则可以为 2 FPS。 理想情况下,您应该以视频媒体类型中指定的恒定帧速率向 MF 提交帧。
如果您想将 stream 联网,通常您还必须提供参数集。 除非您使用的 Intel 硬件 h265 编码器已损坏且 Intel 没有评论,否则MF 通过调用 IMFMediaTypeHandler 接口上的 SetCurrentMediaType 为您提供媒体类型的MF_MT_MPEG_SEQUENCE_HEADER 属性中的数据。 您可以实现该接口以获得通知。 您只有在开始编码后才能获得该数据。 那就是如果您使用接收器编写器,对于IMFTransform
方法更容易,您应该从ProcessOutput
方法获取MF_E_TRANSFORM_STREAM_CHANGE
代码,然后调用GetOutputAvailableType
以使用该魔法 blob 获取更新的媒体类型。
由于ffplay
抱怨 stream 参数,我认为它无法获取 SPS/PPS。 您尚未在硬编码的 SDP 中设置它们 - 请参阅RFC-3984并查找sprop-parameter-sets
。 来自 RFC 的一个示例:
m=视频 49170 RTP/AVP 98
a=rtpmap:98 H264/90000
a=fmtp:98 profile-level-id=42A01E;sprop-parameter-sets=Z0IACpZTBYmI,aMljiA==
我强烈认为ffplay
在 SDP 中期待这些。 我不记得如何从媒体基础编码器中获取 SPS/PPS,但是它们都在示例有效负载中,您需要通过查找正确的 NAL 单元来提取它们,或者谷歌如何从编码器 - 我得到的第一个打击看起来很有希望。
Soonts 为您提供所有必要的东西来解决您的问题。
您需要做的第一件事是在 DXGI_FORMAT_B8G8R8A8_UNORM 和 MFVideoFormat_NV12 之间进行格式转换:
我觉得最好用shader来做格式转换,因为所有的贴图都会留在GPU(性能更好)。
这是您需要做的第一步。 您将有其他人来改进您的程序。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.