I'm providing audio code for an application that will have multiple streams of audio being played back at the same time. I'm a bit confused by all of the different options, and there are some specific things that I don't quite understand.
I am using the IAudioClient calls to get and set volumes. Is that the best way to get volumes for multiple streams?
It appears that I have to call IAudioClient::Initialize. This function requires a WAVEFORMATEX structure. Are any parameters from that other than the number of channels used in volume setting? Also, it appears that Initialize can only be used once, and volume setting and reading happens many times. Should I save the reference to the IAudioClient and use it each time, or can I release it each time I get or set a volume?
How do I differentiate between two streams being played on the same device (endpoint)?
Here's the code that sets the volume (with the usual checks to make sure each call succeeded eliminated to save space):
hr = CoCreateInstance(__uuidof(MMDeviceEnumerator), NULL, CLSCTX_INPROC_SERVER, IID_PPV_ARGS(&DeviceEnumerator));
hr = DeviceEnumerator->GetDevice((wchar_t *)currentPlaybackDevice.id, &pPlaybackDevice);
hr = pPlaybackDevice->Activate(__uuidof(IAudioClient), CLSCTX_INPROC_SERVER, NULL, reinterpret_cast<void **>(&pPlaybackClient));
hr = pPlaybackClient->Initialize(AUDCLNT_SHAREMODE_SHARED, 0, 0, 0, &pWaveFormat, 0);
hr = pPlaybackClient->GetService(__uuidof(IAudioStreamVolume), (void **)&pStreamVolume);
hr = pStreamVolume->GetChannelCount(&channels);
for(UINT32 i = 0; i < channels; i++)
chanVolumes[i] = playbackLevel;
hr = pStreamVolume->SetAllVolumes(channels, chanVolumes);
Number of channels is irrelevant to volume. T adjust volume you need to obtain interfaces IAudioStreamVolume, IChannelAudioVolume. See MSDN writes:
The IAudioStreamVolume interface enables a client to control and
monitor the volume levels for all of the channels in an audio stream.
The client obtains a reference to the IAudioStreamVolume interface on
a stream object by calling the IAudioClient::GetService method with
parameter riid set to REFIID IID_IAudioStreamVolume.
Here is the code snippet for you. It plays synthesized sine wave at louder volume for a few seconds, then continues with updated volume to keep playing quietly.
#define _USE_MATH_DEFINES
#include <math.h>
#include <mmdeviceapi.h>
#include <audioclient.h>
#define _A ATLASSERT
#define __C ATLENSURE_SUCCEEDED
#define __D ATLENSURE_THROW
int _tmain(int argc, _TCHAR* argv[])
{
__C(CoInitialize(NULL));
CComPtr<IMMDeviceEnumerator> pMmDeviceEnumerator;
__C(pMmDeviceEnumerator.CoCreateInstance(__uuidof(MMDeviceEnumerator)));
CComPtr<IMMDevice> pMmDevice;
__C(pMmDeviceEnumerator->GetDefaultAudioEndpoint(eRender, eMultimedia, &pMmDevice));
CComPtr<IAudioClient> pAudioClient;
__C(pMmDevice->Activate(__uuidof(IAudioClient), CLSCTX_ALL, NULL, (VOID**) &pAudioClient));
CComHeapPtr<WAVEFORMATEX> pWaveFormatEx;
__C(pAudioClient->GetMixFormat(&pWaveFormatEx));
static const REFERENCE_TIME g_nBufferTime = 60 * 1000 * 10000i64; // 1 minute
__C(pAudioClient->Initialize(AUDCLNT_SHAREMODE_SHARED, 0, g_nBufferTime, 0, pWaveFormatEx, NULL));
#pragma region Data
CComPtr<IAudioRenderClient> pAudioRenderClient;
__C(pAudioClient->GetService(__uuidof(IAudioRenderClient), (VOID**) &pAudioRenderClient));
UINT32 nSampleCount = (UINT32) (g_nBufferTime / (1000 * 10000i64) * pWaveFormatEx->nSamplesPerSec) / 2;
_A(pWaveFormatEx->wFormatTag == WAVE_FORMAT_EXTENSIBLE);
const WAVEFORMATEXTENSIBLE* pWaveFormatExtensible = (const WAVEFORMATEXTENSIBLE*) (const WAVEFORMATEX*) pWaveFormatEx;
_A(pWaveFormatExtensible->SubFormat == KSDATAFORMAT_SUBTYPE_IEEE_FLOAT);
// ASSU: Mixing format is IEEE Float PCM
BYTE* pnData = NULL;
__C(pAudioRenderClient->GetBuffer(nSampleCount, &pnData));
FLOAT* pfFloatData = (FLOAT*) pnData;
for(UINT32 nSampleIndex = 0; nSampleIndex < nSampleCount; nSampleIndex++)
for(WORD nChannelIndex = 0; nChannelIndex < pWaveFormatEx->nChannels; nChannelIndex++)
pfFloatData[nSampleIndex * pWaveFormatEx->nChannels + nChannelIndex] = sin(1000.0f * nSampleIndex / pWaveFormatEx->nSamplesPerSec * 2 * M_PI);
__C(pAudioRenderClient->ReleaseBuffer(nSampleCount, 0));
#pragma endregion
CComPtr<ISimpleAudioVolume> pSimpleAudioVolume;
__C(pAudioClient->GetService(__uuidof(ISimpleAudioVolume), (VOID**) &pSimpleAudioVolume));
__C(pSimpleAudioVolume->SetMasterVolume(0.50f, NULL));
_tprintf(_T("Playing Loud\n"));
__C(pAudioClient->Start());
Sleep(5 * 1000);
_tprintf(_T("Playing Quiet\n"));
__C(pSimpleAudioVolume->SetMasterVolume(0.10f, NULL));
Sleep(15 * 1000);
// NOTE: We don't care for termination crash
return 0;
}
Related
I'm new to FFMPEG and trying to use it to do some screen capture to a video file, but after a lot of online searching I am stumped as to what I'm doing wrong. Basically, I've already done the effort of capturing screen data via DirectX which stores in a BGR pixel format and I'm just trying to put each frame in a video file. There's two functions, setup which does all the ffmpeg initialization work, and addImage which is called in the main program loop and puts each buffer of BGR image data into a video file. The technique I'm doing for this is to make two frames, one with the BGR data and one with YUP420P (doesn't need to be the latter but after a lot of trial and error it was all I was able to get working with H.264), and use sws_scale to copy data between the two, and then send that frame to video.mp4. The file seems to be having data written to it successfully (the file size grows and grows as the program runs), but when I try and view it in VLC I see nothing- indeed, VLC fails to fetch a length of the video, and bringing up codec and media information both are empty. I turned on ffmpeg verbose logging but all that is spit out is the following:
Setting default whitelist 'Epu��'
Timestamps are unset in a packet for stream -1259342440. This is deprecated and will stop working in the future. Fix your code to set the timestamps properly
Encoder did not produce proper pts, making some up.
From what I am reading, I understand this to be warnings rather than errors that would totally corrupt my video file. I separately went through all the error codes being spit out and everything seems nominal to me (zero for success for most calls, -11 sometimes for avcodec_receive_packet but the docs indicate that's expected sometimes).
Based on my understanding of things as they are, this should be working, but isn't, and the logs and error codes give me nothing to go on, so someone with experience with this I reckon would save me a ton of time. The code is as follows:
VideoService.h
#ifndef VIDEO_SERVICE_H
#define VIDEO_SERVICE_H
extern "C" {
#include <libavcodec/avcodec.h>
#include <libavformat/avformat.h>
#include <libavutil/imgutils.h>
#include <libswscale/swscale.h>
}
class VideoService {
public:
void setup();
void addImage(unsigned char* data, int lineSize, int width, int height, int align);
private:
AVCodecContext* context;
AVFormatContext* formatContext;
AVFrame* bgrFrame;
AVFrame* yuvFrame;
AVStream* videoStream;
SwsContext* swsContext;
};
#endif
VideoService.cpp
#include "VideoService.h"
#include <stdio.h>
void FfmpegLogCallback(void *ptr, int level, const char *fmt, va_list vargs)
{
FILE* f = fopen("ffmpeg.txt", "a");
fprintf(f, fmt, vargs);
fclose(f);
}
void VideoService::setup() {
int result = 0;
av_log_set_level(AV_LOG_VERBOSE);
av_log_set_callback(FfmpegLogCallback);
bgrFrame = av_frame_alloc();
bgrFrame->width = 1920;
bgrFrame->height = 1080;
bgrFrame->format = AV_PIX_FMT_BGRA;
bgrFrame->time_base.num = 1;
bgrFrame->time_base.den = 60;
result = av_frame_get_buffer(bgrFrame, 1);
yuvFrame = av_frame_alloc();
yuvFrame->width = 1920;
yuvFrame->height = 1080;
yuvFrame->format = AV_PIX_FMT_YUV420P;
yuvFrame->time_base.num = 1;
yuvFrame->time_base.den = 60;
result = av_frame_get_buffer(yuvFrame, 1);
const AVOutputFormat* outputFormat = av_guess_format("mp4", "video.mp4", "video/mp4");
result = avformat_alloc_output_context2(
&formatContext,
outputFormat,
"mp4",
"video.mp4"
);
formatContext->oformat = outputFormat;
const AVCodec* codec = avcodec_find_encoder(AVCodecID::AV_CODEC_ID_H264);
result = avio_open2(&formatContext->pb, "video.mp4", AVIO_FLAG_WRITE, NULL, NULL);
videoStream = avformat_new_stream(formatContext, codec);
AVCodecParameters* codecParameters = videoStream->codecpar;
codecParameters->codec_type = AVMediaType::AVMEDIA_TYPE_VIDEO;
codecParameters->codec_id = AVCodecID::AV_CODEC_ID_HEVC;
codecParameters->width = 1920;
codecParameters->height = 1080;
codecParameters->format = AVPixelFormat::AV_PIX_FMT_YUV420P;
videoStream->time_base.num = 1;
videoStream->time_base.den = 60;
result = avformat_write_header(formatContext, NULL);
codec = avcodec_find_encoder(videoStream->codecpar->codec_id);
context = avcodec_alloc_context3(codec);
context->time_base.num = 1;
context->time_base.den = 60;
avcodec_parameters_to_context(context, videoStream->codecpar);
result = avcodec_open2(context, codec, nullptr);
swsContext = sws_getContext(1920, 1080, AV_PIX_FMT_BGRA, 1920, 1080, AV_PIX_FMT_YUV420P, 0, 0, 0, 0);
}
void VideoService::addImage(unsigned char* data, int lineSize, int width, int height, int align) {
int result = 0;
result = av_image_fill_arrays(bgrFrame->data, bgrFrame->linesize, data, AV_PIX_FMT_BGRA, 1920, 1080, 1);
sws_scale(swsContext, bgrFrame->data, bgrFrame->linesize, 0, 1080, &yuvFrame->data[0], yuvFrame->linesize);
result = avcodec_send_frame(context, yuvFrame);
AVPacket *packet = av_packet_alloc();
result = avcodec_receive_packet(context, packet);
if (result != 0) {
return;
}
result = av_interleaved_write_frame(formatContext, packet);
}
My environment is windows 10, I'm building with clang++ 12.0.1, and using the FFMPEG 5.1 libs.
See the official sample, muxing.c.
Fix you code like the following.
Set fields of an AVCodecContext and call the avcodec_parameters_from_context(), instead of calling the avcodec_parameters_to_context(). You should set width, height, bit_rate, pix_fmt, framerate and time_base at least.(See the implementation of the add_stream() in the sample.)
Specify an algorithm such as the SWS_BILINEAR when calling the sws_getContext().(Although a default algorithm will be selected, that's an undocumented feature.)
Set the pts(presentation timestamp) field of an AVFrame.
Implement a loop calling the avcodec_receive_packet() after calling the avcodec_send_frame(). See the write_frame() in the sample.(Single frame can result in multiple packets.)
I am hearing a very loud and harsh distortion sound when I run this simple application. I am simply instantiating a default output unit and assign a render callback. And letting the program run in the runloop. I have detected no errors from Core Audio and everything works as usual except for this distortion.
#import <AudioToolbox/AudioToolbox.h>
OSStatus render1(void *inRefCon,
AudioUnitRenderActionFlags *ioActionFlags,
const AudioTimeStamp *inTimeStamp,
UInt32 inBusNumber,
UInt32 inNumberFrames,
AudioBufferList * ioData)
{
return noErr;
}
int main(int argc, const char * argv[]) {
AudioUnit timerAU;
UInt32 propsize = 0;
AudioComponentDescription outputUnitDesc;
outputUnitDesc.componentType = kAudioUnitType_Output;
outputUnitDesc.componentSubType = kAudioUnitSubType_DefaultOutput;
outputUnitDesc.componentManufacturer = kAudioUnitManufacturer_Apple;
outputUnitDesc.componentFlags = 0;
outputUnitDesc.componentFlagsMask = 0;
//Get RemoteIO AU from Audio Unit Component Manager
AudioComponent outputComp = AudioComponentFindNext(NULL, &outputUnitDesc);
if (outputComp == NULL) exit (-1);
CheckError(AudioComponentInstanceNew(outputComp, &timerAU), "comp");
//Set up render callback function for the RemoteIO AU.
AURenderCallbackStruct renderCallbackStruct;
renderCallbackStruct.inputProc = render1;
renderCallbackStruct.inputProcRefCon = nil;//(__bridge void *)(self);
propsize = sizeof(renderCallbackStruct);
CheckError(AudioUnitSetProperty(timerAU,
kAudioUnitProperty_SetRenderCallback,
kAudioUnitScope_Global,
0,
&renderCallbackStruct,
propsize), "set render");
CheckError(AudioUnitInitialize(timerAU), "init");
// tickMethod = completion;
CheckError(AudioOutputUnitStart(timerAU), "start");
CFRunLoopRunInMode(kCFRunLoopDefaultMode, 1000, false);
}
Your question does not seem complete. I don't know about the side effects of silencing the output noise which is probably just undefined behavior. I also don't know what your code would serve for as such. There is an unfinished render callback on the kAudioUnitSubType_DefaultOutput which does nothing (it is not generating silence!). I know for two ways of silencing it.
In the callback the ioData buffers have to be explicitly filled with zeroes, because there's no guarantee they will be initialized empty:
Float32 * lBuffer0;
Float32 * lBuffer1;
lBuffer0 = (Float32 *)ioData->mBuffers[0].mData;
lBuffer1 = (Float32 *)ioData->mBuffers[1].mData;
memset(lBuffer0, 0, inNumberFrames*sizeof(Float32));
memset(lBuffer1, 0, inNumberFrames*sizeof(Float32));
Other possibility is to leave the unfinished callback as it is, but declare the timerAU to be of outputUnitDesc.componentSubType = kAudioUnitSubType_HALOutput; instead of
outputUnitDesc.componentSubType = kAudioUnitSubType_DefaultOutput;
and explicity disable I/O before setting the render callback by means of following code:
UInt32 lEnableIO = 0;
CheckError(AudioUnitSetProperty(timerAU,
kAudioOutputUnitProperty_EnableIO,
kAudioUnitScope_Output,
0, //output element
&lEnableIO,
sizeof(lEnableIO)),
"couldn't disable output");
I would strongly encourage into studying thoroughly the CoreAudio API and understanding how to set up an audio unit. This is crucial in understanding the matter. I've seen in your code a comment mentioning a RemoteIO AU. There is nothing like a RemoteIO AU in OSX. In case you're attempting a port from iOS code, please try learning the differences. They are well documented.
I've searched the net, I've searched here. I've found code that I could compile and it works fine, but for some reason my code won't produce any sound. I'm porting an old game to the PC (Windows,) and I'm trying to make it as authentic as possible, so I'm wanting to use generated wave forms. I've pretty much copied and pasted the working code (only adding in multiple voices,) and it still won't work (even thought the exact same code for a single voice works fine.) I know I'm missing something obvious, but I just cannot figure out what. Any help would be appreciated thank you.
First some notes... I was looking for something that would allow me to use the original methodology. The original system used paired bytes for music (sound effects - only 2 - were handled in code.) A time byte that counted down every time the routine was called, and a note byte that was played until time reached zero. this was done by patching into the interrupt vector, windows doesn't allow that, so I set up a timer that routing that accomplished the same thing. The timer kicks in, updates the display, and then runs the music sequence. I set this up with a defined time so that I only have one place to adjust the timing at (to get it as close as possible to the original sequence. The music is a generated wave form (and I've double checked the math, and even examined the generated data in debug mode,) and it looks good. The sequence looks good, but doesn't actually produce sound. I tried SDL2 first, and it's method of only playing 1 sound doesn't work for me, also, unless I make the sample duration extremely short (and the sound produced this way is awful,) I can't match the timing (it plays the entire sample through it's own interrupt without letting me make adjustments.) Also, blending the 3 voices together (when they all run with different timings,) is a mess. Most of the other engines I examined work in much the same way, they want to use their own callback interrupt and won't allow me to tweak it appropriately. This is why I started working with OpenAL. It allows multiple voices (sources,) and allows me to set the timings myself. On advice from several forums, I set it up so that the sample lengths are all multiples of full cycles.
Anyway, here's the code.
int main(int argc, char* argv[])
{
FreeConsole(); //Get rid of the DOS console, don't need it
if (InitLog() < 0) return -1; //Start logging
UINT_PTR tim = NULL;
SDL_Event event;
InitVideo(false); //Set to window for now, will put options in later
curmusic = 5;
InitAudio();
SetTimer(NULL,tim,_FREQ_,TimerProc);
SDL_PollEvent(&event);
while (event.type != SDL_KEYDOWN) SDL_PollEvent(&event);
SDL_Quit();
return 0;
}
void CALLBACK TimerProc(HWND hWind, UINT Msg, UINT_PTR idEvent, DWORD dwTime)
{
RenderOutput();
PlayMusic();
//UpdateTimer();
//RotateGate();
return;
}
void InitAudio(void)
{
ALCdevice *dev;
ALCcontext *cxt;
Log("Initializing OpenAL Audio\r\n");
dev = alcOpenDevice(NULL);
if (!dev) {
Log("Failed to open an audio device\r\n");
exit(-1);
}
cxt = alcCreateContext(dev, NULL);
alcMakeContextCurrent(cxt);
if(!cxt) {
Log("Failed to create audio context\r\n");
exit(-1);
}
alGenBuffers(4,Buffer);
if (alGetError() != AL_NO_ERROR) {
Log("Error during buffer creation\r\n");
exit(-1);
}
alGenSources(4, Source);
if (alGetError() != AL_NO_ERROR) {
Log("Error during source creation\r\n");
exit(-1);
}
return;
}
void PlayMusic()
{
static int oldsong, ofset, mtime[4];
double freq;
ALuint srate = 44100;
ALuint voice, i, note, len, hold;
short buf[4][_BUFFSIZE_];
bool test[4] = {false, false, false, false};
if (curmusic != oldsong) {
oldsong = (int)curmusic;
if (curmusic > 0)
ofset = moffset[(curmusic - 1)];
for (voice = 1; voice < 4; voice++)
alSourceStop(Source[voice]);
mtime[voice] = 0;
return;
}
if (curmusic == 0) return;
//Only 3 voices for music, but have
for (voice = 0; voice < 3; voice ++) { // 4 set asside for eventual sound effects
if (mtime[voice] == 0) { //is note finished
alSourceStop(Source[voice]); //It is, so stop the channel (source)
mtime[voice] = music[ofset++]; //Get the next duration
if (mtime[voice] == 0) {oldsong = 0; return;} //zero marks end, so restart
note = music[ofset++]; //Get the next note
if (note > 127) { //Old HW data was designed for could only
if (note == 255) note = 127; //use values 128 - 255 (255 = 127)
freq = (15980 / (voice + (int)(voice / 3))) / (256 - note); //freq of note
len = (ALuint)(srate / freq); //A single cycle of that freq.
hold = len;
while (len < (srate / (1000 / _FREQ_))) len += hold; //Multiply till 1 interrup cycle
while (len > _BUFFSIZE_) len -= hold; //Don't overload buffer
if (len == 0) len = _BUFFSIZE_; //Just to be safe
for (i = 0; i < len; i++) //calculate sine wave and put in buffer
buf[voice][i] = (short)((32760 * sin((2 * M_PI * i * freq) / srate)));
alBufferData(Buffer[voice], AL_FORMAT_MONO16, buf[voice], len, srate);
alSourcei(openAL.Source[i], AL_LOOPING, AL_TRUE);
alSourcei(Source[i], AL_BUFFER, Buffer[i]);
alSourcePlay(Source[voice]);
}
} else --mtime[voice];
}
}
Well, it turns out there were 3 problems with my code. First, you have to link the built wave buffer to the AL generated buffer "before" you link the buffer to the source:
alBufferData(buffer,AL_FORMAT_MONO16,&wave_sample,sample_lenght * sizeof(short),frequency);
alSourcei(source,AL_BUFFER,buffer);
Also in the above example, I multiplied the sample_length by how many bytes are in each sample (in this case "sizeof(short)".
The final problem was that you need to un-link a buffer from the source before you change the buffer data
alSourcei(source,AL_BUFFER,NULL);
The music would play, but not correctly until I added that line to the note change code.
I am developing a multi-platform game that runs on iOS as well as desktops (Windows, Mac, Linux). I want the game to be able to resize certain UI elements depending on the resolution of the screen in inches. The idea is that if a button should be, say, around 1/2 inch across in any interface, it will be scaled automatically that size.
Now for iOS devices this problem is reasonably well solvable using brute force techniques. You can look up the type of the device and use a hard-coded table to determine the screen size in inches for each device. Not the most elegant solution, but sufficient.
Desktops are the tricky ones. What I wish and hope exists is a mechanism by which (some?) monitors report to operating systems their actual screen size in inches. If that mechanism exists and I can access it somehow, I can get good numbers at least for some monitors. But I've never come across any such concept in any of the major OS APIs.
Is there a way to ask for the screen size in inches in Win32? If so, are there monitors that actually provide this information?
(And if the answer is no: Gosh, doesn't this seem awfully useful?)
For Windows, first see SetProcessDPIAware() for a discussion on turning off automatic scaling, and then call GetDeviceCaps( LOGPIXELSX ) and GetDeviceCaps( LOGPIXELSY ) on your HDC to determine the monitor's DPI. Divide the screen resolution on your active monitor by those settings and you've got the size.
Also see this article for a similar discussion on DPI aware apps.
Here is a method I found at the web address "https://ofekshilon.com/2011/11/13/reading-monitor-physical-dimensions-or-getting-the-edid-the-right-way/".
Authour says that measurement is in millimeters.
Does not give you the precise width and height but better approximation than HORSIZE and VERTSIZE. In which I tried on two different monitors and got a max difference of 38 cm (measured screen size - calculated screen size).
#include <SetupApi.h>
#pragma comment(lib, "setupapi.lib")
#define NAME_SIZE 128
const GUID GUID_CLASS_MONITOR = {0x4d36e96e, 0xe325, 0x11ce, 0xbf, 0xc1, 0x08, 0x00, 0x2b, 0xe1, 0x03, 0x18};
// Assumes hDevRegKey is valid
bool GetMonitorSizeFromEDID(const HKEY hDevRegKey, short& WidthMm, short& HeightMm)
{
DWORD dwType, AcutalValueNameLength = NAME_SIZE;
TCHAR valueName[NAME_SIZE];
BYTE EDIDdata[1024];
DWORD edidsize=sizeof(EDIDdata);
for (LONG i = 0, retValue = ERROR_SUCCESS; retValue != ERROR_NO_MORE_ITEMS; ++i)
{
retValue = RegEnumValueA ( hDevRegKey, i, &valueName[0],
&AcutalValueNameLength, NULL, &dwType,
EDIDdata, // buffer
&edidsize); // buffer size
if (retValue != ERROR_SUCCESS || 0 != strcmp(valueName,"EDID"))
continue;
WidthMm = ((EDIDdata[68] & 0xF0) << 4) + EDIDdata[66];
HeightMm = ((EDIDdata[68] & 0x0F) << 8) + EDIDdata[67];
return true; // valid EDID found
}
return false; // EDID not found
}
// strange! Authour requires TargetDevID argument but does not use it
bool GetSizeForDevID(const char *TargetDevID, short& WidthMm, short& HeightMm)
{
HDEVINFO devInfo = SetupDiGetClassDevsExA(
&GUID_CLASS_MONITOR, //class GUID
NULL, //enumerator
NULL, //HWND
DIGCF_PRESENT, // Flags //DIGCF_ALLCLASSES|
NULL, // device info, create a new one.
NULL, // machine name, local machine
NULL);// reserved
if (NULL == devInfo) return false;
bool bRes = false;
for (ULONG i=0; ERROR_NO_MORE_ITEMS != GetLastError(); ++i)
{
SP_DEVINFO_DATA devInfoData;
memset(&devInfoData,0,sizeof(devInfoData));
devInfoData.cbSize = sizeof(devInfoData);
if (SetupDiEnumDeviceInfo(devInfo,i,&devInfoData))
{
HKEY hDevRegKey = SetupDiOpenDevRegKey(devInfo,&devInfoData,DICS_FLAG_GLOBAL, 0, DIREG_DEV, KEY_READ);
if(!hDevRegKey || (hDevRegKey == INVALID_HANDLE_VALUE)) continue;
bRes = GetMonitorSizeFromEDID(hDevRegKey, WidthMm, HeightMm);
RegCloseKey(hDevRegKey);
}
}
SetupDiDestroyDeviceInfoList(devInfo);
return bRes;
}
int main(int argc, CHAR* argv[])
{
short WidthMm, HeightMm;
DISPLAY_DEVICE dd;
dd.cb = sizeof(dd);
DWORD dev = 0; // device index
int id = 1; // monitor number, as used by Display Properties > Settings
char DeviceID[1024];
bool bFoundDevice = false;
while (EnumDisplayDevices(0, dev, &dd, 0) && !bFoundDevice)
{
DISPLAY_DEVICE ddMon = {sizeof(ddMon)};
DWORD devMon = 0;
while (EnumDisplayDevices(dd.DeviceName, devMon, &ddMon, 0) && !bFoundDevice)
{
if (ddMon.StateFlags & DISPLAY_DEVICE_ATTACHED_TO_DESKTOP &&
!(ddMon.StateFlags & DISPLAY_DEVICE_MIRRORING_DRIVER))
{
sprintf(DeviceID,"%s", ddMon.DeviceID+8);
for(auto it=DeviceID; *it; ++it)
if(*it == '\\') { *it = 0; break; }
bFoundDevice = GetSizeForDevID(DeviceID, WidthMm, HeightMm);
}
devMon++;
ZeroMemory(&ddMon, sizeof(ddMon));
ddMon.cb = sizeof(ddMon);
}
ZeroMemory(&dd, sizeof(dd));
dd.cb = sizeof(dd);
dev++;
}
return 0;
}
I'm trying to use Color Converter DMO (http://msdn.microsoft.com/en-us/library/windows/desktop/ff819079(v=vs.85).aspx) to convert RBG24 to YV12/NV12 via Media Foundation. I've created an instance of Color Converter DSP via CLSID_CColorConvertDMO and then tried to set the needed input/output types, but the calls always return E_INVALIDARG even when using media types that are returned by GetOutputAvailableType and GetInputAvailableType. If I set the media type to NULL then i get the error that the media type is invalid, that makes sense. I've seen examples from MSDN, where people do the same - enumerate available types and then set them as input types - and they claim it works, but i'm kinda stuck on the E_INVALIDARG. I understand that this is hard to answer without a code example, if no one has had similar experience, I'll try to post a snipplet, but maybe someone has experienced the same issue?
This DMO/DSP is dual interfaced and is both a DMO with IMediaObject and an MFT with IMFTransform. The two interfaces share a lot common, and here is a code snippet to test initialization of RGB24 into YV12 conversion:
#include "stdafx.h"
#include <dshow.h>
#include <dmo.h>
#include <wmcodecdsp.h>
#pragma comment(lib, "strmiids.lib")
#pragma comment(lib, "wmcodecdspuuid.lib")
int _tmain(int argc, _TCHAR* argv[])
{
ATLVERIFY(SUCCEEDED(CoInitialize(NULL)));
CComPtr<IMediaObject> pMediaObject;
ATLVERIFY(SUCCEEDED(pMediaObject.CoCreateInstance(CLSID_CColorConvertDMO)));
VIDEOINFOHEADER InputVideoInfoHeader;
ZeroMemory(&InputVideoInfoHeader, sizeof InputVideoInfoHeader);
InputVideoInfoHeader.bmiHeader.biSize = sizeof InputVideoInfoHeader.bmiHeader;
InputVideoInfoHeader.bmiHeader.biWidth = 1920;
InputVideoInfoHeader.bmiHeader.biHeight = 1080;
InputVideoInfoHeader.bmiHeader.biPlanes = 1;
InputVideoInfoHeader.bmiHeader.biBitCount = 24;
InputVideoInfoHeader.bmiHeader.biCompression = BI_RGB;
InputVideoInfoHeader.bmiHeader.biSizeImage = 1080 * (1920 * 3);
DMO_MEDIA_TYPE InputMediaType;
ZeroMemory(&InputMediaType, sizeof InputMediaType);
InputMediaType.majortype = MEDIATYPE_Video;
InputMediaType.subtype = MEDIASUBTYPE_RGB24;
InputMediaType.bFixedSizeSamples = TRUE;
InputMediaType.bTemporalCompression = FALSE;
InputMediaType.lSampleSize = InputVideoInfoHeader.bmiHeader.biSizeImage;
InputMediaType.formattype = FORMAT_VideoInfo;
InputMediaType.cbFormat = sizeof InputVideoInfoHeader;
InputMediaType.pbFormat = (BYTE*) &InputVideoInfoHeader;
const HRESULT nSetInputTypeResult = pMediaObject->SetInputType(0, &InputMediaType, 0);
_tprintf(_T("nSetInputTypeResult 0x%08x\n"), nSetInputTypeResult);
VIDEOINFOHEADER OutputVideoInfoHeader = InputVideoInfoHeader;
OutputVideoInfoHeader.bmiHeader.biBitCount = 12;
OutputVideoInfoHeader.bmiHeader.biCompression = MAKEFOURCC('Y', 'V', '1', '2');
OutputVideoInfoHeader.bmiHeader.biSizeImage = 1080 * 1920 * 12 / 8;
DMO_MEDIA_TYPE OutputMediaType = InputMediaType;
OutputMediaType.subtype = MEDIASUBTYPE_YV12;
OutputMediaType.lSampleSize = OutputVideoInfoHeader.bmiHeader.biSizeImage;
OutputMediaType.cbFormat = sizeof OutputVideoInfoHeader;
OutputMediaType.pbFormat = (BYTE*) &OutputVideoInfoHeader;
const HRESULT nSetOutputTypeResult = pMediaObject->SetOutputType(0, &OutputMediaType, 0);
_tprintf(_T("nSetOutputTypeResult 0x%08x\n"), nSetOutputTypeResult);
// TODO: ProcessInput, ProcessOutput
pMediaObject.Release();
CoUninitialize();
return 0;
}
This should work fine and print two S_OKs out...