2
我已經寫一個DirectShow源過濾器，從ATSC-153廣播，寫上的WinCE/ARM視頻處理器取AVC/AAC視頻幀/ AAC接入單元。輸出引腳（其中2個，視頻一個，音頻一個）連接到適當的解碼器和渲染器。目前，我正在從適當的RTP標題中獲取PTS，並將它們傳遞給源過濾器並對directshow時鐘執行計算。視頻PTS的速率爲90KHz，音頻PTS速率不同，我目前的測試流的音頻滴答聲爲55.2Khz。
接下來是convert_to_dshow_timestamp（）和FillBuffer（）例程。在過濾器檢索視頻/音頻時，我打印出轉換後的時間戳，時間差在100-200毫秒之內。這不會是壞事，可以與之合作。但是，視頻會在2-3秒後播放音頻。
/*常規轉換的時鐘速率來器directshow時鐘速率*/ 靜態無符號長長convert_to_dshow_timestamp（ 無符號長長TS， 無符號長率 ） { 長雙赫茲; 長雙倍; long double tmp;
if (rate == 0)
{
return 0;
}
hz = (long double) 1.0/rate;
multi = hz/1e-7;
tmp = ((long double) ts * multi) + 0.5;
return (unsigned long long) tmp;
}
/*源濾波器FillBuffer（）例程*/ HRESULT OutputPin :: FillBuffer（IMediaSample * pSamp） { BYTE * pData所; DWORD dataSize; pipeStream stream; BOOL retVal; DWORD returnBytes; HRESULT hr; DWORD discont; REFERENCE_TIME ts; REFERENCE_TIME df; unsigned long long difPts; unsigned long long difTimeRef;
pSamp->GetPointer(&pData);
dataSize = pSamp->GetSize();
ZeroMemory(pData, dataSize);
stream.lBuf = pData;
stream.dataSize = dataSize;
/* Pin type 1 is H.264 AVC video frames */
if (m_iPinType == 1)
{
retVal = DeviceIoControl(
ghMHTune,
IOCTL_MHTUNE_RVIDEO_STREAM,
NULL,
0,
&stream,
sizeof(pipeStream),
&returnBytes,
NULL
);
if (retVal == TRUE)
{
/* Get the data */
/* Check for the first of the stream, if so, set the start time */
pSamp->SetActualDataLength(returnBytes);
hr = S_OK;
if (returnBytes > 0)
{
/* The discontinuety is set in upper layers, when an RTP
* sequence number has been lost.
*/
discont = stream.discont;
/* Check for another break in stream time */
if (
m_PrevTimeRef &&
((m_PrevTimeRef > (stream.timeRef + 90000 * 10)) ||
((m_PrevTimeRef + 90000 * 10) < stream.timeRef))
)
{
dbg_log(TEXT("MY:DISC HERE\n"));
if (m_StartStream > 0)
{
discont = 1;
}
}
/* If the stream has not started yet, or there is a
* discontinuety then reset the stream time.
*/
if ((m_StartStream == 0) || (discont != 0))
{
sys_time = timeGetTime() - m_ClockStartTime;
m_OtherSide->sys_time = sys_time;
/* For Video, the clockRate is 90Khz */
m_RefGap = (sys_time * (stream.clockRate/1000)) +
(stream.clockRate/2);
/* timeRef is the PTS for the frame from the RTP header */
m_TimeGap = stream.timeRef;
m_StartStream = 1;
difTimeRef = 1;
m_PrevPTS = 0;
m_PrevSysTime = timeGetTime();
dbg_log(
TEXT("MY:StartStream %lld: %lld: %lld\n"),
sys_time,
m_RefGap,
m_TimeGap
);
}
else
{
m_StartStream++;
}
difTimeRef = stream.timeRef - m_PrevTimeRef;
m_PrevTimeRef = stream.timeRef;
/* Difference in 90 Khz clocking */
ts = stream.timeRef - m_TimeGap + m_RefGap;
ts = convert_to_dshow_timestamp(ts, stream.clockRate);
if (discont != 0)
{
dbg_log(TEXT("MY:VDISC TRUE\n"));
pSamp->SetDiscontinuity(TRUE);
}
else
{
pSamp->SetDiscontinuity(FALSE);
pSamp->SetSyncPoint(TRUE);
}
difPts = ts - m_PrevPTS;
df = ts + 1;
m_PrevPTS = ts;
dbg_log(
TEXT("MY:T %lld: %lld = %lld: %d: %lld\n"),
ts,
m_OtherSide->m_PrevPTS,
stream.timeRef,
(timeGetTime() - m_PrevSysTime),
difPts
);
pSamp->SetTime(&ts, &df);
m_PrevSysTime = timeGetTime();
}
else
{
Sleep(10);
}
}
else
{
dbg_log(TEXT("MY: Fill FAIL\n"));
hr = E_FAIL;
}
}
else if (m_iPinType == 2)
{
/* Pin Type 2 is audio AAC Access units, with ADTS headers */
retVal = DeviceIoControl(
ghMHTune,
IOCTL_MHTUNE_RAUDIO_STREAM,
NULL,
0,
&stream,
sizeof(pipeStream),
&returnBytes,
NULL
);
if (retVal == TRUE)
{
/* Get the data */
/* Check for the first of the stream, if so, set the start time */
hr = S_OK;
if (returnBytes > 0)
{
discont = stream.discont;
if ((m_StartStream == 0) || (discont != 0))
{
sys_time = timeGetTime() - m_ClockStartTime;
m_RefGap = (sys_time * (stream.clockRate/1000)) +
(stream.clockRate/2);
/* Mark the first PTS from stream. This PTS is from the
* RTP header, and is usually clocked differently than the
* video clock.
*/
m_TimeGap = stream.timeRef;
m_StartStream = 1;
difTimeRef = 1;
m_PrevPTS = 0;
m_PrevSysTime = timeGetTime();
dbg_log(
TEXT("MY:AStartStream %lld: %lld: %lld\n"),
sys_time,
m_RefGap,
m_TimeGap
);
}
/* Let the video side stream in first before letting audio
* start to flow.
*/
if (m_OtherSide->m_StartStream < 32)
{
pSamp->SetActualDataLength(0);
Sleep(10);
return hr;
}
else
{
pSamp->SetActualDataLength(returnBytes);
}
difTimeRef = stream.timeRef - m_PrevTimeRef;
m_PrevTimeRef = stream.timeRef;
if (discont != 0)
{
dbg_log(TEXT("MY:ADISC TRUE\n"));
pSamp->SetDiscontinuity(TRUE);
}
else
{
pSamp->SetDiscontinuity(FALSE);
pSamp->SetSyncPoint(TRUE);
}
/* Difference in Audio PTS clock, TESTING AT 55.2 Khz */
ts = stream.timeRef - m_TimeGap + m_RefGap;
ts = convert_to_dshow_timestamp(ts, stream.clockRate);
difPts = ts - m_PrevPTS;
df = ts + 1;
m_PrevPTS = ts;
dbg_log(
TEXT("MY:AT %lld = %lld: %d: %lld\n"),
ts,
stream.timeRef,
(timeGetTime() - m_PrevSysTime),
difPts
);
pSamp->SetTime(&ts, &df);
m_PrevSysTime = timeGetTime();
}
else
{
pSamp->SetActualDataLength(0);
Sleep(10);
}
}
}
return hr;
}代碼 /* * /結束
我試圖調整視頻PTS，通過簡單地增加（90000×10），以查看該視頻將大大先於音頻，但它沒有。視頻仍會在2秒或更長時間內播放音頻。我真的不明白爲什麼這不起作用。每個視頻幀應該提前10秒。這不正確嗎？
他們的主要問題是，基本上，算法的聲音？他們似乎可以獨立運行視頻/音頻。
源過濾器不是推式過濾器，我不確定這是否會有所作爲。我沒有解碼器與廣播輸入不同步的問題。
非常感謝。
拖尾是否會隨時間發生，還是立即以2-3秒的延遲開始？此外，請將代碼重新格式化爲更具可讀性。 – BeemerGuy 2010-11-21 01:52:37
抱歉，關於代碼格式。我會盡力在下一次做得更好。 – davroslyrad 2010-12-01 14:47:29