我在尝试使用AVFramework框架和AVAsset创建ProRes编码的mov文件时遇到了一些问题。
在OSX 10.10.5上，使用XCode 7，链接10.9个库。 到目前为止，我已设法创建包含视频和多个音频通道的有效ProRes文件。
（我创建了多个未压缩的48K，16位PCM音频轨道）
添加视频帧效果很好，添加音频帧效果很好，或至少在代码中成功。
然而，当我回放文件时，看起来好像音频帧在12,13,14或15帧序列中重复。
查看波形，从* .mov可以很容易地看到重复的音频......
也就是说，前13或X视频帧都包含完全相同的音频，然后再次为下一个X重复，然后一次又一次地重复等等......
视频很好，只是音频似乎在循环/重复。
无论我使用多少音频通道/音轨作为音源，我都会出现问题，我只使用了1首音轨进行了测试，并且还使用了4首和8首音轨。
它与我提供给系统的样本的格式和数量无关，即使用720p60,1080p23和1080i59都表现出相同的不正确行为。
但我肯定会向Audio encode / SampleBuffer创建过程提交不同的音频数据，因为我已经非常详细地记录了这一点（因为它未在下面的代码中显示）
我尝试了很多不同的东西来修改代码并揭露问题，但没有成功，因此我在这里问，并希望有人可以看到我的代码的问题或给我一些关于这个问题。
我使用的代码如下：
int main(int argc, const char * argv[])
{
@autoreleasepool
{
NSLog(@"Hello, World! - Welcome to the ProResCapture With Audio sample app. ");
OSStatus status;
AudioStreamBasicDescription audioFormat;
CMAudioFormatDescriptionRef audioFormatDesc;
// OK so lets include the hardware stuff first and then we can see about doing some actual capture and compress stuff
HARDWARE_HANDLE pHardware = sdiFactory();
if (pHardware)
{
unsigned long ulUpdateType = UPD_FMT_FRAME;
unsigned long ulFieldCount = 0;
unsigned int numAudioChannels = 4; //8; //4;
int numFramesToCapture = 300;
gBFHancBuffer = (unsigned int*)myAlloc(gHANC_SIZE);
int audioSize = 2002 * 4 * 16;
short* pAudioSamples = (short*)new char[audioSize];
std::vector<short*> vecOfNonInterleavedAudioSamplesPtrs;
for (int i = 0; i < 16; i++)
{
vecOfNonInterleavedAudioSamplesPtrs.push_back((short*)myAlloc(2002 * sizeof(short)));
}
bool bVideoModeIsValid = SetupAndConfigureHardwareToCaptureIncomingVideo();
if (bVideoModeIsValid)
{
gBFBytes = (BLUE_UINT32*)myAlloc(gGoldenSize);
bool canAddVideoWriter = false;
bool canAddAudioWriter = false;
int nAudioSamplesWritten = 0;
// declare the vars for our various AVAsset elements
AVAssetWriter* assetWriter = nil;
AVAssetWriterInput* assetWriterInputVideo = nil;
AVAssetWriterInput* assetWriterAudioInput[16];
AVAssetWriterInputPixelBufferAdaptor* adaptor = nil;
NSURL* localOutputURL = nil;
NSError* localError = nil;
// create the file we are goijmng to be writing to
localOutputURL = [NSURL URLWithString:@"file:///Volumes/Media/ProResAVCaptureAnyFormat.mov"];
assetWriter = [[AVAssetWriter alloc] initWithURL: localOutputURL fileType:AVFileTypeQuickTimeMovie error:&localError];
if (assetWriter)
{
assetWriter.shouldOptimizeForNetworkUse = NO;
// Lets configure the Audio and Video settings for this writer...
{
// Video First.
// Add a video input
// create a dictionary with the settings we want ie. Prores capture and width and height.
NSMutableDictionary* videoSettings = [NSMutableDictionary dictionaryWithObjectsAndKeys:
AVVideoCodecAppleProRes422, AVVideoCodecKey,
[NSNumber numberWithInt:width], AVVideoWidthKey,
[NSNumber numberWithInt:height], AVVideoHeightKey,
nil];
assetWriterInputVideo = [AVAssetWriterInput assetWriterInputWithMediaType: AVMediaTypeVideo outputSettings:videoSettings];
adaptor = [AVAssetWriterInputPixelBufferAdaptor assetWriterInputPixelBufferAdaptorWithAssetWriterInput:assetWriterInputVideo
sourcePixelBufferAttributes:nil];
canAddVideoWriter = [assetWriter canAddInput:assetWriterInputVideo];
}
{ // Add a Audio AssetWriterInput
// Create a dictionary with the settings we want ie. Uncompressed PCM audio 16 bit little endian.
NSMutableDictionary* audioSettings = [NSMutableDictionary dictionaryWithObjectsAndKeys:
[NSNumber numberWithInt:kAudioFormatLinearPCM], AVFormatIDKey,
[NSNumber numberWithFloat:48000.0], AVSampleRateKey,
[NSNumber numberWithInt:16], AVLinearPCMBitDepthKey,
[NSNumber numberWithBool:NO], AVLinearPCMIsNonInterleaved,
[NSNumber numberWithBool:NO], AVLinearPCMIsFloatKey,
[NSNumber numberWithBool:NO], AVLinearPCMIsBigEndianKey,
[NSNumber numberWithUnsignedInteger:1], AVNumberOfChannelsKey,
nil];
// OR use... FillOutASBDForLPCM(AudioStreamBasicDescription& outASBD, Float64 inSampleRate, UInt32 inChannelsPerFrame, UInt32 inValidBitsPerChannel, UInt32 inTotalBitsPerChannel, bool inIsFloat, bool inIsBigEndian, bool inIsNonInterleaved = false)
UInt32 inValidBitsPerChannel = 16;
UInt32 inTotalBitsPerChannel = 16;
bool inIsFloat = false;
bool inIsBigEndian = false;
UInt32 inChannelsPerTrack = 1;
FillOutASBDForLPCM(audioFormat, 48000.00, inChannelsPerTrack, inValidBitsPerChannel, inTotalBitsPerChannel, inIsFloat, inIsBigEndian);
status = CMAudioFormatDescriptionCreate(kCFAllocatorDefault,
&audioFormat,
0,
NULL,
0,
NULL,
NULL,
&audioFormatDesc
);
for (int t = 0; t < numAudioChannels; t++)
{
assetWriterAudioInput[t] = [AVAssetWriterInput assetWriterInputWithMediaType:AVMediaTypeAudio outputSettings:audioSettings];
canAddAudioWriter = [assetWriter canAddInput:assetWriterAudioInput[t] ];
if (canAddAudioWriter)
{
assetWriterAudioInput[t].expectsMediaDataInRealTime = YES; //true;
[assetWriter addInput:assetWriterAudioInput[t] ];
}
}
CMFormatDescriptionRef myFormatDesc = assetWriterAudioInput[0].sourceFormatHint;
NSString* medType = [assetWriterAudioInput[0] mediaType];
}
if(canAddVideoWriter)
{
// tell the asset writer to expect media in real time.
assetWriterInputVideo.expectsMediaDataInRealTime = YES; //true;
// add the Input(s)
[assetWriter addInput:assetWriterInputVideo];
// Start writing the frames..
BOOL success = true;
success = [assetWriter startWriting];
CMTime startTime = CMTimeMake(0, fpsRate);
[assetWriter startSessionAtSourceTime:kCMTimeZero];
// [assetWriter startSessionAtSourceTime:startTime];
if (success)
{
startOurVideoCaptureProcess();
// **** possible enhancement is to use a pixelBufferPool to manage multiple buffers at once...
CVPixelBufferRef buffer = NULL;
int kRecordingFPS = fpsRate;
bool frameAdded = false;
unsigned int bufferID;
for( int i = 0; i < numFramesToCapture; i++)
{
printf("\n");
buffer = pixelBufferFromCard(bufferID, width, height, memFmt); // This function to get a CVBufferREf From our device, as well as getting the Audio data
while(!adaptor.assetWriterInput.readyForMoreMediaData)
{
printf(" readyForMoreMediaData FAILED \n");
}
if (buffer)
{
// Add video
printf("appending Frame %d ", i);
CMTime frameTime = CMTimeMake(i, kRecordingFPS);
frameAdded = [adaptor appendPixelBuffer:buffer withPresentationTime:frameTime];
if (frameAdded)
printf("VideoAdded.....\n ");
// Add Audio
{
// Do some Processing on the captured data to extract the interleaved Audio Samples for each channel
struct hanc_decode_struct decode;
DecodeHancFrameEx(gBFHancBuffer, decode);
int nAudioSamplesCaptured = 0;
if(decode.no_audio_samples > 0)
{
printf("completed deCodeHancEX, found %d samples \n", ( decode.no_audio_samples / numAudioChannels) );
nAudioSamplesCaptured = decode.no_audio_samples / numAudioChannels;
}
CMTime audioTimeStamp = CMTimeMake(nAudioSamplesWritten, 480000); // (Samples Written) / sampleRate for audio
// This function repacks the Audio from interleaved PCM data a vector of individual array of Audio data
RepackDecodedHancAudio((void*)pAudioSamples, numAudioChannels, nAudioSamplesCaptured, vecOfNonInterleavedAudioSamplesPtrs);
for (int t = 0; t < numAudioChannels; t++)
{
CMBlockBufferRef blockBuf = NULL; // *********** MUST release these AFTER adding the samples to the assetWriter...
CMSampleBufferRef cmBuf = NULL;
int sizeOfSamplesInBytes = nAudioSamplesCaptured * 2; // always 16bit memory samples...
// Create sample Block buffer for adding to the audio input.
status = CMBlockBufferCreateWithMemoryBlock(kCFAllocatorDefault,
(void*)vecOfNonInterleavedAudioSamplesPtrs[t],
sizeOfSamplesInBytes,
kCFAllocatorNull,
NULL,
0,
sizeOfSamplesInBytes,
0,
&blockBuf);
if (status != noErr)
NSLog(@"CMBlockBufferCreateWithMemoryBlock error");
status = CMAudioSampleBufferCreateWithPacketDescriptions(kCFAllocatorDefault,
blockBuf,
TRUE,
0,
NULL,
audioFormatDesc,
nAudioSamplesCaptured,
audioTimeStamp,
NULL,
&cmBuf);
if (status != noErr)
NSLog(@"CMSampleBufferCreate error");
// leys check if the CMSampleBuf is valid
bool bValid = CMSampleBufferIsValid(cmBuf);
// examine this values for debugging info....
CMTime cmTimeSampleDuration = CMSampleBufferGetDuration(cmBuf);
CMTime cmTimePresentationTime = CMSampleBufferGetPresentationTimeStamp(cmBuf);
if (status != noErr)
NSLog(@"Invalid Buffer found!!! possible CMSampleBufferCreate error?");
if(!assetWriterAudioInput[t].readyForMoreMediaData)
printf(" readyForMoreMediaData FAILED - Had to Drop a frame\n");
else
{
if(assetWriter.status == AVAssetWriterStatusWriting)
{
BOOL r = YES;
r = [assetWriterAudioInput[t] appendSampleBuffer:cmBuf];
if (!r)
{
NSLog(@"appendSampleBuffer error");
}
else
success = true;
}
else
printf("AssetWriter Not ready???!? \n");
}
if (cmBuf)
{
CFRelease(cmBuf);
cmBuf = 0;
}
if(blockBuf)
{
CFRelease(blockBuf);
blockBuf = 0;
}
}
nAudioSamplesWritten = nAudioSamplesWritten + nAudioSamplesCaptured;
}
if(success)
{
printf("Audio tracks Added..");
}
else
{
NSError* nsERR = [assetWriter error];
printf("Problem Adding Audio tracks / samples");
}
printf("Success \n");
}
if (buffer)
{
CVBufferRelease(buffer);
}
}
}
AVAssetWriterStatus sta = [assetWriter status];
CMTime endTime = CMTimeMake((numFramesToCapture-1), fpsRate);
if (audioFormatDesc)
{
CFRelease(audioFormatDesc);
audioFormatDesc = 0;
}
// Finish the session
StopVideoCaptureProcess();
[assetWriterInputVideo markAsFinished];
for (int t = 0; t < numAudioChannels; t++)
{
[assetWriterAudioInput[t] markAsFinished];
}
[assetWriter endSessionAtSourceTime:endTime];
bool finishedSuccessfully = [assetWriter finishWriting];
if (finishedSuccessfully)
NSLog(@"Writing file ended successfully \n");
else
{
NSLog(@"Writing file ended WITH ERRORS...");
sta = [assetWriter status];
if (sta != AVAssetWriterStatusCompleted)
{
NSError* nsERR = [assetWriter error];
printf("investoigating the error \n");
}
}
}
else
{
NSLog(@"Unable to Add the InputVideo Asset Writer to the AssetWriter, file will not be written - Exiting");
}
if (audioFormatDesc)
CFRelease(audioFormatDesc);
}
for (int i = 0; i < 16; i++)
{
if (vecOfNonInterleavedAudioSamplesPtrs[i])
{
bfFree(2002 * sizeof(unsigned short), vecOfNonInterleavedAudioSamplesPtrs[i]);
vecOfNonInterleavedAudioSamplesPtrs[i] = nullptr;
}
}
}
else
{
NSLog(@"Unable to find a valid input signal - Exiting");
}
if (pAudioSamples)
delete pAudioSamples;
}
}
return 0;
}
这是一个连接到某些特殊硬件的非常基本的示例（代码是遗漏的）
它抓取视频和音频帧，然后有音频处理从交错PCM到每个轨道的PCM数据的单个阵列
然后将每个缓冲区添加到适当的轨道，无论是视频还是音频......
最后，AvAsset内容已完成并关闭，我退出并清理。
非常感谢任何帮助，
干杯，
詹姆斯
答案 0 :(得分：0)
我终于找到了解决这个问题的有效方案。
解决方案分为两部分：
我从使用CMAudioSampleBufferCreateWithPacketDescriptions开始 使用CMSampleBufferCreate（..）以及该函数调用的相应参数。
最初在使用CMSampleBufferCreate进行体验时，我错误地使用了一些参数，它给了我与我最初概述的相同的结果，但仔细检查了我传递给CMSampleTimingInfo结构的值 - 具体来说持续时间部分，我最终使一切正常工作!!
所以我似乎正在正确地创建CMBlockBufferRef，但是在使用它来创建我传递给AVAssetWriterInput的CMSampleBufRef时我需要更加小心！
希望这有助于其他人，因为这对我来说是一个令人讨厌的问题！