解码h264视频流以获取图像缓冲区

时间:2016-10-22 16:56:44

标签: ios h.264 video-toolbox

我跟着this post解码了我的h264视频流帧。

我的数据框如下:

enter image description here

我的代码:

NSString * const naluTypesStrings[] =
{
    @"0: Unspecified (non-VCL)",
    @"1: Coded slice of a non-IDR picture (VCL)",    // P frame
    @"2: Coded slice data partition A (VCL)",
    @"3: Coded slice data partition B (VCL)",
    @"4: Coded slice data partition C (VCL)",
    @"5: Coded slice of an IDR picture (VCL)",      // I frame
    @"6: Supplemental enhancement information (SEI) (non-VCL)",
    @"7: Sequence parameter set (non-VCL)",         // SPS parameter
    @"8: Picture parameter set (non-VCL)",          // PPS parameter
    @"9: Access unit delimiter (non-VCL)",
    @"10: End of sequence (non-VCL)",
    @"11: End of stream (non-VCL)",
    @"12: Filler data (non-VCL)",
    @"13: Sequence parameter set extension (non-VCL)",
    @"14: Prefix NAL unit (non-VCL)",
    @"15: Subset sequence parameter set (non-VCL)",
    @"16: Reserved (non-VCL)",
    @"17: Reserved (non-VCL)",
    @"18: Reserved (non-VCL)",
    @"19: Coded slice of an auxiliary coded picture without partitioning (non-VCL)",
    @"20: Coded slice extension (non-VCL)",
    @"21: Coded slice extension for depth view components (non-VCL)",
    @"22: Reserved (non-VCL)",
    @"23: Reserved (non-VCL)",
    @"24: STAP-A Single-time aggregation packet (non-VCL)",
    @"25: STAP-B Single-time aggregation packet (non-VCL)",
    @"26: MTAP16 Multi-time aggregation packet (non-VCL)",
    @"27: MTAP24 Multi-time aggregation packet (non-VCL)",
    @"28: FU-A Fragmentation unit (non-VCL)",
    @"29: FU-B Fragmentation unit (non-VCL)",
    @"30: Unspecified (non-VCL)",
    @"31: Unspecified (non-VCL)",
};


-(void) receivedRawVideoFrame:(uint8_t *)frame withSize:(uint32_t)frameSize isIFrame:(int)isIFrame
{
    // First NAUL is AUD so i skiped 6 frame
    frame = &frame[6];
    frameSize -= 6;
    OSStatus status;

    uint8_t *data = NULL;
    uint8_t *pps = NULL;
    uint8_t *sps = NULL;

    // I know what my H.264 data source's NALUs look like so I know start code index is always 0.
    // if you don't know where it starts, you can use a for loop similar to how i find the 2nd and 3rd start codes
    int startCodeIndex = 0;
    int secondStartCodeIndex = 0;
    int thirdStartCodeIndex = 0;
    int fourthStartCodeIndex = 0;
    long blockLength = 0;

    CMSampleBufferRef sampleBuffer = NULL;
    CMBlockBufferRef blockBuffer = NULL;

    int nalu_type = (frame[startCodeIndex + 4] & 0x1F);
    NSLog(@"~~~~~~~ Received NALU Type \"%@\" ~~~~~~~~", naluTypesStrings[nalu_type]);

    // if we havent already set up our format description with our SPS PPS parameters, we
    // can't process any frames except type 7 that has our parameters
    if (nalu_type != 7 && _formatDesc == NULL)
    {
        NSLog(@"Video error: Frame is not an I Frame and format description is null");
        return;
    }

    // NALU type 7 is the SPS parameter NALU
    if (nalu_type == 7)
    {
        // find where the second PPS start code begins, (the 0x00 00 00 01 code)
        // from which we also get the length of the first SPS code
        for (int i = startCodeIndex + 4; i < frameSize; i++)
        {
            if (frame[i] == 0x00 && frame[i+1] == 0x00 && frame[i+2] == 0x00 && frame[i+3] == 0x01)
            {
                secondStartCodeIndex = i;
                _spsSize = secondStartCodeIndex;   // includes the header in the size
                break;
            }
        }

        // find what the second NALU type is
        nalu_type = (frame[secondStartCodeIndex + 4] & 0x1F);
        NSLog(@"~~~~~~~ Received NALU Type \"%@\" ~~~~~~~~", naluTypesStrings[nalu_type]);
    }

    // type 8 is the PPS parameter NALU
    if(nalu_type == 8)
    {
        // find where the NALU after this one starts so we know how long the PPS parameter is
        for (int i = secondStartCodeIndex + 4; i < frameSize; i++)
        {
            if (frame[i] == 0x00 && frame[i+1] == 0x00 && frame[i+2] == 0x01)
            {
                thirdStartCodeIndex = i;
                _ppsSize = thirdStartCodeIndex - _spsSize;
                break;
            }
        }
//        _ppsSize = frameSize - -_spsSize;

        // allocate enough data to fit the SPS and PPS parameters into our data objects.
        // VTD doesn't want you to include the start code header (4 bytes long) so we add the - 4 here
        sps =  malloc(_spsSize - 4);
        pps = malloc(_ppsSize - 4);

        // copy in the actual sps and pps values, again ignoring the 4 byte header
        memcpy (sps, &frame[4], _spsSize-4);
        memcpy (pps, &frame[_spsSize+4], _ppsSize-4);

        // now we set our H264 parameters
        uint8_t*  parameterSetPointers[2] = {sps, pps};
        size_t parameterSetSizes[2] = {(_spsSize-4), (_ppsSize-4)};

        status = CMVideoFormatDescriptionCreateFromH264ParameterSets(kCFAllocatorDefault, 2,
                                                                     (const uint8_t *const*)parameterSetPointers,
                                                                     parameterSetSizes, 4,
                                                                     &_formatDesc);

        NSLog(@"\t\t Creation of CMVideoFormatDescription: %@", (status == noErr) ? @"successful!" : @"failed...");
        if(status != noErr) NSLog(@"\t\t Format Description ERROR type: %d", (int)status);

        // See if decomp session can convert from previous format description
        // to the new one, if not we need to remake the decomp session.
        // This snippet was not necessary for my applications but it could be for yours
//        BOOL needNewDecompSession = (VTDecompressionSessionCanAcceptFormatDescription(_decompressionSession, _formatDesc) == NO);
//        if(needNewDecompSession)
//        {
//            [self createDecompSession];
//        }

        // now lets handle the IDR frame that (should) come after the parameter sets
        // I say "should" because that's how I expect my H264 stream to work, YMMV
        nalu_type = (frame[thirdStartCodeIndex + 3] & 0x1F);
        NSLog(@"~~~~~~~ Received NALU Type \"%@\" ~~~~~~~~", naluTypesStrings[nalu_type]);
    }

    // create our VTDecompressionSession.  This isnt neccessary if you choose to use AVSampleBufferDisplayLayer
    if((status == noErr) && (_decompressionSession == NULL))
    {
        [self createDecompSession];
    }

    if(nalu_type == 6)
    {
        for (int i = thirdStartCodeIndex + 3; i < frameSize; i++)
        {
            if (frame[i] == 0x00 && frame[i+1] == 0x00 && frame[i+2] == 0x01)
            {
                fourthStartCodeIndex = i;
                _seiSize = fourthStartCodeIndex - (_spsSize + _ppsSize);
                break;
            }
        }

        // do stuff here
        // [...]
        nalu_type = (frame[fourthStartCodeIndex + 3] & 0x1F);
    }

    // type 5 is an IDR frame NALU.  The SPS and PPS NALUs should always be followed by an IDR (or IFrame) NALU, as far as I know
    if(nalu_type == 5)
    {
        // find the offset, or where the SPS and PPS NALUs end and the IDR frame NALU begins
        int offset = fourthStartCodeIndex;
        int fifthStartCodeIndex = 0;

        for (int i = fourthStartCodeIndex + 3; i < frameSize; i++)
        {
            if (frame[i] == 0x00 && frame[i+1] == 0x00 && frame[i+2] == 0x01)
            {
                fifthStartCodeIndex = i;
                break;
            }
        }


        blockLength = fifthStartCodeIndex - offset;
        data = malloc(blockLength);
        data = memcpy(data, &frame[offset], blockLength);

        // replace the start code header on this NALU with its size.
        // AVCC format requires that you do this.
        // htonl converts the unsigned int from host to network byte order
        uint32_t dataLength32 = htonl (blockLength - 3);
        memcpy (data, &dataLength32, sizeof (uint32_t));

        // create a block buffer from the IDR NALU
        status = CMBlockBufferCreateWithMemoryBlock(NULL, data,  // memoryBlock to hold buffered data
                                                    blockLength,  // block length of the mem block in bytes.
                                                    kCFAllocatorNull, NULL,
                                                    0, // offsetToData
                                                    blockLength,   // dataLength of relevant bytes, starting at offsetToData
                                                    0, &blockBuffer);

        NSLog(@"\t\t BlockBufferCreation: \t %@", (status == kCMBlockBufferNoErr) ? @"successful!" : @"failed...");


        blockLength = frameSize - fifthStartCodeIndex;
        data = malloc(blockLength);
        data = memcpy(data, &frame[offset], blockLength);
        // replace the start code header on this NALU with its size.
        // AVCC format requires that you do this.
        // htonl converts the unsigned int from host to network byte order
        uint32_t dataLength32_1 = htonl (blockLength - 3);
        memcpy (data, &dataLength32_1, sizeof (uint32_t));

        status = CMBlockBufferAppendMemoryBlock(blockBuffer,
                                       data,
                                       blockLength,
                                       kCFAllocatorNull,
                                       NULL,
                                       0,
                                       blockLength,
                                       0);
        NSLog(@"\t\t BlockBufferAppend: \t %@", (status == kCMBlockBufferNoErr) ? @"successful!" : @"failed...");

    }

    // NALU type 1 is non-IDR (or PFrame) picture
    if (nalu_type == 1)
    {
        // non-IDR frames do not have an offset due to SPS and PSS, so the approach
        // is similar to the IDR frames just without the offset
        blockLength = frameSize;
        data = malloc(blockLength);
        data = memcpy(data, &frame[0], blockLength);

        // again, replace the start header with the size of the NALU
        uint32_t dataLength32 = htonl (blockLength - 4);
        memcpy (data, &dataLength32, sizeof (uint32_t));

        status = CMBlockBufferCreateWithMemoryBlock(NULL, data,  // memoryBlock to hold data. If NULL, block will be alloc when needed
                                                    blockLength,  // overall length of the mem block in bytes
                                                    kCFAllocatorNull, NULL,
                                                    0,     // offsetToData
                                                    blockLength,  // dataLength of relevant data bytes, starting at offsetToData
                                                    0, &blockBuffer);

        NSLog(@"\t\t BlockBufferCreation: \t %@", (status == kCMBlockBufferNoErr) ? @"successful!" : @"failed...");
    }

    // now create our sample buffer from the block buffer,
    if(status == noErr)
    {
        // here I'm not bothering with any timing specifics since in my case we displayed all frames immediately
        const size_t sampleSize = blockLength;
        sampleBuffer = NULL;
        status = CMSampleBufferCreate(kCFAllocatorDefault,
                                      blockBuffer, true, NULL, NULL,
                                      _formatDesc, 1, 0, NULL, 1,
                                      &sampleSize, &sampleBuffer);

        NSLog(@"\t\t SampleBufferCreate: \t %@", (status == noErr) ? @"successful!" : @"failed...");
    }

    if(status == noErr)
    {
        // set some values of the sample buffer's attachments
        CFArrayRef attachments = CMSampleBufferGetSampleAttachmentsArray(sampleBuffer, YES);
        CFMutableDictionaryRef dict = (CFMutableDictionaryRef)CFArrayGetValueAtIndex(attachments, 0);
        CFDictionarySetValue(dict, kCMSampleAttachmentKey_DisplayImmediately, kCFBooleanTrue);

        // either send the samplebuffer to a VTDecompressionSession or to an AVSampleBufferDisplayLayer
        [self render:sampleBuffer];
    }

    // free memory to avoid a memory leak, do the same for sps, pps and blockbuffer
    if (NULL != data)
    {
        free (data);
        data = NULL;
    }
}

-(void) createDecompSession
{
    // make sure to destroy the old VTD session
    _decompressionSession = NULL;
    VTDecompressionOutputCallbackRecord callBackRecord;
    callBackRecord.decompressionOutputCallback = decompressionSessionDecodeFrameCallback;

    // this is necessary if you need to make calls to Objective C "self" from within in the callback method.
    callBackRecord.decompressionOutputRefCon = (__bridge void *)self;

    // you can set some desired attributes for the destination pixel buffer.  I didn't use this but you may
    // if you need to set some attributes, be sure to uncomment the dictionary in VTDecompressionSessionCreate
    NSDictionary *destinationImageBufferAttributes = [NSDictionary dictionaryWithObjectsAndKeys:
                                                      [NSNumber numberWithBool:YES],
                                                      (id)kCVPixelBufferOpenGLESCompatibilityKey,
                                                      nil];

    OSStatus status =  VTDecompressionSessionCreate(NULL, _formatDesc, NULL,
                                                     (__bridge CFDictionaryRef)(destinationImageBufferAttributes),
                                                    &callBackRecord, &_decompressionSession);
    NSLog(@"Video Decompression Session Create: \t %@", (status == noErr) ? @"successful!" : @"failed...");
    if(status != noErr) NSLog(@"\t\t VTD ERROR type: %d", (int)status);
}

void decompressionSessionDecodeFrameCallback(void *decompressionOutputRefCon,
                                             void *sourceFrameRefCon,
                                             OSStatus status,
                                             VTDecodeInfoFlags infoFlags,
                                             CVImageBufferRef imageBuffer,
                                             CMTime presentationTimeStamp,
                                             CMTime presentationDuration)
{
    //    THISCLASSNAME *streamManager = (__bridge THISCLASSNAME *)decompressionOutputRefCon;

    if (status != noErr)
    {
        NSError *error = [NSError errorWithDomain:NSOSStatusErrorDomain code:status userInfo:nil];
        NSLog(@"Decompressed error: %@", error);
    }
    else
    {
        NSLog(@"Decompressed sucessfully");

        // do something with your resulting CVImageBufferRef that is your decompressed frame
        //        [streamManager displayDecodedFrame:imageBuffer];
    }
}

- (void) render:(CMSampleBufferRef)sampleBuffer
{
    VTDecodeFrameFlags flags = kVTDecodeFrame_1xRealTimePlayback;
    VTDecodeInfoFlags flagOut;
    NSDate* currentTime = [NSDate date];
    VTDecompressionSessionDecodeFrame(_decompressionSession, sampleBuffer, flags,
                                      (void*)CFBridgingRetain(currentTime), &flagOut);

    CFRelease(sampleBuffer);

    // if you're using AVSampleBufferDisplayLayer, you only need to use this line of code
    // [videoLayer enqueueSampleBuffer:sampleBuffer];
}


@end

输出:

[2110:825268] ~~~~~~~ Received NALU Type "7: Sequence parameter set (non-VCL)" ~~~~~~~~

[2110:825268] ~~~~~~~ Received NALU Type "8: Picture parameter set (non-VCL)" ~~~~~~~~

[2110:825268]   Creation of CMVideoFormatDescription: successful!

[2110:825268] ~~~~~~~ Received NALU Type "6: Supplemental enhancement information (SEI) (non-VCL)" ~~~~~~~~

[2110:825268]   BlockBufferCreation:    successful!

[2110:825268]   BlockBufferAppend:  successful!

[2110:825268]   SampleBufferCreate:     successful!

[2110:825277] Decompressed error: Error Domain=NSOSStatusErrorDomain Code=-12909 "(null)"

请指出我错过了什么。

0 个答案:

没有答案