iOS音视频实时采集硬件编码

版权声明:本文为博主原创文章,未经博主允许不得转载。 https://blog.csdn.net/u011518723/article/details/49248467

iOS音视频实时采集硬件编码(H264+AAC)

做 iOS开发已经好几年了,从来没写博客的习惯,今天就试试写点东西

最近在做音视频方面的东西,发现国内硬编的资料特别少,去网上搜全是软编,于是翻墙,发现外国人就是有分享精神,研究了一个星期终于整理出来一套 iOS 实时硬编码,大概功能实现:

  • 使用 AVCaptureSession进行实时采集音视频
  • 通过AVCaptureVideoDataOutputSampleBufferDelegate获取到音视频buffer数据
  • 分别对音视频原始数据进行编码
  • 传输
//
//  ViewController.h
//  H264AACEncode
//
//  Created by ZhangWen on 15/10/14.
//  Copyright © 2015年 Zhangwen. All rights reserved.
//

#import <UIKit/UIKit.h>
#import <AVFoundation/AVFoundation.h>
#import "AACEncoder.h"
#import "H264Encoder.h"


@interface ViewController : UIViewController <AVCaptureVideoDataOutputSampleBufferDelegate,AVCaptureAudioDataOutputSampleBufferDelegate,H264EncoderDelegate>


@end
//
//  ViewController.m
//  H264AACEncode
//
//  Created by ZhangWen on 15/10/14.
//  Copyright © 2015年 Zhangwen. All rights reserved.
//

#import "ViewController.h"

#define CAPTURE_FRAMES_PER_SECOND       20
#define SAMPLE_RATE                     44100
#define VideoWidth                      480
#define VideoHeight                     640

@interface ViewController ()
{
    UIButton *startBtn;
    bool startCalled;

    H264Encoder *h264Encoder;
    AACEncoder *aacEncoder;

    AVCaptureSession *captureSession;

    dispatch_queue_t _audioQueue;

    AVCaptureConnection* _audioConnection;
    AVCaptureConnection* _videoConnection;


    NSMutableData *_data;
    NSString *h264File;
    NSFileHandle *fileHandle;

}
@end

@implementation ViewController

- (void)viewDidLoad {
    [super viewDidLoad];
    // Do any additional setup after loading the view, typically from a nib.

    startCalled = true;

    _data = [[NSMutableData alloc] init];
    captureSession = [[AVCaptureSession alloc] init];

    [self initStartBtn];

}

#pragma mark
#pragma mark - 设置音频 capture
- (void) setupAudioCapture {
    aacEncoder = [[AACEncoder alloc] init];
    // create capture device with video input

    /*
     * Create audio connection
     */
    AVCaptureDevice *audioDevice = [AVCaptureDevice defaultDeviceWithMediaType:AVMediaTypeAudio];
    NSError *error = nil;
    AVCaptureDeviceInput *audioInput = [[AVCaptureDeviceInput alloc] initWithDevice:audioDevice error:&error];
    if (error) {
        NSLog(@"Error getting audio input device: %@", error.description);
    }
    if ([captureSession canAddInput:audioInput]) {
        [captureSession addInput:audioInput];
    }

    _audioQueue = dispatch_queue_create("Audio Capture Queue", DISPATCH_QUEUE_SERIAL);
    AVCaptureAudioDataOutput* audioOutput = [[AVCaptureAudioDataOutput alloc] init];
    [audioOutput setSampleBufferDelegate:self queue:_audioQueue];
    if ([captureSession canAddOutput:audioOutput]) {
        [captureSession addOutput:audioOutput];
    }
    _audioConnection = [audioOutput connectionWithMediaType:AVMediaTypeAudio];
}

- (AVCaptureDevice *)cameraWithPosition:(AVCaptureDevicePosition)position
{
    NSArray *devices = [AVCaptureDevice devicesWithMediaType:AVMediaTypeVideo];
    for ( AVCaptureDevice *device in devices )
        if ( device.position == position )
            return device;
    return nil;
}

#pragma mark
#pragma mark - 设置视频 capture
- (void) setupVideoCaprure
{
    h264Encoder = [H264Encoder alloc];
    [h264Encoder initWithConfiguration];

    NSError *deviceError;

    AVCaptureDevice *cameraDevice = [AVCaptureDevice defaultDeviceWithMediaType:AVMediaTypeVideo];
//    cameraDevice = [self cameraWithPosition:AVCaptureDevicePositionBack];
//    cameraDevice.position = AVCaptureDevicePositionBack;
    AVCaptureDeviceInput *inputDevice = [AVCaptureDeviceInput deviceInputWithDevice:cameraDevice error:&deviceError];

    // make output device

    AVCaptureVideoDataOutput *outputDevice = [[AVCaptureVideoDataOutput alloc] init];

    NSString* key = (NSString*)kCVPixelBufferPixelFormatTypeKey;

    NSNumber* val = [NSNumber
                     numberWithUnsignedInt:kCVPixelFormatType_420YpCbCr8BiPlanarFullRange];
    NSDictionary* videoSettings =
    [NSDictionary dictionaryWithObject:val forKey:key];

    NSError *error;
    [cameraDevice lockForConfiguration:&error];
    if (error == nil) {

        NSLog(@"cameraDevice.activeFormat.videoSupportedFrameRateRanges IS %@",[cameraDevice.activeFormat.videoSupportedFrameRateRanges objectAtIndex:0]);

        if (cameraDevice.activeFormat.videoSupportedFrameRateRanges){

            [cameraDevice setActiveVideoMinFrameDuration:CMTimeMake(1, CAPTURE_FRAMES_PER_SECOND)];
            [cameraDevice setActiveVideoMaxFrameDuration:CMTimeMake(1, CAPTURE_FRAMES_PER_SECOND)];
        }
    }else{
        // handle error2
    }
    [cameraDevice unlockForConfiguration];


    // Start the session running to start the flow of data

    outputDevice.videoSettings = videoSettings;

    [outputDevice setSampleBufferDelegate:self queue:dispatch_get_main_queue()];

    // initialize capture session

    if ([captureSession canAddInput:inputDevice]) {
        [captureSession addInput:inputDevice];
    }
    if ([captureSession canAddOutput:outputDevice]) {
        [captureSession addOutput:outputDevice];
    }

    // begin configuration for the AVCaptureSession
    [captureSession beginConfiguration];

    // picture resolution
    [captureSession setSessionPreset:[NSString stringWithString:AVCaptureSessionPreset640x480]];

    _videoConnection = [outputDevice connectionWithMediaType:AVMediaTypeVideo];

    //Set landscape (if required)
    if ([_videoConnection isVideoOrientationSupported])
    {
        AVCaptureVideoOrientation orientation = AVCaptureVideoOrientationLandscapeRight;        //<<<<<SET VIDEO ORIENTATION IF LANDSCAPE
        [_videoConnection setVideoOrientation:orientation];
    }


    // make preview layer and add so that camera's view is displayed on screen

    NSFileManager *fileManager = [NSFileManager defaultManager];
    NSArray *paths = NSSearchPathForDirectoriesInDomains(NSDocumentDirectory, NSUserDomainMask, YES);
    NSString *documentsDirectory = [paths objectAtIndex:0];

    h264File = [documentsDirectory stringByAppendingPathComponent:@"test.h264"];
    [fileManager removeItemAtPath:h264File error:nil];
    [fileManager createFileAtPath:h264File contents:nil attributes:nil];

    // Open the file using POSIX as this is anyway a test application
    //fd = open([h264File UTF8String], O_RDWR);
    fileHandle = [NSFileHandle fileHandleForWritingAtPath:h264File];

    [h264Encoder initEncode:VideoWidth height:VideoHeight];
    h264Encoder.delegate = self;

}

#pragma mark
#pragma mark - sampleBuffer 数据
-(void) captureOutput:(AVCaptureOutput*)captureOutput didOutputSampleBuffer:(CMSampleBufferRef)sampleBuffer fromConnection:(AVCaptureConnection*)connection

{
    CMTime pts = CMSampleBufferGetPresentationTimeStamp(sampleBuffer);
    double dPTS = (double)(pts.value) / pts.timescale;

//    NSLog(@"DPTS is %f",dPTS);

    if (connection == _videoConnection) {
        [h264Encoder encode:sampleBuffer];
    } else if (connection == _audioConnection) {

        [aacEncoder encodeSampleBuffer:sampleBuffer completionBlock:^(NSData *encodedData, NSError *error) {
            if (encodedData) {

                NSLog(@"Audio data (%lu): %@", (unsigned long)encodedData.length, encodedData.description);

#pragma mark
#pragma mark -  音频数据(encodedData)
                [_data appendData:encodedData];


            } else {
                NSLog(@"Error encoding AAC: %@", error);
            }
        }];

    }

}

#pragma mark
#pragma mark - 视频 sps 和 pps
- (void)gotSpsPps:(NSData*)sps pps:(NSData*)pps
{

    const char bytes[] = "\x00\x00\x00\x01";
    size_t length = (sizeof bytes) - 1; //string literals have implicit trailing '\0'
    NSData *ByteHeader = [NSData dataWithBytes:bytes length:length];
    [fileHandle writeData:ByteHeader];
    [fileHandle writeData:sps];
    [fileHandle writeData:ByteHeader];
    [fileHandle writeData:pps];

}

#pragma mark
#pragma mark - 视频数据回调
- (void)gotEncodedData:(NSData*)data isKeyFrame:(BOOL)isKeyFrame
{
    NSLog(@"Video data (%lu): %@", (unsigned long)data.length, data.description);

    if (fileHandle != NULL)
    {
        const char bytes[] = "\x00\x00\x00\x01";
        size_t length = (sizeof bytes) - 1; //string literals have implicit trailing '\0'
        NSData *ByteHeader = [NSData dataWithBytes:bytes length:length];

#pragma mark
#pragma mark - 视频数据(data)

        [fileHandle writeData:ByteHeader];
        //[fileHandle writeData:UnitHeader];
        [fileHandle writeData:data];

    }
}

#pragma mark
#pragma mark - 录制
- (void)startBtnClicked
{
    if (startCalled)
    {
        [self startCamera];
        startCalled = false;
        [startBtn setTitle:@"Stop" forState:UIControlStateNormal];

    }
    else
    {
        [startBtn setTitle:@"Start" forState:UIControlStateNormal];
        startCalled = true;
        [self stopCarmera];
    }

}

- (void) startCamera
{
    [self setupAudioCapture];
    [self setupVideoCaprure];
    [captureSession commitConfiguration];
    [captureSession startRunning];
}

- (void) stopCarmera
{
    [h264Encoder End];
    [captureSession stopRunning];
    //close(fd);
    [fileHandle closeFile];
    fileHandle = NULL;

    // 获取程序Documents目录路径
    NSArray *paths = NSSearchPathForDirectoriesInDomains(NSDocumentDirectory,NSUserDomainMask, YES);
    NSString *documentsDirectory = [paths objectAtIndex:0];

    NSMutableString * path = [[NSMutableString alloc]initWithString:documentsDirectory];
    [path appendString:@"/AACFile"];

    [_data writeToFile:path atomically:YES];

}

- (void)initStartBtn
{
    startBtn = [UIButton buttonWithType:UIButtonTypeCustom];
    startBtn.frame = CGRectMake(0, 0, 100, 30);
    startBtn.center = self.view.center;
    [startBtn addTarget:self action:@selector(startBtnClicked) forControlEvents:UIControlEventTouchUpInside];
    [startBtn setTitle:@"Start" forState:UIControlStateNormal];
    [startBtn setTitleColor:[UIColor blackColor] forState:UIControlStateNormal];
    [self.view addSubview:startBtn];
}

- (void)didReceiveMemoryWarning {
    [super didReceiveMemoryWarning];
    // Dispose of any resources that can be recreated.
}

@end
//
//  AACEncoder.h
//  H264AACEncode
//
//  Created by ZhangWen on 15/10/14.
//  Copyright © 2015年 Zhangwen. All rights reserved.
//

#import <Foundation/Foundation.h>
#import <AVFoundation/AVFoundation.h>
#import <AudioToolbox/AudioToolbox.h>

@interface AACEncoder : NSObject

@property (nonatomic) dispatch_queue_t encoderQueue;
@property (nonatomic) dispatch_queue_t callbackQueue;

- (void) encodeSampleBuffer:(CMSampleBufferRef)sampleBuffer completionBlock:(void (^)(NSData *encodedData, NSError* error))completionBlock;


@end
//
//  AACEncoder.m
//  H264AACEncode
//
//  Created by ZhangWen on 15/10/14.
//  Copyright © 2015年 Zhangwen. All rights reserved.
//

#import "AACEncoder.h"

@interface AACEncoder()
@property (nonatomic) AudioConverterRef audioConverter;
@property (nonatomic) uint8_t *aacBuffer;
@property (nonatomic) NSUInteger aacBufferSize;
@property (nonatomic) char *pcmBuffer;
@property (nonatomic) size_t pcmBufferSize;

@end

@implementation AACEncoder

- (void) dealloc {
    AudioConverterDispose(_audioConverter);
    free(_aacBuffer);
}

- (id) init {
    if (self = [super init]) {
        _encoderQueue = dispatch_queue_create("AAC Encoder Queue", DISPATCH_QUEUE_SERIAL);
        _callbackQueue = dispatch_queue_create("AAC Encoder Callback Queue", DISPATCH_QUEUE_SERIAL);
        _audioConverter = NULL;
        _pcmBufferSize = 0;
        _pcmBuffer = NULL;
        _aacBufferSize = 1024;
        _aacBuffer = malloc(_aacBufferSize * sizeof(uint8_t));
        memset(_aacBuffer, 0, _aacBufferSize);
    }
    return self;
}

- (void) setupEncoderFromSampleBuffer:(CMSampleBufferRef)sampleBuffer {
    AudioStreamBasicDescription inAudioStreamBasicDescription = *CMAudioFormatDescriptionGetStreamBasicDescription((CMAudioFormatDescriptionRef)CMSampleBufferGetFormatDescription(sampleBuffer));

    AudioStreamBasicDescription outAudioStreamBasicDescription = {0}; // Always initialize the fields of a new audio stream basic description structure to zero, as shown here: ...
    outAudioStreamBasicDescription.mSampleRate = inAudioStreamBasicDescription.mSampleRate; // The number of frames per second of the data in the stream, when the stream is played at normal speed. For compressed formats, this field indicates the number of frames per second of equivalent decompressed data. The mSampleRate field must be nonzero, except when this structure is used in a listing of supported formats (see “kAudioStreamAnyRate”).
    outAudioStreamBasicDescription.mFormatID = kAudioFormatMPEG4AAC; // kAudioFormatMPEG4AAC_HE does not work. Can't find `AudioClassDescription`. `mFormatFlags` is set to 0.
    outAudioStreamBasicDescription.mFormatFlags = kMPEG4Object_AAC_LC; // Format-specific flags to specify details of the format. Set to 0 to indicate no format flags. See “Audio Data Format Identifiers” for the flags that apply to each format.
    outAudioStreamBasicDescription.mBytesPerPacket = 0; // The number of bytes in a packet of audio data. To indicate variable packet size, set this field to 0. For a format that uses variable packet size, specify the size of each packet using an AudioStreamPacketDescription structure.
    outAudioStreamBasicDescription.mFramesPerPacket = 1024; // The number of frames in a packet of audio data. For uncompressed audio, the value is 1. For variable bit-rate formats, the value is a larger fixed number, such as 1024 for AAC. For formats with a variable number of frames per packet, such as Ogg Vorbis, set this field to 0.
    outAudioStreamBasicDescription.mBytesPerFrame = 0; // The number of bytes from the start of one frame to the start of the next frame in an audio buffer. Set this field to 0 for compressed formats. ...
    outAudioStreamBasicDescription.mChannelsPerFrame = 1; // The number of channels in each frame of audio data. This value must be nonzero.
    outAudioStreamBasicDescription.mBitsPerChannel = 0; // ... Set this field to 0 for compressed formats.
    outAudioStreamBasicDescription.mReserved = 0; // Pads the structure out to force an even 8-byte alignment. Must be set to 0.
    AudioClassDescription *description = [self
                                          getAudioClassDescriptionWithType:kAudioFormatMPEG4AAC
                                          fromManufacturer:kAppleSoftwareAudioCodecManufacturer];

    OSStatus status = AudioConverterNewSpecific(&inAudioStreamBasicDescription, &outAudioStreamBasicDescription, 1, description, &_audioConverter);
    if (status != 0) {
        NSLog(@"setup converter: %d", (int)status);
    }
}

- (AudioClassDescription *)getAudioClassDescriptionWithType:(UInt32)type
                                           fromManufacturer:(UInt32)manufacturer
{
    static AudioClassDescription desc;

    UInt32 encoderSpecifier = type;
    OSStatus st;

    UInt32 size;
    st = AudioFormatGetPropertyInfo(kAudioFormatProperty_Encoders,
                                    sizeof(encoderSpecifier),
                                    &encoderSpecifier,
                                    &size);
    if (st) {
        NSLog(@"error getting audio format propery info: %d", (int)(st));
        return nil;
    }

    unsigned int count = size / sizeof(AudioClassDescription);
    AudioClassDescription descriptions[count];
    st = AudioFormatGetProperty(kAudioFormatProperty_Encoders,
                                sizeof(encoderSpecifier),
                                &encoderSpecifier,
                                &size,
                                descriptions);
    if (st) {
        NSLog(@"error getting audio format propery: %d", (int)(st));
        return nil;
    }

    for (unsigned int i = 0; i < count; i++) {
        if ((type == descriptions[i].mSubType) &&
            (manufacturer == descriptions[i].mManufacturer)) {
            memcpy(&desc, &(descriptions[i]), sizeof(desc));
            return &desc;
        }
    }

    return nil;
}

static OSStatus inInputDataProc(AudioConverterRef inAudioConverter, UInt32 *ioNumberDataPackets, AudioBufferList *ioData, AudioStreamPacketDescription **outDataPacketDescription, void *inUserData)
{
    AACEncoder *encoder = (__bridge AACEncoder *)(inUserData);
    UInt32 requestedPackets = *ioNumberDataPackets;
    //NSLog(@"Number of packets requested: %d", (unsigned int)requestedPackets);
    size_t copiedSamples = [encoder copyPCMSamplesIntoBuffer:ioData];
    if (copiedSamples < requestedPackets) {
        //NSLog(@"PCM buffer isn't full enough!");
        *ioNumberDataPackets = 0;
        return -1;
    }
    *ioNumberDataPackets = 1;
    //NSLog(@"Copied %zu samples into ioData", copiedSamples);
    return noErr;
}

- (size_t) copyPCMSamplesIntoBuffer:(AudioBufferList*)ioData {
    size_t originalBufferSize = _pcmBufferSize;
    if (!originalBufferSize) {
        return 0;
    }
    ioData->mBuffers[0].mData = _pcmBuffer;
    ioData->mBuffers[0].mDataByteSize = _pcmBufferSize;
    _pcmBuffer = NULL;
    _pcmBufferSize = 0;
    return originalBufferSize;
}


- (void) encodeSampleBuffer:(CMSampleBufferRef)sampleBuffer completionBlock:(void (^)(NSData * encodedData, NSError* error))completionBlock {
    CFRetain(sampleBuffer);
    dispatch_async(_encoderQueue, ^{
        if (!_audioConverter) {
            [self setupEncoderFromSampleBuffer:sampleBuffer];
        }
        CMBlockBufferRef blockBuffer = CMSampleBufferGetDataBuffer(sampleBuffer);
        CFRetain(blockBuffer);
        OSStatus status = CMBlockBufferGetDataPointer(blockBuffer, 0, NULL, &_pcmBufferSize, &_pcmBuffer);
        NSError *error = nil;
        if (status != kCMBlockBufferNoErr) {
            error = [NSError errorWithDomain:NSOSStatusErrorDomain code:status userInfo:nil];
        }
        //NSLog(@"PCM Buffer Size: %zu", _pcmBufferSize);

        memset(_aacBuffer, 0, _aacBufferSize);
        AudioBufferList outAudioBufferList = {0};
        outAudioBufferList.mNumberBuffers = 1;
        outAudioBufferList.mBuffers[0].mNumberChannels = 1;
        outAudioBufferList.mBuffers[0].mDataByteSize = _aacBufferSize;
        outAudioBufferList.mBuffers[0].mData = _aacBuffer;
        AudioStreamPacketDescription *outPacketDescription = NULL;
        UInt32 ioOutputDataPacketSize = 1;
        status = AudioConverterFillComplexBuffer(_audioConverter, inInputDataProc, (__bridge void *)(self), &ioOutputDataPacketSize, &outAudioBufferList, outPacketDescription);
        //NSLog(@"ioOutputDataPacketSize: %d", (unsigned int)ioOutputDataPacketSize);
        NSData *data = nil;
        if (status == 0) {
            NSData *rawAAC = [NSData dataWithBytes:outAudioBufferList.mBuffers[0].mData length:outAudioBufferList.mBuffers[0].mDataByteSize];
            NSData *adtsHeader = [self adtsDataForPacketLength:rawAAC.length];
            NSMutableData *fullData = [NSMutableData dataWithData:adtsHeader];
            [fullData appendData:rawAAC];
            data = fullData;
        } else {
            error = [NSError errorWithDomain:NSOSStatusErrorDomain code:status userInfo:nil];
        }
        if (completionBlock) {
            dispatch_async(_callbackQueue, ^{
                completionBlock(data, error);
            });
        }
        CFRelease(sampleBuffer);
        CFRelease(blockBuffer);
    });
}



/**
 *  Add ADTS header at the beginning of each and every AAC packet.
 *  This is needed as MediaCodec encoder generates a packet of raw
 *  AAC data.
 *
 *  Note the packetLen must count in the ADTS header itself.
 *  See: http://wiki.multimedia.cx/index.php?title=ADTS
 *  Also: http://wiki.multimedia.cx/index.php?title=MPEG-4_Audio#Channel_Configurations
 **/
- (NSData*) adtsDataForPacketLength:(NSUInteger)packetLength {
    int adtsLength = 7;
    char *packet = malloc(sizeof(char) * adtsLength);
    // Variables Recycled by addADTStoPacket
    int profile = 2;  //AAC LC
    //39=MediaCodecInfo.CodecProfileLevel.AACObjectELD;
    int freqIdx = 4;  //44.1KHz
    int chanCfg = 1;  //MPEG-4 Audio Channel Configuration. 1 Channel front-center
    NSUInteger fullLength = adtsLength + packetLength;
    // fill in ADTS data
    packet[0] = (char)0xFF; // 11111111     = syncword
    packet[1] = (char)0xF9; // 1111 1 00 1  = syncword MPEG-2 Layer CRC
    packet[2] = (char)(((profile-1)<<6) + (freqIdx<<2) +(chanCfg>>2));
    packet[3] = (char)(((chanCfg&3)<<6) + (fullLength>>11));
    packet[4] = (char)((fullLength&0x7FF) >> 3);
    packet[5] = (char)(((fullLength&7)<<5) + 0x1F);
    packet[6] = (char)0xFC;
    NSData *data = [NSData dataWithBytesNoCopy:packet length:adtsLength freeWhenDone:YES];
    return data;
}


@end
//
//  H264Encoder.h
//  H264AACEncode
//
//  Created by ZhangWen on 15/10/14.
//  Copyright © 2015年 Zhangwen. All rights reserved.
//

#import <Foundation/Foundation.h>
#import <AVFoundation/AVFoundation.h>
#import <VideoToolbox/VideoToolbox.h>

@protocol H264EncoderDelegate <NSObject>

- (void)gotSpsPps:(NSData*)sps pps:(NSData*)pps;
- (void)gotEncodedData:(NSData*)data isKeyFrame:(BOOL)isKeyFrame;

@end
@interface H264Encoder : NSObject

- (void) initWithConfiguration;
- (void) start:(int)width  height:(int)height;
- (void) initEncode:(int)width  height:(int)height;
- (void) encode:(CMSampleBufferRef )sampleBuffer;
- (void) End;


@property (weak, nonatomic) NSString *error;
@property (weak, nonatomic) id<H264EncoderDelegate> delegate;

@end
//
//  H264Encoder.m
//  H264AACEncode
//
//  Created by ZhangWen on 15/10/14.
//  Copyright © 2015年 Zhangwen. All rights reserved.
//

#import "H264Encoder.h"

@implementation H264Encoder

{
    NSString * yuvFile;
    VTCompressionSessionRef EncodingSession;
    dispatch_queue_t aQueue;
    CMFormatDescriptionRef  format;
    CMSampleTimingInfo * timingInfo;
    BOOL initialized;
    int  frameCount;
    NSData *sps;
    NSData *pps;
}
@synthesize error;

- (void) initWithConfiguration
{

    EncodingSession = nil;
    initialized = true;
    aQueue = dispatch_get_global_queue(DISPATCH_QUEUE_PRIORITY_DEFAULT, 0);
    frameCount = 0;
    sps = NULL;
    pps = NULL;

}

void didCompressH264(void *outputCallbackRefCon, void *sourceFrameRefCon, OSStatus status, VTEncodeInfoFlags infoFlags,
                     CMSampleBufferRef sampleBuffer )
{
    //    NSLog(@"didCompressH264 called with status %d infoFlags %d", (int)status, (int)infoFlags);
    if (status != 0) return;

    if (!CMSampleBufferDataIsReady(sampleBuffer))
    {
        NSLog(@"didCompressH264 data is not ready ");
        return;
    }
    H264Encoder* encoder = (__bridge H264Encoder*)outputCallbackRefCon;

    // Check if we have got a key frame first
    bool keyframe = !CFDictionaryContainsKey( (CFArrayGetValueAtIndex(CMSampleBufferGetSampleAttachmentsArray(sampleBuffer, true), 0)), kCMSampleAttachmentKey_NotSync);

    if (keyframe)
    {
        CMFormatDescriptionRef format = CMSampleBufferGetFormatDescription(sampleBuffer);
        // CFDictionaryRef extensionDict = CMFormatDescriptionGetExtensions(format);
        // Get the extensions
        // From the extensions get the dictionary with key "SampleDescriptionExtensionAtoms"
        // From the dict, get the value for the key "avcC"

        size_t sparameterSetSize, sparameterSetCount;
        const uint8_t *sparameterSet;
        OSStatus statusCode = CMVideoFormatDescriptionGetH264ParameterSetAtIndex(format, 0, &sparameterSet, &sparameterSetSize, &sparameterSetCount, 0 );
        if (statusCode == noErr)
        {
            // Found sps and now check for pps
            size_t pparameterSetSize, pparameterSetCount;
            const uint8_t *pparameterSet;
            OSStatus statusCode = CMVideoFormatDescriptionGetH264ParameterSetAtIndex(format, 1, &pparameterSet, &pparameterSetSize, &pparameterSetCount, 0 );
            if (statusCode == noErr)
            {
                // Found pps
                encoder->sps = [NSData dataWithBytes:sparameterSet length:sparameterSetSize];
                encoder->pps = [NSData dataWithBytes:pparameterSet length:pparameterSetSize];
                if (encoder->_delegate)
                {
                    [encoder->_delegate gotSpsPps:encoder->sps pps:encoder->pps];
                }
            }
        }
    }

    CMBlockBufferRef dataBuffer = CMSampleBufferGetDataBuffer(sampleBuffer);
    size_t length, totalLength;
    char *dataPointer;
    OSStatus statusCodeRet = CMBlockBufferGetDataPointer(dataBuffer, 0, &length, &totalLength, &dataPointer);
    if (statusCodeRet == noErr) {

        size_t bufferOffset = 0;
        static const int AVCCHeaderLength = 4;
        while (bufferOffset < totalLength - AVCCHeaderLength) {

            // Read the NAL unit length
            uint32_t NALUnitLength = 0;
            memcpy(&NALUnitLength, dataPointer + bufferOffset, AVCCHeaderLength);

            // Convert the length value from Big-endian to Little-endian
            NALUnitLength = CFSwapInt32BigToHost(NALUnitLength);

            NSData* data = [[NSData alloc] initWithBytes:(dataPointer + bufferOffset + AVCCHeaderLength) length:NALUnitLength];
            [encoder->_delegate gotEncodedData:data isKeyFrame:keyframe];

            // Move to the next NAL unit in the block buffer
            bufferOffset += AVCCHeaderLength + NALUnitLength;
        }

    }

}

- (void) start:(int)width  height:(int)height
{
    int frameSize = (width * height * 1.5);

    if (!initialized)
    {
        NSLog(@"H264: Not initialized");
        error = @"H264: Not initialized";
        return;
    }
    dispatch_sync(aQueue, ^{

        // For testing out the logic, lets read from a file and then send it to encoder to create h264 stream

        // Create the compression session
        OSStatus status = VTCompressionSessionCreate(NULL, width, height, kCMVideoCodecType_H264, NULL, NULL, NULL, didCompressH264, (__bridge void *)(self),  &EncodingSession);
        NSLog(@"H264: VTCompressionSessionCreate %d", (int)status);

        if (status != 0)
        {
            NSLog(@"H264: Unable to create a H264 session");
            error = @"H264: Unable to create a H264 session";

            return ;

        }

        // Set the properties
        VTSessionSetProperty(EncodingSession, kVTCompressionPropertyKey_RealTime, kCFBooleanTrue);
        VTSessionSetProperty(EncodingSession, kVTCompressionPropertyKey_AllowFrameReordering, kCFBooleanFalse);
        VTSessionSetProperty(EncodingSession, kVTCompressionPropertyKey_MaxKeyFrameInterval, 240);

        VTSessionSetProperty(EncodingSession, kVTCompressionPropertyKey_ProfileLevel, kVTProfileLevel_H264_High_AutoLevel);


        // Tell the encoder to start encoding
        VTCompressionSessionPrepareToEncodeFrames(EncodingSession);

        // Start reading from the file and copy it to the buffer

        // Open the file using POSIX as this is anyway a test application
        int fd = open([yuvFile UTF8String], O_RDONLY);
        if (fd == -1)
        {
            NSLog(@"H264: Unable to open the file");
            error = @"H264: Unable to open the file";

            return ;
        }

        NSMutableData* theData = [[NSMutableData alloc] initWithLength:frameSize] ;
        NSUInteger actualBytes = frameSize;
        while (actualBytes > 0)
        {
            void* buffer = [theData mutableBytes];
            NSUInteger bufferSize = [theData length];

            actualBytes = read(fd, buffer, bufferSize);
            if (actualBytes < frameSize)
                [theData setLength:actualBytes];

            frameCount++;
            // Create a CM Block buffer out of this data
            CMBlockBufferRef BlockBuffer = NULL;
            OSStatus status = CMBlockBufferCreateWithMemoryBlock(NULL, buffer, actualBytes,kCFAllocatorNull, NULL, 0, actualBytes, kCMBlockBufferAlwaysCopyDataFlag, &BlockBuffer);

            // Check for error
            if (status != noErr)
            {
                NSLog(@"H264: CMBlockBufferCreateWithMemoryBlock failed with %d", (int)status);
                error = @"H264: CMBlockBufferCreateWithMemoryBlock failed ";

                return ;
            }

            // Create a CM Sample Buffer
            CMSampleBufferRef sampleBuffer = NULL;
            CMFormatDescriptionRef formatDescription;
            CMFormatDescriptionCreate ( kCFAllocatorDefault, // Allocator
                                       kCMMediaType_Video,
                                       'I420',
                                       NULL,
                                       &formatDescription );
            CMSampleTimingInfo sampleTimingInfo = {CMTimeMake(1, 300)};

            OSStatus statusCode = CMSampleBufferCreate(kCFAllocatorDefault, BlockBuffer, YES, NULL, NULL, formatDescription, 1, 1, &sampleTimingInfo, 0, NULL, &sampleBuffer);

            // Check for error
            if (statusCode != noErr) {
                NSLog(@"H264: CMSampleBufferCreate failed with %d", (int)statusCode);
                error = @"H264: CMSampleBufferCreate failed ";

                return;
            }
            CFRelease(BlockBuffer);
            BlockBuffer = NULL;

            // Get the CV Image buffer
            CVImageBufferRef imageBuffer = (CVImageBufferRef)CMSampleBufferGetImageBuffer(sampleBuffer);

            // Create properties
            CMTime presentationTimeStamp = CMTimeMake(frameCount, 300);
            //CMTime duration = CMTimeMake(1, DURATION);
            VTEncodeInfoFlags flags;

            // Pass it to the encoder
            statusCode = VTCompressionSessionEncodeFrame(EncodingSession,
                                                         imageBuffer,
                                                         presentationTimeStamp,
                                                         kCMTimeInvalid,
                                                         NULL, NULL, &flags);
            // Check for error
            if (statusCode != noErr) {
                NSLog(@"H264: VTCompressionSessionEncodeFrame failed with %d", (int)statusCode);
                error = @"H264: VTCompressionSessionEncodeFrame failed ";

                // End the session
                VTCompressionSessionInvalidate(EncodingSession);
                CFRelease(EncodingSession);
                EncodingSession = NULL;
                error = NULL;
                return;
            }
            //            NSLog(@"H264: VTCompressionSessionEncodeFrame Success");

        }

        // Mark the completion
        VTCompressionSessionCompleteFrames(EncodingSession, kCMTimeInvalid);

        // End the session
        VTCompressionSessionInvalidate(EncodingSession);
        CFRelease(EncodingSession);
        EncodingSession = NULL;
        error = NULL;

        close(fd);
    });


}
- (void) initEncode:(int)width  height:(int)height
{
    dispatch_sync(aQueue, ^{

        // For testing out the logic, lets read from a file and then send it to encoder to create h264 stream

        // Create the compression session
        OSStatus status = VTCompressionSessionCreate(NULL, width, height, kCMVideoCodecType_H264, NULL, NULL, NULL, didCompressH264, (__bridge void *)(self),  &EncodingSession);
        NSLog(@"H264: VTCompressionSessionCreate %d", (int)status);

        if (status != 0)
        {
            NSLog(@"H264: Unable to create a H264 session");
            error = @"H264: Unable to create a H264 session";

            return ;

        }

        // Set the properties
        VTSessionSetProperty(EncodingSession, kVTCompressionPropertyKey_RealTime, kCFBooleanTrue);
        VTSessionSetProperty(EncodingSession, kVTCompressionPropertyKey_ProfileLevel, kVTProfileLevel_H264_Main_AutoLevel);


        // Tell the encoder to start encoding
        VTCompressionSessionPrepareToEncodeFrames(EncodingSession);
    });
}
- (void) encode:(CMSampleBufferRef )sampleBuffer
{
    dispatch_sync(aQueue, ^{

        frameCount++;
        // Get the CV Image buffer
        CVImageBufferRef imageBuffer = (CVImageBufferRef)CMSampleBufferGetImageBuffer(sampleBuffer);

        // Create properties
        CMTime presentationTimeStamp = CMTimeMake(frameCount, 1000);
        //CMTime duration = CMTimeMake(1, DURATION);
        VTEncodeInfoFlags flags;

        // Pass it to the encoder
        OSStatus statusCode = VTCompressionSessionEncodeFrame(EncodingSession,
                                                              imageBuffer,
                                                              presentationTimeStamp,
                                                              kCMTimeInvalid,
                                                              NULL, NULL, &flags);
        // Check for error
        if (statusCode != noErr) {
            NSLog(@"H264: VTCompressionSessionEncodeFrame failed with %d", (int)statusCode);
            error = @"H264: VTCompressionSessionEncodeFrame failed ";

            // End the session
            VTCompressionSessionInvalidate(EncodingSession);
            CFRelease(EncodingSession);
            EncodingSession = NULL;
            error = NULL;
            return;
        }
        //            NSLog(@"H264: VTCompressionSessionEncodeFrame Success");
    });


}


- (void) End
{
    // Mark the completion
    VTCompressionSessionCompleteFrames(EncodingSession, kCMTimeInvalid);

    // End the session
    VTCompressionSessionInvalidate(EncodingSession);
    CFRelease(EncodingSession);
    EncodingSession = NULL;
    error = NULL;

}

@end

好多具体实现我也不是理解的很透彻,不过总算是做出来了, CPU 大概在百分之30左右,比软编强很多.
不知道写明白没有,别叫我程序员,我只是代码的搬运工!

阅读更多

没有更多推荐了,返回首页