- r - 以节省内存的方式增长 data.frame
- ruby-on-rails - ruby/ruby on rails 内存泄漏检测
- android - 无法解析导入android.support.v7.app
- UNIX 域套接字与共享内存(映射文件)
我正在努力对从 AVCaptureSession
接收的音频缓冲区进行编码,使用AudioConverter
,然后将它们附加到 AVAssetWriter
。
我没有收到任何错误(包括 OSStatus 响应),并且生成的 CMSampleBuffer
似乎包含有效数据,但是生成的文件根本没有任何可播放的音频。与视频一起写作时,视频帧停止在 (appendSampleBuffer()
中附加几帧返回 false,但没有 AVAssetWriter.error
),可能是因为 Assets 作家正在等待音频 catch 来。我怀疑这与方式有关我正在为 AAC 设置启动。
该应用程序使用 RxSwift,但我删除了 RxSwift 部分以便更容易为更广泛的受众理解。
请查看下面代码中的评论以获取更多...评论
给定一个设置结构:
import Foundation
import AVFoundation
import CleanroomLogger
public struct AVSettings {
let orientation: AVCaptureVideoOrientation = .Portrait
let sessionPreset = AVCaptureSessionPreset1280x720
let videoBitrate: Int = 2_000_000
let videoExpectedFrameRate: Int = 30
let videoMaxKeyFrameInterval: Int = 60
let audioBitrate: Int = 32 * 1024
/// Settings that are `0` means variable rate.
/// The `mSampleRate` and `mChennelsPerFrame` is overwritten at run-time
/// to values based on the input stream.
let audioOutputABSD = AudioStreamBasicDescription(
mSampleRate: AVAudioSession.sharedInstance().sampleRate,
mFormatID: kAudioFormatMPEG4AAC,
mFormatFlags: UInt32(MPEG4ObjectID.AAC_Main.rawValue),
mBytesPerPacket: 0,
mFramesPerPacket: 1024,
mBytesPerFrame: 0,
mChannelsPerFrame: 1,
mBitsPerChannel: 0,
mReserved: 0)
let audioEncoderClassDescriptions = [
AudioClassDescription(
mType: kAudioEncoderComponentType,
mSubType: kAudioFormatMPEG4AAC,
mManufacturer: kAppleSoftwareAudioCodecManufacturer) ]
}
一些辅助函数:
public func getVideoDimensions(fromSettings settings: AVSettings) -> (Int, Int) {
switch (settings.sessionPreset, settings.orientation) {
case (AVCaptureSessionPreset1920x1080, .Portrait): return (1080, 1920)
case (AVCaptureSessionPreset1280x720, .Portrait): return (720, 1280)
default: fatalError("Unsupported session preset and orientation")
}
}
public func createAudioFormatDescription(fromSettings settings: AVSettings) -> CMAudioFormatDescription {
var result = noErr
var absd = settings.audioOutputABSD
var description: CMAudioFormatDescription?
withUnsafePointer(&absd) { absdPtr in
result = CMAudioFormatDescriptionCreate(nil,
absdPtr,
0, nil,
0, nil,
nil,
&description)
}
if result != noErr {
Log.error?.message("Could not create audio format description")
}
return description!
}
public func createVideoFormatDescription(fromSettings settings: AVSettings) -> CMVideoFormatDescription {
var result = noErr
var description: CMVideoFormatDescription?
let (width, height) = getVideoDimensions(fromSettings: settings)
result = CMVideoFormatDescriptionCreate(nil,
kCMVideoCodecType_H264,
Int32(width),
Int32(height),
[:],
&description)
if result != noErr {
Log.error?.message("Could not create video format description")
}
return description!
}
这是 Assets 编写器的初始化方式:
guard let audioDevice = defaultAudioDevice() else
{ throw RecordError.MissingDeviceFeature("Microphone") }
guard let videoDevice = defaultVideoDevice(.Back) else
{ throw RecordError.MissingDeviceFeature("Camera") }
let videoInput = try AVCaptureDeviceInput(device: videoDevice)
let audioInput = try AVCaptureDeviceInput(device: audioDevice)
let videoFormatHint = createVideoFormatDescription(fromSettings: settings)
let audioFormatHint = createAudioFormatDescription(fromSettings: settings)
let writerVideoInput = AVAssetWriterInput(mediaType: AVMediaTypeVideo,
outputSettings: nil,
sourceFormatHint: videoFormatHint)
let writerAudioInput = AVAssetWriterInput(mediaType: AVMediaTypeAudio,
outputSettings: nil,
sourceFormatHint: audioFormatHint)
writerVideoInput.expectsMediaDataInRealTime = true
writerAudioInput.expectsMediaDataInRealTime = true
let url = NSURL(fileURLWithPath: NSTemporaryDirectory(), isDirectory: true)
.URLByAppendingPathComponent(NSProcessInfo.processInfo().globallyUniqueString)
.URLByAppendingPathExtension("mp4")
let assetWriter = try AVAssetWriter(URL: url, fileType: AVFileTypeMPEG4)
if !assetWriter.canAddInput(writerVideoInput) {
throw RecordError.Unknown("Could not add video input") }
if !assetWriter.canAddInput(writerAudioInput) {
throw RecordError.Unknown("Could not add audio input") }
assetWriter.addInput(writerVideoInput)
assetWriter.addInput(writerAudioInput)
这就是音频样本的编码方式,问题区域最有可能在这里。我重写了它,因此它不使用任何 Rx-isms。
var outputABSD = settings.audioOutputABSD
var outputFormatDescription: CMAudioFormatDescription! = nil
CMAudioFormatDescriptionCreate(nil, &outputABSD, 0, nil, 0, nil, nil, &formatDescription)
var converter: AudioConverter?
// Indicates whether priming information has been attached to the first buffer
var primed = false
func encodeAudioBuffer(settings: AVSettings, buffer: CMSampleBuffer) throws -> CMSampleBuffer? {
// Create the audio converter if it's not available
if converter == nil {
var classDescriptions = settings.audioEncoderClassDescriptions
var inputABSD = CMAudioFormatDescriptionGetStreamBasicDescription(CMSampleBufferGetFormatDescription(buffer)!).memory
var outputABSD = settings.audioOutputABSD
outputABSD.mSampleRate = inputABSD.mSampleRate
outputABSD.mChannelsPerFrame = inputABSD.mChannelsPerFrame
var converter: AudioConverterRef = nil
var result = noErr
result = withUnsafePointer(&outputABSD) { outputABSDPtr in
return withUnsafePointer(&inputABSD) { inputABSDPtr in
return AudioConverterNewSpecific(inputABSDPtr,
outputABSDPtr,
UInt32(classDescriptions.count),
&classDescriptions,
&converter)
}
}
if result != noErr { throw RecordError.Unknown }
// At this point I made an attempt to retrieve priming info from
// the audio converter assuming that it will give me back default values
// I can use, but ended up with `nil`
var primeInfo: AudioConverterPrimeInfo? = nil
var primeInfoSize = UInt32(sizeof(AudioConverterPrimeInfo))
// The following returns a `noErr` but `primeInfo` is still `nil``
AudioConverterGetProperty(converter,
kAudioConverterPrimeInfo,
&primeInfoSize,
&primeInfo)
// I've also tried to set `kAudioConverterPrimeInfo` so that it knows
// the leading frames that are being primed, but the set didn't seem to work
// (`noErr` but getting the property afterwards still returned `nil`)
}
let converter = converter!
// Need to give a big enough output buffer.
// The assumption is that it will always be <= to the input size
let numSamples = CMSampleBufferGetNumSamples(buffer)
// This becomes 1024 * 2 = 2048
let outputBufferSize = numSamples * Int(inputABSD.mBytesPerPacket)
let outputBufferPtr = UnsafeMutablePointer<Void>.alloc(outputBufferSize)
defer {
outputBufferPtr.destroy()
outputBufferPtr.dealloc(1)
}
var result = noErr
var outputPacketCount = UInt32(1)
var outputData = AudioBufferList(
mNumberBuffers: 1,
mBuffers: AudioBuffer(
mNumberChannels: outputABSD.mChannelsPerFrame,
mDataByteSize: UInt32(outputBufferSize),
mData: outputBufferPtr))
// See below for `EncodeAudioUserData`
var userData = EncodeAudioUserData(inputSampleBuffer: buffer,
inputBytesPerPacket: inputABSD.mBytesPerPacket)
withUnsafeMutablePointer(&userData) { userDataPtr in
// See below for `fetchAudioProc`
result = AudioConverterFillComplexBuffer(
converter,
fetchAudioProc,
userDataPtr,
&outputPacketCount,
&outputData,
nil)
}
if result != noErr {
Log.error?.message("Error while trying to encode audio buffer, code: \(result)")
return nil
}
// See below for `CMSampleBufferCreateCopy`
guard let newBuffer = CMSampleBufferCreateCopy(buffer,
fromAudioBufferList: &outputData,
newFromatDescription: outputFormatDescription) else {
Log.error?.message("Could not create sample buffer from audio buffer list")
return nil
}
if !primed {
primed = true
// Simply picked 2112 samples based on convention, is there a better way to determine this?
let samplesToPrime: Int64 = 2112
let samplesPerSecond = Int32(settings.audioOutputABSD.mSampleRate)
let primingDuration = CMTimeMake(samplesToPrime, samplesPerSecond)
// Without setting the attachment the asset writer will complain about the
// first buffer missing the `TrimDurationAtStart` attachment, is there are way
// to infer the value from the given `AudioBufferList`?
CMSetAttachment(newBuffer,
kCMSampleBufferAttachmentKey_TrimDurationAtStart,
CMTimeCopyAsDictionary(primingDuration, nil),
kCMAttachmentMode_ShouldNotPropagate)
}
return newBuffer
}
下面是为音频转换器获取样本的过程,以及数据传递给它的结构:
private class EncodeAudioUserData {
var inputSampleBuffer: CMSampleBuffer?
var inputBytesPerPacket: UInt32
init(inputSampleBuffer: CMSampleBuffer,
inputBytesPerPacket: UInt32) {
self.inputSampleBuffer = inputSampleBuffer
self.inputBytesPerPacket = inputBytesPerPacket
}
}
private let fetchAudioProc: AudioConverterComplexInputDataProc = {
(inAudioConverter,
ioDataPacketCount,
ioData,
outDataPacketDescriptionPtrPtr,
inUserData) in
var result = noErr
if ioDataPacketCount.memory == 0 { return noErr }
let userData = UnsafeMutablePointer<EncodeAudioUserData>(inUserData).memory
// If its already been processed
guard let buffer = userData.inputSampleBuffer else {
ioDataPacketCount.memory = 0
return -1
}
var inputBlockBuffer: CMBlockBuffer?
var inputBufferList = AudioBufferList()
result = CMSampleBufferGetAudioBufferListWithRetainedBlockBuffer(
buffer,
nil,
&inputBufferList,
sizeof(AudioBufferList),
nil,
nil,
0,
&inputBlockBuffer)
if result != noErr {
Log.error?.message("Error while trying to retrieve buffer list, code: \(result)")
ioDataPacketCount.memory = 0
return result
}
let packetsCount = inputBufferList.mBuffers.mDataByteSize / userData.inputBytesPerPacket
ioDataPacketCount.memory = packetsCount
ioData.memory.mBuffers.mNumberChannels = inputBufferList.mBuffers.mNumberChannels
ioData.memory.mBuffers.mDataByteSize = inputBufferList.mBuffers.mDataByteSize
ioData.memory.mBuffers.mData = inputBufferList.mBuffers.mData
if outDataPacketDescriptionPtrPtr != nil {
outDataPacketDescriptionPtrPtr.memory = nil
}
return noErr
}
这就是我将 AudioBufferList
转换为 CMSampleBuffer
的方式:
public func CMSampleBufferCreateCopy(
buffer: CMSampleBuffer,
inout fromAudioBufferList bufferList: AudioBufferList,
newFromatDescription formatDescription: CMFormatDescription? = nil)
-> CMSampleBuffer? {
var result = noErr
var sizeArray: [Int] = [Int(bufferList.mBuffers.mDataByteSize)]
// Copy timing info from the previous buffer
var timingInfo = CMSampleTimingInfo()
result = CMSampleBufferGetSampleTimingInfo(buffer, 0, &timingInfo)
if result != noErr { return nil }
var newBuffer: CMSampleBuffer?
result = CMSampleBufferCreateReady(
kCFAllocatorDefault,
nil,
formatDescription ?? CMSampleBufferGetFormatDescription(buffer),
Int(bufferList.mNumberBuffers),
1, &timingInfo,
1, &sizeArray,
&newBuffer)
if result != noErr { return nil }
guard let b = newBuffer else { return nil }
CMSampleBufferSetDataBufferFromAudioBufferList(b, nil, nil, 0, &bufferList)
return newBuffer
}
有什么我明显做错的地方吗?有没有合适的方法从 AudioBufferList
构造 CMSampleBuffer
?你如何转移启动从转换器到您创建的 CMSampleBuffer
的信息?
对于我的用例,我需要手动进行编码,因为缓冲区将是进一步操纵管道(虽然我已经禁用了所有编码后的转换以确保它有效。)
任何帮助都将非常感激。抱歉代码太多摘要,但我想提供尽可能多的上下文。
提前致谢:)
一些相关问题:
我用过的一些引用资料:
最佳答案
事实证明我做错了很多事情。我不会发布乱码,而是尝试将其组织成我发现的小块内容..
这对我来说是一个巨大的困惑:
CMSampleBuffer
可以有 1 个或多个样本缓冲区(通过 CMSampleBufferGetNumSamples
发现)CMSampleBuffer
代表一个音频数据包。CMSampleBufferGetNumSamples(sample)
将返回给定缓冲区中包含的数据包数。AudioStreamBasicDescription
的 mFramesPerPacket
属性控制。对于线性 PCM 缓冲区,每个样本缓冲区的总大小为 frames * bytes per frame
。对于压缩缓冲区(如 AAC),总大小和帧数之间没有关系。AudioConverterComplexInputDataProc
此回调用于检索更多线性 PCM 音频数据以进行编码。您必须必须提供至少 ioNumberDataPackets
指定的数据包数量。由于我一直在使用转换器进行实时推送式编码,因此我需要确保每次数据推送都包含最少数量的数据包。像这样的东西(伪代码):
let minimumPackets = outputFramesPerPacket / inputFramesPerPacket
var buffers: [CMSampleBuffer] = []
while getTotalSize(buffers) < minimumPackets {
buffers = buffers + [getNextBuffer()]
}
AudioConverterFillComplexBuffer(...)
CMSampleBuffer
的如果 CMSampleBuffer
包含多个缓冲区,您实际上可以对它们进行切片。执行此操作的工具是 CMSampleBufferCopySampleBufferForRange
。这很好,因此您可以向 AudioConverterComplexInputDataProc
提供它要求的确切 数据包数,这样可以更轻松地处理生成的编码缓冲区的计时信息。因为如果您在转换器期望 1024
时提供 1500
数据帧,则结果样本缓冲区的持续时间为 1024/sampleRate
而不是到 1500/sampleRate
。
在进行 AAC 编码时,您必须像这样设置修剪持续时间:
CMSetAttachment(buffer,
kCMSampleBufferAttachmentKey_TrimDurationAtStart,
CMTimeCopyAsDictionary(primingDuration, kCFAllocatorDefault),
kCMAttachmentMode_ShouldNotPropagate)
我做错的一件事是我在编码时间 添加了修剪持续时间。这应该由您的编写器处理,以便它可以保证将信息添加到您的前导音频帧中。
此外,kCMSampleBufferAttachmentKey_TrimDurationAtStart
的值应该永远大于样本缓冲区的持续时间。启动示例:
2112
44100
2112/44100 = ~0.0479s
1024
,启动持续时间:1024/44100
1024
,启动持续时间:1088/41100
CMSampleBuffer
AudioConverterFillComplexBuffer
有一个可选的 outputPacketDescriptionsPtr
。 你应该使用它。它将指向包含样本大小信息的新数据包描述数组。您需要此样本大小信息来构建新的压缩样本缓冲区:
let bufferList: AudioBufferList
let packetDescriptions: [AudioStreamPacketDescription]
var newBuffer: CMSampleBuffer?
CMAudioSampleBufferCreateWithPacketDescriptions(
kCFAllocatorDefault, // allocator
nil, // dataBuffer
false, // dataReady
nil, // makeDataReadyCallback
nil, // makeDataReadyRefCon
formatDescription, // formatDescription
Int(bufferList.mNumberBuffers), // numSamples
CMSampleBufferGetPresentationTimeStamp(buffer), // sbufPTS (first PTS)
&packetDescriptions, // packetDescriptions
&newBuffer)
关于ios - 使用 AudioConverter 进行 AAC 编码并写入 AVAssetWriter,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/36351327/
IO 设备如何知道属于它的内存中的值在memory mapped IO 中发生了变化? ? 例如,假设内存地址 0 专用于保存 VGA 设备的背景颜色。当我们更改 memory[0] 中的值时,VGA
我目前正在开发一个使用Facebook sdk登录(通过FBLoginView)的iOS应用。 一切正常,除了那些拥有较旧版本的facebook的人。 当他们按下“使用Facebook登录”按钮时,他
假设我有: this - is an - example - with some - dashesNSRange将使用`rangeOfString:@“-”拾取“-”的第一个实例,但是如果我只想要最后
Card.io SDK提供以下详细信息: 卡号,有效期,月份,年份,CVV和邮政编码。 如何从此SDK获取国家名称。 - (void)userDidProvideCreditCardInfo:(Car
iOS 应用程序如何从网络服务下载图片并在安装过程中将它们安装到用户的 iOS 设备上?可能吗? 最佳答案 您无法控制应用在用户设备上的安装,因此无法在安装过程中下载其他数据。 只需在安装后首次启动应
我曾经开发过一款企业版 iOS 产品,我们公司曾将其出售给大型企业,供他们的员工使用。 该应用程序通过 AppStore 提供,企业用户获得了公司特定的配置文件(包含应用程序配置文件)以启用他们有权使
我正在尝试将 Card.io SDK 集成到我的 iOS 应用程序中。我想为 CardIO ui 做一个简单的本地化,如更改取消按钮标题或“在此保留信用卡”提示文本。 我在 github 上找到了这个
我正在使用 CardIOView 和 CardIOViewDelegate 类,没有可以设置为 YES 的 BOOL 来扫描 collectCardholderName。我可以看到它在 CardIOP
我有一个集成了通话工具包的 voip 应用程序。每次我从我的 voip 应用程序调用时,都会在 native 电话应用程序中创建一个新的最近通话记录。我在 voip 应用程序中也有自定义联系人(电话应
iOS 应用程序如何知道应用程序打开时屏幕上是否已经有键盘?应用程序运行后,它可以接收键盘显示/隐藏通知。但是,如果应用程序在分屏模式下作为辅助应用程序打开,而主应用程序已经显示键盘,则辅助应用程序不
我在模拟器中收到以下错误: ImageIO: CGImageReadSessionGetCachedImageBlockData *** CGImageReadSessionGetCachedIm
如 Apple 文档所示,可以通过 EAAccessory Framework 与经过认证的配件(由 Apple 认证)进行通信。但是我有点困惑,因为一些帖子告诉我它也可以通过 CoreBluetoo
尽管现在的调试器已经很不错了,但有时找出应用程序中正在发生的事情的最好方法仍然是古老的 NSLog。当您连接到计算机时,这样做很容易; Xcode 会帮助弹出日志查看器面板,然后就可以了。当您不在办公
在我的 iOS 应用程序中,我定义了一些兴趣点。其中一些有一个 Kontakt.io 信标的名称,它绑定(bind)到一个特定的 PoI(我的意思是通常贴在信标标签上的名称)。现在我想在附近发现信标,
我正在为警报提示创建一个 trigger.io 插件。尝试从警报提示返回数据。这是我的代码: // Prompt + (void)show_prompt:(ForgeTask*)task{
您好,我是 Apple iOS 的新手。我阅读并搜索了很多关于推送通知的文章,但我没有发现任何关于 APNS 从 io4 到 ios 6 的新更新的信息。任何人都可以向我提供 APNS 如何在 ios
UITabBar 的高度似乎在 iOS 7 和 8/9/10/11 之间发生了变化。我发布这个问题是为了让其他人轻松找到答案。 那么:在 iPhone 和 iPad 上的 iOS 8/9/10/11
我想我可以针对不同的 iOS 版本使用不同的 Storyboard。 由于 UI 的差异,我将创建下一个 Storyboard: Main_iPhone.storyboard Main_iPad.st
我正在写一些东西,我将使用设备的 iTunes 库中的一部分音轨来覆盖 2 个视频的组合,例如: AVMutableComposition* mixComposition = [[AVMutableC
我创建了一个简单的 iOS 程序,可以顺利编译并在 iPad 模拟器上运行良好。当我告诉 XCode 4 使用我连接的 iPad 设备时,无法编译相同的程序。问题似乎是当我尝试使用附加的 iPad 时
我是一名优秀的程序员,十分优秀!