ios - 暂停/恢复时实时AVAssetWriter同步音频和视频

Question

我正在尝试使用 iPhone 的前置摄像头录制有声视频。因为我还需要支持暂停/恢复功能，所以我需要使用 AVAssetWriter .我在网上找到了一个用 Objective-C 编写的示例，它几乎实现了所需的功能( http://www.gdcl.co.uk/2013/02/20/iPhone-Pause.html )

不幸的是，在将此示例转换为 Swift 后，我​​注意到如果我暂停/恢复，在每个“部分”的末尾有一段很小但很明显的时间段，在此期间视频只是一个静止帧并且正在播放音频。所以，似乎当 isPaused触发时，录制的音轨比录制的视频轨长。

对不起，如果它看起来像一个菜鸟问题，但我不是 AVFoundation 的专家一些帮助将不胜感激!

下面我发布了我对 didOutput sampleBuffer 的实现.

func captureOutput(_ output: AVCaptureOutput, didOutput sampleBuffer: CMSampleBuffer, from connection: AVCaptureConnection) {
    var isVideo = true
    if videoConntection != connection {
        isVideo = false
    }
    if (!isCapturing || isPaused) {
        return
    }

    if (encoder == nil) {
        if isVideo {
            return
        }
        if let fmt = CMSampleBufferGetFormatDescription(sampleBuffer) {
            let desc = CMAudioFormatDescriptionGetStreamBasicDescription(fmt as CMAudioFormatDescription)
            if let chan = desc?.pointee.mChannelsPerFrame, let rate = desc?.pointee.mSampleRate {
                let path = tempPath()!
                encoder = VideoEncoder(path: path, height: Int(cameraSize.height), width: Int(cameraSize.width), channels: chan, rate: rate)
            }
        }
    }
    if discont {
        if isVideo {
            return
        }
        discont = false
        var pts = CMSampleBufferGetPresentationTimeStamp(sampleBuffer)
        let last = lastAudio
        if last.flags.contains(CMTimeFlags.valid) {
            if cmOffset.flags.contains(CMTimeFlags.valid) {
                pts = CMTimeSubtract(pts, cmOffset)
            }
            let off = CMTimeSubtract(pts, last)
            print("setting offset from \(isVideo ? "video":"audio")")
            print("adding \(CMTimeGetSeconds(off)) to \(CMTimeGetSeconds(cmOffset)) (pts \(CMTimeGetSeconds(cmOffset)))")
            if cmOffset.value == 0 {
                cmOffset = off
            }
            else {
                cmOffset = CMTimeAdd(cmOffset, off)
            }
        }
        lastVideo.flags = []
        lastAudio.flags = []
        return
    }
    var out:CMSampleBuffer?
    if cmOffset.value > 0 {
        var count:CMItemCount = CMSampleBufferGetNumSamples(sampleBuffer)
        let pInfo = UnsafeMutablePointer<CMSampleTimingInfo>.allocate(capacity: count)
        CMSampleBufferGetSampleTimingInfoArray(sampleBuffer, entryCount: count, arrayToFill: pInfo, entriesNeededOut: &count)
        var i = 0
        while i<count {
            pInfo[i].decodeTimeStamp = CMTimeSubtract(pInfo[i].decodeTimeStamp, cmOffset)
            pInfo[i].presentationTimeStamp = CMTimeSubtract(pInfo[i].presentationTimeStamp, cmOffset)
            i+=1
        }
        CMSampleBufferCreateCopyWithNewTiming(allocator: nil, sampleBuffer: sampleBuffer, sampleTimingEntryCount: count, sampleTimingArray: pInfo, sampleBufferOut: &out)
    }
    else {
        out = sampleBuffer
    }
    var pts = CMSampleBufferGetPresentationTimeStamp(out!)
    let dur = CMSampleBufferGetDuration(out!)
    if (dur.value > 0)
    {
        pts = CMTimeAdd(pts, dur);
    }
    if (isVideo) {
        lastVideo = pts;
    }
    else {
        lastAudio = pts;
    }
    encoder?.encodeFrame(sampleBuffer: out!, isVideo: isVideo)
}

这是我的 VideoEncoder类(class):

final class VideoEncoder {
    var writer:AVAssetWriter
    var videoInput:AVAssetWriterInput
    var audioInput:AVAssetWriterInput
    var path:String

    init(path:String, height:Int, width:Int, channels:UInt32, rate:Float64) {
        self.path = path
        if FileManager.default.fileExists(atPath:path) {
            try? FileManager.default.removeItem(atPath: path)
        }
        let url = URL(fileURLWithPath: path)
        writer = try! AVAssetWriter(outputURL: url, fileType: .mp4)
        videoInput = AVAssetWriterInput(mediaType: .video, outputSettings: [
            AVVideoCodecKey: AVVideoCodecType.h264,
            AVVideoWidthKey:height,
            AVVideoHeightKey:width
        ])
        videoInput.expectsMediaDataInRealTime = true
        writer.add(videoInput)

        audioInput = AVAssetWriterInput(mediaType: .audio, outputSettings: [
            AVFormatIDKey:kAudioFormatMPEG4AAC,
            AVNumberOfChannelsKey:channels,
            AVSampleRateKey:rate
        ])
        audioInput.expectsMediaDataInRealTime = true
        writer.add(audioInput)
    }

    func finish(with completionHandler:@escaping ()->Void) {
        writer.finishWriting(completionHandler: completionHandler)
    }

    func encodeFrame(sampleBuffer:CMSampleBuffer, isVideo:Bool) -> Bool {
        if CMSampleBufferDataIsReady(sampleBuffer) {
            if writer.status == .unknown {
                writer.startWriting()
                writer.startSession(atSourceTime: CMSampleBufferGetPresentationTimeStamp(sampleBuffer))
            }
            if writer.status == .failed {
                QFLogger.shared.addLog(format: "[ERROR initiating AVAssetWriter]", args: [], error: writer.error)
                return false
            }
            if isVideo {
                if videoInput.isReadyForMoreMediaData {
                    videoInput.append(sampleBuffer)
                    return true
                }
            }
            else {
                if audioInput.isReadyForMoreMediaData {
                    audioInput.append(sampleBuffer)
                    return true
                }
            }
        }
        return false
    }
}

代码的其余部分应该很明显，但为了使其完整，这里是我要暂停的内容:

isPaused = true
discont = true

这是简历:

isPaused = false

如果有人能帮助我了解如何在这样的现场录制过程中对齐视频和音频轨道，那就太好了!

Answer 1

好的，事实证明我提供的代码没有错误。我遇到的问题是由打开的视频平滑引起的 :) 我猜它需要额外的帧来平滑视频，这就是为什么视频输出在短时间内卡住的原因。