- iOS/Objective-C 元类和类别
- objective-c - -1001 错误,当 NSURLSession 通过 httpproxy 和/etc/hosts
- java - 使用网络类获取 url 地址
- ios - 推送通知中不播放声音
我在 SO 和一些不错的博客文章上挖掘了很多但似乎我有独特的要求单独读取视频和音频缓冲区以便在录制过程中对其进行进一步处理。
我的用例就像当用户开始录制视频时,我需要使用 ML-Face-Detection-Kit
不断处理视频帧,并不断处理音频帧以确保用户正在说些什么并检测噪音水平。为此,我认为我需要将视频和音频都放在一个单独的缓冲区中,并在处理后将其合并并保存到 MP4 文件中作为录音。
我试过了CameraView由伟人开发Mattia Iavarone但它仅提供视频帧。
我愿意接受其他有用的建议/反馈来处理这种情况。
最佳答案
这是一个 answer引用 javaCV 库的 RecordActivity.java示例。
它使用单独的音频和视频线程实时获取帧。
编辑 1:我按照建议包含了 Bytedeco 的 RecordActivity.java 的代码示例。
package org.bytedeco.javacv.recordactivity;
import android.app.Activity;
import android.content.Context;
import android.content.pm.ActivityInfo;
import android.hardware.Camera;
import android.hardware.Camera.PreviewCallback;
import android.media.AudioFormat;
import android.media.AudioRecord;
import android.media.MediaRecorder;
import android.os.Bundle;
import android.os.PowerManager;
import android.util.Log;
import android.view.Display;
import android.view.KeyEvent;
import android.view.LayoutInflater;
import android.view.SurfaceHolder;
import android.view.SurfaceView;
import android.view.View;
import android.view.View.OnClickListener;
import android.view.WindowManager;
import android.widget.Button;
import android.widget.LinearLayout;
import android.widget.RelativeLayout;
import java.io.IOException;
import java.nio.ByteBuffer;
import java.nio.ShortBuffer;
import java.util.Collections;
import java.util.Comparator;
import java.util.List;
import org.bytedeco.javacpp.avutil;
import org.bytedeco.javacv.FFmpegFrameFilter;
import org.bytedeco.javacv.FFmpegFrameRecorder;
import org.bytedeco.javacv.Frame;
import org.bytedeco.javacv.FrameFilter;
public class RecordActivity extends Activity implements OnClickListener {
private final static String CLASS_LABEL = "RecordActivity";
private final static String LOG_TAG = CLASS_LABEL;
private String ffmpeg_link = "/mnt/sdcard/stream.flv";
long startTime = 0;
boolean recording = false;
private FFmpegFrameRecorder recorder;
private boolean isPreviewOn = false;
/*Filter information, change boolean to true if adding a fitler*/
private boolean addFilter = true;
private String filterString = "";
FFmpegFrameFilter filter;
private int sampleAudioRateInHz = 44100;
private int imageWidth = 320;
private int imageHeight = 240;
private int frameRate = 30;
/* audio data getting thread */
private AudioRecord audioRecord;
private AudioRecordRunnable audioRecordRunnable;
private Thread audioThread;
volatile boolean runAudioThread = true;
/* video data getting thread */
private Camera cameraDevice;
private CameraView cameraView;
private Frame yuvImage = null;
/* layout setting */
private final int bg_screen_bx = 232;
private final int bg_screen_by = 128;
private final int bg_screen_width = 700;
private final int bg_screen_height = 500;
private final int bg_width = 1123;
private final int bg_height = 715;
private final int live_width = 640;
private final int live_height = 480;
private int screenWidth, screenHeight;
private Button btnRecorderControl;
/* The number of seconds in the continuous record loop (or 0 to disable loop). */
final int RECORD_LENGTH = 0;
Frame[] images;
long[] timestamps;
ShortBuffer[] samples;
int imagesIndex, samplesIndex;
@Override
public void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
setRequestedOrientation(ActivityInfo.SCREEN_ORIENTATION_LANDSCAPE);
setContentView(R.layout.main);
initLayout();
}
@Override
protected void onDestroy() {
super.onDestroy();
recording = false;
if (cameraView != null) {
cameraView.stopPreview();
}
if(cameraDevice != null) {
cameraDevice.stopPreview();
cameraDevice.release();
cameraDevice = null;
}
}
private void initLayout() {
/* get size of screen */
Display display = ((WindowManager) getSystemService(Context.WINDOW_SERVICE)).getDefaultDisplay();
screenWidth = display.getWidth();
screenHeight = display.getHeight();
RelativeLayout.LayoutParams layoutParam = null;
LayoutInflater myInflate = null;
myInflate = (LayoutInflater) getSystemService(Context.LAYOUT_INFLATER_SERVICE);
RelativeLayout topLayout = new RelativeLayout(this);
setContentView(topLayout);
LinearLayout preViewLayout = (LinearLayout) myInflate.inflate(R.layout.main, null);
layoutParam = new RelativeLayout.LayoutParams(screenWidth, screenHeight);
topLayout.addView(preViewLayout, layoutParam);
/* add control button: start and stop */
btnRecorderControl = (Button) findViewById(R.id.recorder_control);
btnRecorderControl.setText("Start");
btnRecorderControl.setOnClickListener(this);
/* add camera view */
int display_width_d = (int) (1.0 * bg_screen_width * screenWidth / bg_width);
int display_height_d = (int) (1.0 * bg_screen_height * screenHeight / bg_height);
int prev_rw, prev_rh;
if (1.0 * display_width_d / display_height_d > 1.0 * live_width / live_height) {
prev_rh = display_height_d;
prev_rw = (int) (1.0 * display_height_d * live_width / live_height);
} else {
prev_rw = display_width_d;
prev_rh = (int) (1.0 * display_width_d * live_height / live_width);
}
layoutParam = new RelativeLayout.LayoutParams(prev_rw, prev_rh);
layoutParam.topMargin = (int) (1.0 * bg_screen_by * screenHeight / bg_height);
layoutParam.leftMargin = (int) (1.0 * bg_screen_bx * screenWidth / bg_width);
cameraDevice = Camera.open();
Log.i(LOG_TAG, "cameara open");
cameraView = new CameraView(this, cameraDevice);
topLayout.addView(cameraView, layoutParam);
Log.i(LOG_TAG, "cameara preview start: OK");
}
//---------------------------------------
// initialize ffmpeg_recorder
//---------------------------------------
private void initRecorder() {
Log.w(LOG_TAG,"init recorder");
if (RECORD_LENGTH > 0) {
imagesIndex = 0;
images = new Frame[RECORD_LENGTH * frameRate];
timestamps = new long[images.length];
for (int i = 0; i < images.length; i++) {
images[i] = new Frame(imageWidth, imageHeight, Frame.DEPTH_UBYTE, 2);
timestamps[i] = -1;
}
} else if (yuvImage == null) {
yuvImage = new Frame(imageWidth, imageHeight, Frame.DEPTH_UBYTE, 2);
Log.i(LOG_TAG, "create yuvImage");
}
Log.i(LOG_TAG, "ffmpeg_url: " + ffmpeg_link);
recorder = new FFmpegFrameRecorder(ffmpeg_link, imageWidth, imageHeight, 1);
recorder.setFormat("flv");
recorder.setSampleRate(sampleAudioRateInHz);
// Set in the surface changed method
recorder.setFrameRate(frameRate);
// The filterString is any ffmpeg filter.
// Here is the link for a list: https://ffmpeg.org/ffmpeg-filters.html
filterString = "transpose=0";
filter = new FFmpegFrameFilter(filterString, imageWidth, imageHeight);
//default format on android
filter.setPixelFormat(avutil.AV_PIX_FMT_NV21);
Log.i(LOG_TAG, "recorder initialize success");
audioRecordRunnable = new AudioRecordRunnable();
audioThread = new Thread(audioRecordRunnable);
runAudioThread = true;
}
public void startRecording() {
initRecorder();
try {
recorder.start();
startTime = System.currentTimeMillis();
recording = true;
audioThread.start();
if(addFilter) {
filter.start();
}
} catch (FFmpegFrameRecorder.Exception | FrameFilter.Exception e) {
e.printStackTrace();
}
}
public void stopRecording() {
runAudioThread = false;
try {
audioThread.join();
} catch (InterruptedException e) {
// reset interrupt to be nice
Thread.currentThread().interrupt();
return;
}
audioRecordRunnable = null;
audioThread = null;
if (recorder != null && recording) {
if (RECORD_LENGTH > 0) {
Log.v(LOG_TAG,"Writing frames");
try {
int firstIndex = imagesIndex % samples.length;
int lastIndex = (imagesIndex - 1) % images.length;
if (imagesIndex <= images.length) {
firstIndex = 0;
lastIndex = imagesIndex - 1;
}
if ((startTime = timestamps[lastIndex] - RECORD_LENGTH * 1000000L) < 0) {
startTime = 0;
}
if (lastIndex < firstIndex) {
lastIndex += images.length;
}
for (int i = firstIndex; i <= lastIndex; i++) {
long t = timestamps[i % timestamps.length] - startTime;
if (t >= 0) {
if (t > recorder.getTimestamp()) {
recorder.setTimestamp(t);
}
recorder.record(images[i % images.length]);
}
}
firstIndex = samplesIndex % samples.length;
lastIndex = (samplesIndex - 1) % samples.length;
if (samplesIndex <= samples.length) {
firstIndex = 0;
lastIndex = samplesIndex - 1;
}
if (lastIndex < firstIndex) {
lastIndex += samples.length;
}
for (int i = firstIndex; i <= lastIndex; i++) {
recorder.recordSamples(samples[i % samples.length]);
}
} catch (FFmpegFrameRecorder.Exception e) {
Log.v(LOG_TAG,e.getMessage());
e.printStackTrace();
}
}
recording = false;
Log.v(LOG_TAG,"Finishing recording, calling stop and release on recorder");
try {
recorder.stop();
recorder.release();
filter.stop();
filter.release();
} catch (FFmpegFrameRecorder.Exception | FrameFilter.Exception e) {
e.printStackTrace();
}
recorder = null;
}
}
@Override
public boolean onKeyDown(int keyCode, KeyEvent event) {
if (keyCode == KeyEvent.KEYCODE_BACK) {
if (recording) {
stopRecording();
}
finish();
return true;
}
return super.onKeyDown(keyCode, event);
}
//---------------------------------------------
// audio thread, gets and encodes audio data
//---------------------------------------------
class AudioRecordRunnable implements Runnable {
@Override
public void run() {
android.os.Process.setThreadPriority(android.os.Process.THREAD_PRIORITY_URGENT_AUDIO);
// Audio
int bufferSize;
ShortBuffer audioData;
int bufferReadResult;
bufferSize = AudioRecord.getMinBufferSize(sampleAudioRateInHz,
AudioFormat.CHANNEL_IN_MONO, AudioFormat.ENCODING_PCM_16BIT);
audioRecord = new AudioRecord(MediaRecorder.AudioSource.MIC, sampleAudioRateInHz,
AudioFormat.CHANNEL_IN_MONO, AudioFormat.ENCODING_PCM_16BIT, bufferSize);
if (RECORD_LENGTH > 0) {
samplesIndex = 0;
samples = new ShortBuffer[RECORD_LENGTH * sampleAudioRateInHz * 2 / bufferSize + 1];
for (int i = 0; i < samples.length; i++) {
samples[i] = ShortBuffer.allocate(bufferSize);
}
} else {
audioData = ShortBuffer.allocate(bufferSize);
}
Log.d(LOG_TAG, "audioRecord.startRecording()");
audioRecord.startRecording();
/* ffmpeg_audio encoding loop */
while (runAudioThread) {
if (RECORD_LENGTH > 0) {
audioData = samples[samplesIndex++ % samples.length];
audioData.position(0).limit(0);
}
//Log.v(LOG_TAG,"recording? " + recording);
bufferReadResult = audioRecord.read(audioData.array(), 0, audioData.capacity());
audioData.limit(bufferReadResult);
if (bufferReadResult > 0) {
Log.v(LOG_TAG,"bufferReadResult: " + bufferReadResult);
// If "recording" isn't true when start this thread, it never get's set according to this if statement...!!!
// Why? Good question...
if (recording) {
if (RECORD_LENGTH <= 0) try {
recorder.recordSamples(audioData);
//Log.v(LOG_TAG,"recording " + 1024*i + " to " + 1024*i+1024);
} catch (FFmpegFrameRecorder.Exception e) {
Log.v(LOG_TAG,e.getMessage());
e.printStackTrace();
}
}
}
}
Log.v(LOG_TAG,"AudioThread Finished, release audioRecord");
/* encoding finish, release recorder */
if (audioRecord != null) {
audioRecord.stop();
audioRecord.release();
audioRecord = null;
Log.v(LOG_TAG,"audioRecord released");
}
}
}
//---------------------------------------------
// camera thread, gets and encodes video data
//---------------------------------------------
class CameraView extends SurfaceView implements SurfaceHolder.Callback, PreviewCallback {
private SurfaceHolder mHolder;
private Camera mCamera;
public CameraView(Context context, Camera camera) {
super(context);
Log.w("camera","camera view");
mCamera = camera;
mHolder = getHolder();
mHolder.addCallback(CameraView.this);
mHolder.setType(SurfaceHolder.SURFACE_TYPE_PUSH_BUFFERS);
mCamera.setPreviewCallback(CameraView.this);
}
@Override
public void surfaceCreated(SurfaceHolder holder) {
try {
stopPreview();
mCamera.setPreviewDisplay(holder);
} catch (IOException exception) {
mCamera.release();
mCamera = null;
}
}
public void surfaceChanged(SurfaceHolder holder, int format, int width, int height) {
stopPreview();
Camera.Parameters camParams = mCamera.getParameters();
List<Camera.Size> sizes = camParams.getSupportedPreviewSizes();
// Sort the list in ascending order
Collections.sort(sizes, new Comparator<Camera.Size>() {
public int compare(final Camera.Size a, final Camera.Size b) {
return a.width * a.height - b.width * b.height;
}
});
// Pick the first preview size that is equal or bigger, or pick the last (biggest) option if we cannot
// reach the initial settings of imageWidth/imageHeight.
for (int i = 0; i < sizes.size(); i++) {
if ((sizes.get(i).width >= imageWidth && sizes.get(i).height >= imageHeight) || i == sizes.size() - 1) {
imageWidth = sizes.get(i).width;
imageHeight = sizes.get(i).height;
Log.v(LOG_TAG, "Changed to supported resolution: " + imageWidth + "x" + imageHeight);
break;
}
}
camParams.setPreviewSize(imageWidth, imageHeight);
Log.v(LOG_TAG,"Setting imageWidth: " + imageWidth + " imageHeight: " + imageHeight + " frameRate: " + frameRate);
camParams.setPreviewFrameRate(frameRate);
Log.v(LOG_TAG,"Preview Framerate: " + camParams.getPreviewFrameRate());
mCamera.setParameters(camParams);
// Set the holder (which might have changed) again
try {
mCamera.setPreviewDisplay(holder);
mCamera.setPreviewCallback(CameraView.this);
startPreview();
} catch (Exception e) {
Log.e(LOG_TAG, "Could not set preview display in surfaceChanged");
}
}
@Override
public void surfaceDestroyed(SurfaceHolder holder) {
try {
mHolder.addCallback(null);
mCamera.setPreviewCallback(null);
} catch (RuntimeException e) {
// The camera has probably just been released, ignore.
}
}
public void startPreview() {
if (!isPreviewOn && mCamera != null) {
isPreviewOn = true;
mCamera.startPreview();
}
}
public void stopPreview() {
if (isPreviewOn && mCamera != null) {
isPreviewOn = false;
mCamera.stopPreview();
}
}
@Override
public void onPreviewFrame(byte[] data, Camera camera) {
if (audioRecord == null || audioRecord.getRecordingState() != AudioRecord.RECORDSTATE_RECORDING) {
startTime = System.currentTimeMillis();
return;
}
if (RECORD_LENGTH > 0) {
int i = imagesIndex++ % images.length;
yuvImage = images[i];
timestamps[i] = 1000 * (System.currentTimeMillis() - startTime);
}
/* get video data */
if (yuvImage != null && recording) {
((ByteBuffer)yuvImage.image[0].position(0)).put(data);
if (RECORD_LENGTH <= 0) try {
Log.v(LOG_TAG,"Writing Frame");
long t = 1000 * (System.currentTimeMillis() - startTime);
if (t > recorder.getTimestamp()) {
recorder.setTimestamp(t);
}
if(addFilter) {
filter.push(yuvImage);
Frame frame2;
while ((frame2 = filter.pull()) != null) {
recorder.record(frame2, filter.getPixelFormat());
}
} else {
recorder.record(yuvImage);
}
} catch (FFmpegFrameRecorder.Exception | FrameFilter.Exception e) {
Log.v(LOG_TAG,e.getMessage());
e.printStackTrace();
}
}
}
}
@Override
public void onClick(View v) {
if (!recording) {
startRecording();
Log.w(LOG_TAG, "Start Button Pushed");
btnRecorderControl.setText("Stop");
} else {
// This will trigger the audio recording loop to stop and then set isRecorderStart = false;
stopRecording();
Log.w(LOG_TAG, "Stop Button Pushed");
btnRecorderControl.setText("Start");
}
}
}
关于android - 使用前置摄像头录制视频时分别获取视频和音频缓冲区,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/54049275/
我一直在为实时流和静态文件(HTTP 上的 MP3)构建网络广播播放器。我选了Howler.js作为规范化 quirks 的后端的 HTML5 Audio (思考:自动播放、淡入/淡出、进度事件)。
vue移动端input上传视频、音频,供大家参考,具体内容如下 html部分 ?
关闭。这个问题需要更多 focused .它目前不接受答案。 想改进这个问题?更新问题,使其仅关注一个问题 editing this post . 7年前关闭。 Improve this questi
我想在我的程序中访问音频和视频。 MAC里面可以吗? 我们的程序在 Windows 上运行,我使用 directshow 进行音频/视频编程。但我想在 MAC 中开发相同的东西。 有没有像direct
我的应用程序(使用 Flutter 制作,但这应该无关紧要)具有类似于计时器的功能,可以定期(10 秒到 3 分钟)发出滴答声。我在我的 Info.plist 中激活了背景模式 Audio、AirPl
我是 ionic 2 的初学者 我使用了音频文件。 import { Component } from '@angular/core'; import {NavController, Alert
我有一个包含ListView和图片的数据库,我想在每个语音数据中包含它们。我已经尝试过,但是有很多错误。以下是我的java和xml。 数据库.java package com.example.data
我在zend framework 2上建立了一个音乐社交网络。您可以想象它与SoundCloud相同,用户上传歌曲,其他用户播放它们,这些是网站上的基本操作。 我知道将要托管该页面的服务器将需要大量带
我正在尝试在android应用中播放音频,但是在代码中AssetFileDescriptor asset1及其下一行存在错误。这是代码: MediaPlayer mp; @Override prote
我对 WordPress Audio Shortcode有问题。我这样使用它: 但是在前面,在HTML代码中我得到了: document.createElement('audio');
我正在做一项关于降低噪音的滤波技术的实验。我在数据集中的样本是音频文件(.wav),因此,我有:原始录制的音频文件,我将它们与噪声混合,因此变得混合(噪声信号),我将这些噪声信号通过滤波算法传递,输出
一个人会使用哪种类型的神经网络架构将声音映射到其他声音?神经网络擅长学习从序列到其他序列,因此声音增强/生成似乎是它们的一种非常流行的应用(但不幸的是,事实并非如此-我只能找到一个(相当古老的)洋红色
这个让我抓狂: 在专用于此声音播放/录制应用程序的 Vista+ 计算机上,我需要我的应用程序确保(默认)麦克风电平被推到最大。我该怎么做? 我找到了 Core Audio lib ,找到了如何将 I
{ "manifest_version": 2, "name": "Kitten Radio Extension", "description": "Listen while browsi
class Main { WaveFileReader reader; short[] sample; Complex[] tmpComplexArray; publi
我正在使用电话录音软件(android),该软件可以记录2个人在电话中的通话。每个电话的输出是一个音频文件,其中包含来自 call 者和被 call 者的声音。 但是,大多数情况下,运行此软件的电话发
我正在构建一个需要语音激活命令的Web应用程序。我正在使用getUserMedia作为音频输入。 对于语音激活命令,该过程是用户将需要通过记录其语音来“校准”命令。例如,对于“停止”命令,用户将说出“
我正在开发一个Cordova应用程序,并将PouchDB用作数据库,当连接可用时,它将所有信息复制到CouchDB。 我成功存储了简单的文本和图像。 我一直在尝试存储视频和音频,但是没有运气。 我存储
我正在开发web application,我必须在其中使用.MP3的地方使用播放声音,但是会发生问题。 声音为play good in chrome, Firefox,但为safari its not
如何减少音频文件的位深?是否忽略了MSB或LSB?两者混合吗? (旁问:这叫什么?) 最佳答案 TL / DR:将音频曲线高度变量右移至较低位深度 可以将音频视为幅度(Y轴)随时间(X轴)的模拟曲线。
我是一名优秀的程序员,十分优秀!