ffmpeg tutorial 6 --音频同步实践

最新推荐文章于 2023-02-14 10:43:28 发布

titer1

最新推荐文章于 2023-02-14 10:43:28 发布

阅读量1.5k

点赞数 1

分类专栏： ffmpeg FFmpeg入门实践与分析

本文链接：https://blog.csdn.net/titer1/article/details/29838753

版权

ffmpeg 同时被 2 个专栏收录

7 篇文章 0 订阅

订阅专栏

FFmpeg入门实践与分析

7 篇文章 4 订阅

订阅专栏

音频同步

初步印象：播放的速度终于均匀了，不过感觉好快

话说，是按照视频同步的方案增加的函数

增加的大函数都是audio做文件名的。期望在下一轮阅读中再次分析 synchronize_audio

比较tutorial5 vs tutorial 6

结构有点乱

代码增加的大致有：

选择同步的时钟接口函数

新添加了 double get_video_clock(VideoState *is)

double get_video_clock(VideoState *is) {

double delta;




delta = (av_gettime() - is->video_current_pts_time) / 1000000.0;

return is->video_current_pts + delta;

}




double get_external_clock(VideoState *is) {

return av_gettime() / 1000000.0;

}

double get_master_clock(VideoState *is) {

if(is->av_sync_type == AV_SYNC_VIDEO_MASTER) {

return get_video_clock(is);

} else if(is->av_sync_type == AV_SYNC_AUDIO_MASTER) {

return get_audio_clock(is);

} else {

return get_external_clock(is);

}

}

重点移植 synchronize_audio

第二是，添加了类似于尚一章同步视频的函数：同步音频，这个函数期望反复阅读
鉴于重要性，分代码展示和代码分析两端

int synchronize_audio(VideoState *is, short *samples,
		      int samples_size, double pts) {
  int n;
  double ref_clock;

  n = 2 * is->audio_st->codec->channels;
  
  if(is->av_sync_type != AV_SYNC_AUDIO_MASTER) {
    double diff, avg_diff;
    int wanted_size, min_size, max_size, nb_samples;
    
    ref_clock = get_master_clock(is);
    diff = get_audio_clock(is) - ref_clock;

    if(diff < AV_NOSYNC_THRESHOLD) {
      // accumulate the diffs
      is->audio_diff_cum = diff + is->audio_diff_avg_coef
	* is->audio_diff_cum;
      if(is->audio_diff_avg_count < AUDIO_DIFF_AVG_NB) {//涉及到一个公式
	is->audio_diff_avg_count++;
      } else {
	avg_diff = is->audio_diff_cum * (1.0 - is->audio_diff_avg_coef);

	if(fabs(avg_diff) >= is->audio_diff_threshold) {
	  wanted_size = samples_size + ((int)(diff * is->audio_st->codec->sample_rate) * n);
	  min_size = samples_size * ((100 - SAMPLE_CORRECTION_PERCENT_MAX) / 100);
	  max_size = samples_size * ((100 + SAMPLE_CORRECTION_PERCENT_MAX) / 100);
	  if(wanted_size < min_size) {
	    wanted_size = min_size;
	  } else if (wanted_size > max_size) {
	    wanted_size = max_size;
	  }

	  if(wanted_size < samples_size) {
	    /* remove samples */
	    samples_size = wanted_size;
	  } else if(wanted_size > samples_size) {
	    uint8_t *samples_end, *q;
	    int nb;


	    /* add samples by copying final sample*/
	    nb = (samples_size - wanted_size);
	    samples_end = (uint8_t *)samples + samples_size - n;
	    q = samples_end + n;
	    while(nb > 0) {
	      memcpy(q, samples_end, n);
	      q += n;
	      nb -= n;
	    }
	    samples_size = wanted_size;
	  }
	}
      }
    } else {
      /* difference is TOO big; reset diff stuff */
      is->audio_diff_avg_count = 0;
      is->audio_diff_cum = 0;
    }
  }
  return samples_size;
}

下面用突出显示展示我认为代码中的难点。

/* Add or subtract samples to get a better sync, return new

audio buffer size */

int synchronize_audio(VideoState *is, short *samples,

int samples_size, double pts) {

int n;

double ref_clock;

n = 2 * is->audio_st->codec->channels;

if(is->av_sync_type != AV_SYNC_AUDIO_MASTER) {

double diff, avg_diff;

int wanted_size, min_size, max_size, nb_samples;

ref_clock = get_master_clock(is);

diff = get_audio_clock(is) - ref_clock;

if(diff < AV_NOSYNC_THRESHOLD) {

// accumulate the diffs

is->audio_diff_cum = diff + is->audio_diff_avg_coef

* is->audio_diff_cum;

if(is->audio_diff_avg_count < AUDIO_DIFF_AVG_NB) {//涉及到一个公式

is->audio_diff_avg_count++;

} else {

avg_diff = is->audio_diff_cum * (1.0 - is->audio_diff_avg_coef);

//这一个函数都是理解的难点

if(fabs(avg_diff) >= is->audio_diff_threshold) {

wanted_size = samples_size + ((int)(diff * is->audio_st->codec->sample_rate) * n);

min_size = samples_size * ((100 - SAMPLE_CORRECTION_PERCENT_MAX) / 100);

max_size = samples_size * ((100 + SAMPLE_CORRECTION_PERCENT_MAX) / 100);

if(wanted_size < min_size) {

wanted_size = min_size;

} else if (wanted_size > max_size) {

wanted_size = max_size;

}

if(wanted_size < samples_size) {

/* remove samples */

samples_size = wanted_size;

} else if(wanted_size > samples_size) {

uint8_t *samples_end, *q;

int nb;

/* add samples by copying final sample*/

nb = (samples_size - wanted_size);

samples_end = (uint8_t *)samples + samples_size - n;

q = samples_end + n;

while(nb > 0) {

memcpy(q, samples_end, n);

q += n;

nb -= n;

}

samples_size = wanted_size;

}

} else {

/* difference is TOO big; reset diff stuff */

is->audio_diff_avg_count = 0;

is->audio_diff_cum = 0;

}

return samples_size;

}

变化最大的函数之audio_callback

void audio_callback(void *userdata, Uint8 *stream, int len) {


VideoState *is = (VideoState *)userdata;

int len1, audio_size;

double pts;




while(len > 0) {

if(is->audio_buf_index >= is->audio_buf_size) {

/* We have already sent all our data; get more */

audio_size = audio_decode_frame(is, is->audio_buf, sizeof(is->audio_buf), &pts);

if(audio_size < 0) {

/* If error, output silence */

is->audio_buf_size = 1024;

memset(is->audio_buf, 0, is->audio_buf_size);

} else {

audio_size = synchronize_audio(is, (int16_t *)is->audio_buf,

audio_size, pts);

is->audio_buf_size = audio_size;

}

is->audio_buf_index = 0;

}

len1 = is->audio_buf_size - is->audio_buf_index;

if(len1 > len)

len1 = len;

memcpy(stream, (uint8_t *)is->audio_buf + is->audio_buf_index, len1);

len -= len1;

stream += len1;

is->audio_buf_index += len1;

}

}

以上是代码，这里附带两个版本的callback函数的对比图：

可以看到终点修改的位置在解码后的处理。尤其注意红色的标示部分

对比视频同步的代码，主要在vedio_thread中。

小结看代码思路

音频的入口，就是从回调函数看起，然后看到同步的函数

对比，视频，视频就是从线程看起，并且结合主函数的刷新定时器来看。

代码实践

以下直接拿log分析：给出一次代码运行过程产生的输出，以后直接对应代码

Function: synchronize_audio(VideoState *, short *, int, double), diff=0.027000000000000000

Function: synchronize_audio(VideoState *, short *, int, double), // accumulate the diffs= 0.027000000000000000

Function: synchronize_audio(VideoState *, short *, int, double), audio_diff_avg_count=0

Function: audio_callback(void *, unsigned char *, int),auido_size= 480

//这是一轮音频get 解码播放 的过程，round 0,相同的过程将会持续到round 18,变化请看下面的注释



//省略其中重复的18个



//这是第20次音频取样播放，20是认为设定的阈值（详细见宏定义）；此时计算avg_diff，【】【】其实就是执行的另外一条代码覆盖；


//并且第一次【注意，这是第一次】进入休整样本值的过程中，后续的代码执行结果：表示我们想让样本变小？？

Function: synchronize_audio(VideoState *, short *, int, double), diff=-13.566370441424555

Function: synchronize_audio(VideoState *, short *, int, double), // accumulate the diffs= -13.573071923920748

Function: synchronize_audio(VideoState *, short *, int, double), avg_diff=-9.2559631349317831e+061, 【when】is->audio_diff_avg_count:20 >10 //

Function: synchronize_audio(VideoState *, short *, int, double), wanted_size < min_size ：-216580 < 0

Function: synchronize_audio(VideoState *, short *, int, double), /* remove samples */

Function: audio_callback(void *, unsigned char *, int),auido_size= 0

初步印象：视频放完了，音频还没有放完。

表格一：audio_size （synchronize_audio返回的值）

比较一下老代码，这个值是多还是少？

Todo:分析一下老版本的值多少？

可否从音频的波特率上分析下, 一共20个，20*480

Line 4: Function: audio_callback(void *, unsigned char *, int),auido_size= 480

Line 8: Function: audio_callback(void *, unsigned char *, int),auido_size= 480

Line 12: Function: audio_callback(void *, unsigned char *, int),auido_size= 480

Line 16: Function: audio_callback(void *, unsigned char *, int),auido_size= 480

Line 20: Function: audio_callback(void *, unsigned char *, int),auido_size= 480

Line 24: Function: audio_callback(void *, unsigned char *, int),auido_size= 480

Line 28: Function: audio_callback(void *, unsigned char *, int),auido_size= 480

Line 32: Function: audio_callback(void *, unsigned char *, int),auido_size= 480

Line 36: Function: audio_callback(void *, unsigned char *, int),auido_size= 480

Line 40: Function: audio_callback(void *, unsigned char *, int),auido_size= 480

Line 44: Function: audio_callback(void *, unsigned char *, int),auido_size= 480

Line 48: Function: audio_callback(void *, unsigned char *, int),auido_size= 480

Line 52: Function: audio_callback(void *, unsigned char *, int),auido_size= 480

Line 56: Function: audio_callback(void *, unsigned char *, int),auido_size= 480

Line 60: Function: audio_callback(void *, unsigned char *, int),auido_size= 480

Line 64: Function: audio_callback(void *, unsigned char *, int),auido_size= 480

Line 68: Function: audio_callback(void *, unsigned char *, int),auido_size= 480

Line 72: Function: audio_callback(void *, unsigned char *, int),auido_size= 480

Line 76: Function: audio_callback(void *, unsigned char *, int),auido_size= 480

Line 80: Function: audio_callback(void *, unsigned char *, int),auido_size= 480

Line 86: Function: audio_callback(void *, unsigned char *, int),auido_size= 0

Line 92: Function: audio_callback(void *, unsigned char *, int),auido_size= 0

Line 98: Function: audio_callback(void *, unsigned char *, int),auido_size= 0

Line 104: Function: audio_callback(void *, unsigned char *, int),auido_size= 0

Line 110: Function: audio_callback(void *, unsigned char *, int),auido_size= 0

Line 116: Function: audio_callback(void *, unsigned char *, int),auido_size= 0

Line 122: Function: audio_callback(void *, unsigned char *, int),auido_size= 0

Line 128: Function: audio_callback(void *, unsigned char *, int),auido_size= 0

Line 134: Function: audio_callback(void *, unsigned char *, int),auido_size= 0

Line 140: Function: audio_callback(void *, unsigned char *, int),auido_size= 0

Line 146: Function: audio_callback(void *, unsigned char *, int),auido_size= 0

附件：完整的log分析记录：

Function: synchronize_audio(VideoState *, short *, int, double), diff=0.027000000000000000

Function: synchronize_audio(VideoState *, short *, int, double), // accumulate the diffs= 0.027000000000000000

Function: synchronize_audio(VideoState *, short *, int, double), audio_diff_avg_count=0