FFmpeg —— 11.示例程序（五）：音视频复用器（muxer——不涉及编码和解码）

清疚 2021-09-24 04:16 331阅读 0赞

参考：[https://blog.csdn.net/leixiaohua1020/article/details/39802913][https_blog.csdn.net_leixiaohua1020_article_details_39802913]

FFmpeg版本：

ffmpeg version git-2020-03-30-8d019db

# 简介 #

本文记录一个基于FFmpeg的视音频复用器（Simplest FFmpeg muxer）。视音频复用器（Muxer）即是将视频压缩数据（例如H.264）和音频压缩数据（例如AAC）合并到一个封装格式数据（例如MKV）中去。如图所示。**在这个过程中并不涉及到编码和解码。**

![20200417215904661.png][]

本文记录的程序将一个H.264编码的视频码流文件和一个MP3编码的音频码流文件，合成为一个MP4封装格式的文件。

# 流程 #

程序的流程如下图所示。从流程图中可以看出，一共初始化了3个AVFormatContext，其中2个用于输入，1个用于输出。3个AVFormatContext初始化之后，通过avcodec\_copy\_context()函数可以将输入视频/音频的参数拷贝至输出视频/音频的AVCodecContext结构体。然后分别调用视频输入流和音频输入流的av\_read\_frame()，从视频输入流中取出视频的AVPacket，音频输入流中取出音频的AVPacket，分别将取出的AVPacket写入到输出文件中即可。其间用到了一个不太常见的函数av\_compare\_ts()，是比较时间戳用的。通过该函数可以决定该写入视频还是音频。  
![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2d1b3l1bmZlaTEyMw_size_16_color_FFFFFF_t_70][]

本文介绍的视音频复用器，输入的视频不一定是H.264裸流文件，音频也不一定是纯音频文件。可以选择两个封装过的视音频文件作为输入。程序会从视频输入文件中“挑”出视频流，音频输入文件中“挑”出音频流，再将“挑选”出来的视音频流复用起来。  
PS1：对于某些封装格式（例如MP4/FLV/MKV等）中的H.264，需要用到名称为“h264\_mp4toannexb”的bitstream filter。  
PS2：对于某些封装格式（例如MP4/FLV/MKV等）中的AAC，需要用到名称为“aac\_adtstoasc”的bitstream filter。

简单介绍一下流程中各个重要函数的意义：

avformat_open_input()：打开输入文件。
    avcodec_copy_context()：赋值AVCodecContext的参数。
    avformat_alloc_output_context2()：初始化输出文件。
    avio_open()：打开输出文件。
    avformat_write_header()：写入文件头。
    av_compare_ts()：比较时间戳，决定写入视频还是写入音频。这个函数相对要少见一些。
    av_read_frame()：从输入文件读取一个AVPacket。
    av_interleaved_write_frame()：写入一个AVPacket到输出文件。
    av_write_trailer()：写入文件尾。

# 程序源码 #

/*
     * 最简单的基于FFmpeg的音视频复用器（不涉及编码和解码）
     *
     * 本程序可以将音频码流和视频码流打包到一种封装格式中
     * 程序中将AAC编码的音频流和H.264编码的视频流打包成MP4格式文件
     *
     */
    
    #include <stdio.h>
    
    #define __STDC_CONSTANT_MACROS
    
    extern "C"
    {
    #include "libavformat/avformat.h"
    #include "libavdevice/avdevice.h"
    }
    
    
    /*
    FIX: H.264 in some container format (FLV, MP4, MKV etc.) need
    "h264_mp4toannexb" bitstream filter (BSF)
      *Add SPS,PPS in front of IDR frame
      *Add start code ("0,0,0,1") in front of NALU
    H.264 in some container (MPEG2TS) don't need this BSF.
    */
    //'1': Use H.264 Bitstream Filter
    #define USE_H264BSF 0
    
    /*
    FIX:AAC in some container format (FLV, MP4, MKV etc.) need
    "aac_adtstoasc" bitstream filter (BSF)
    */
    //'1': Use AAC Bitstream Filter
    #define USE_AACBSF 0
    
    
    int main(int argc, char *argv[])
    {
    	AVFormatContext *ifmtCtxVideo = NULL, *ifmtCtxAudio = NULL, *ofmtCtx = NULL;
    	AVPacket packet;
    
    	int inVideoIndex = -1, inAudioIndex = -1;
    	int outVideoIndex = -1, outAudioIndex = -1;
    	int frameIndex = 0;
    
    	int64_t curPstVideo = 0, curPstAudio = 0;
    
    	int ret = 0;
    	unsigned int i = 0;
    
    	const char *inFilenameVideo = "input.h264";
    	const char *inFilenameAudio = "input.aac";
    	const char *outFilename = "output.mp4";
    
    	//注册设备
    	avdevice_register_all();
    
    	//打开输入视频文件
    	ret = avformat_open_input(&ifmtCtxVideo, inFilenameVideo, 0, 0);
    	if (ret < 0)
    	{
    		printf("can't open input video file\n");
    		goto end;
    	}
    
    	//查找输入流
    	ret = avformat_find_stream_info(ifmtCtxVideo, 0);
    	if (ret < 0)
    	{
    		printf("failed to retrieve input video stream information\n");
    		goto end;
    	}
    
    	//打开输入音频文件
    	ret = avformat_open_input(&ifmtCtxAudio, inFilenameAudio, 0, 0);
    	if (ret < 0)
    	{
    		printf("can't open input audio file\n");
    		goto end;
    	}
    
    	//查找输入流
    	ret = avformat_find_stream_info(ifmtCtxAudio, 0);
    	if (ret < 0)
    	{
    		printf("failed to retrieve input audio stream information\n");
    		goto end;
    	}
    
    	printf("===========Input Information==========\n");
    	av_dump_format(ifmtCtxVideo, 0, inFilenameVideo, 0);
    	av_dump_format(ifmtCtxAudio, 0, inFilenameAudio, 0);
    	printf("======================================\n");
    
    	//新建输出上下文
    	avformat_alloc_output_context2(&ofmtCtx, NULL, NULL, outFilename);
    	if (!ofmtCtx)
    	{
    		printf("can't create output context\n");
    		goto end;
    	}
    
    	//视频输入流
    	for (i = 0; i < ifmtCtxVideo->nb_streams; ++i)
    	{
    		if (ifmtCtxVideo->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_VIDEO)
    		{
    			AVStream *inStream = ifmtCtxVideo->streams[i];
    			AVStream *outStream = avformat_new_stream(ofmtCtx, NULL);
    			inVideoIndex = i;
    
    			if (!outStream)
    			{
    				printf("failed to allocate output stream\n");
    				goto end;
    			}
    
    			outVideoIndex = outStream->index;
    
    			if (avcodec_parameters_copy(outStream->codecpar, inStream->codecpar) < 0)
    			{
    				printf("faild to copy context from input to output stream");
    				goto end;
    			}
    
    			outStream->codecpar->codec_tag = 0;
    
    			break;
    		}
    	}
    
    	//音频输入流
    	for (i = 0; i < ifmtCtxAudio->nb_streams; ++i)
    	{
    		if (ifmtCtxAudio->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_AUDIO)
    		{
    			AVStream *inStream = ifmtCtxAudio->streams[i];
    			AVStream *outStream = avformat_new_stream(ofmtCtx, NULL);
    			inAudioIndex = i;
    
    			if (!outStream)
    			{
    				printf("failed to allocate output stream\n");
    				goto end;
    			}
    
    			outAudioIndex = outStream->index;
    
    			if (avcodec_parameters_copy(outStream->codecpar, inStream->codecpar) < 0)
    			{
    				printf("faild to copy context from input to output stream");
    				goto end;
    			}
    
    			outStream->codecpar->codec_tag = 0;
    
    			break;
    		}
    	}
    
    	printf("==========Output Information==========\n");
    	av_dump_format(ofmtCtx, 0, outFilename, 1);
    	printf("======================================\n");
    
    	//打开输入文件
    	if (!(ofmtCtx->oformat->flags & AVFMT_NOFILE))
    	{
    		if (avio_open(&ofmtCtx->pb, outFilename, AVIO_FLAG_WRITE) < 0)
    		{
    			printf("can't open out file\n");
    			goto end;
    		}
    	}
    
    	//写文件头
    	if (avformat_write_header(ofmtCtx, NULL) < 0)
    	{
    		printf("Error occurred when opening output file\n");
    		goto end;
    	}
    
    
    #if USE_H264BSF
    	AVBitStreamFilterContext* h264bsfc =  av_bitstream_filter_init("h264_mp4toannexb");
    #endif
    #if USE_AACBSF
    	AVBitStreamFilterContext* aacbsfc =  av_bitstream_filter_init("aac_adtstoasc");
    #endif
    	while (1)
    	{
    		AVFormatContext *ifmtCtx = NULL;
    		AVStream *inStream, *outStream;
    		int streamIndex = 0;
    
    		if (av_compare_ts(curPstVideo, ifmtCtxVideo->streams[inVideoIndex]->time_base, curPstAudio, ifmtCtxAudio->streams[inAudioIndex]->time_base) < 0)
    		{
    			ifmtCtx = ifmtCtxVideo;
    			streamIndex = outVideoIndex;
    
    			if (av_read_frame(ifmtCtx, &packet) >= 0)
    			{
    				do
    				{
    					inStream = ifmtCtx->streams[packet.stream_index];
    					outStream = ofmtCtx->streams[streamIndex];
    
    					if (packet.stream_index == inVideoIndex)
    					{
    						//Fix: No PTS(Example: Raw H.264
    						//Simple Write PTS
    						if (packet.pts == AV_NOPTS_VALUE)
    						{
    							//write PTS
    							AVRational timeBase1 = inStream->time_base;
    							//Duration between 2 frames
    							int64_t calcDuration = (double)AV_TIME_BASE/av_q2d(inStream->r_frame_rate);
    							//Parameters
    							packet.pts = (double)(frameIndex*calcDuration)/(double)(av_q2d(timeBase1)*AV_TIME_BASE);
    							packet.dts = packet.pts;
    							packet.duration = (double)calcDuration/(double)(av_q2d(timeBase1)*AV_TIME_BASE);
    							frameIndex++;
    						}
    
    						curPstVideo = packet.pts;
    						break;
    					}
    				}while(av_read_frame(ifmtCtx, &packet) >= 0);
    			}
    			else
    			{
    				break;
    			}
    		}
    		else
    		{
    			ifmtCtx = ifmtCtxAudio;
    			streamIndex = outAudioIndex;
    
    			if (av_read_frame(ifmtCtx, &packet) >= 0)
    			{
    				do
    				{
    					inStream = ifmtCtx->streams[packet.stream_index];
    					outStream = ofmtCtx->streams[streamIndex];
    
    					if (packet.stream_index == inAudioIndex)
    					{
    						//Fix: No PTS(Example: Raw H.264
    						//Simple Write PTS
    						if (packet.pts == AV_NOPTS_VALUE)
    						{
    							//write PTS
    							AVRational timeBase1 = inStream->time_base;
    							//Duration between 2 frames
    							int64_t calcDuration = (double)AV_TIME_BASE/av_q2d(inStream->r_frame_rate);
    							//Parameters
    							packet.pts = (double)(frameIndex*calcDuration)/(double)(av_q2d(timeBase1)*AV_TIME_BASE);
    							packet.dts = packet.pts;
    							packet.duration = (double)calcDuration/(double)(av_q2d(timeBase1)*AV_TIME_BASE);
    							frameIndex++;
    						}
    
    						curPstAudio = packet.pts;
    						break;
    					}
    				}while(av_read_frame(ifmtCtx, &packet) >= 0);
    			}
    			else
    			{
    				break;
    			}
    		}
    
    		//FIX:Bitstream Filter
    #if USE_H264BSF
    		av_bitstream_filter_filter(h264bsfc, inStream->codec, NULL, &packet.data, &packet.size, packet.data, packet.size, 0);
    #endif
    #if USE_AACBSF
    		av_bitstream_filter_filter(aacbsfc, outStream->codec, NULL, &packet.data, &packet.size, packet.data, packet.size, 0);
    #endif
    
    		//Convert PTS/DTS
    		packet.pts = av_rescale_q_rnd(packet.pts, inStream->time_base, outStream->time_base, (AVRounding)(AV_ROUND_NEAR_INF|AV_ROUND_PASS_MINMAX));
    		packet.dts = av_rescale_q_rnd(packet.dts, inStream->time_base, outStream->time_base, (AVRounding)(AV_ROUND_NEAR_INF|AV_ROUND_PASS_MINMAX));
    		packet.duration = av_rescale_q(packet.duration, inStream->time_base, outStream->time_base);
    		packet.pos = -1;
    		packet.stream_index = streamIndex;
    
    		//write
    		if (av_interleaved_write_frame(ofmtCtx, &packet) < 0)
    		{
    			printf("error muxing packet");
    			break;
    		}
    
    		av_packet_unref(&packet);
    	}
    
    	//Write file trailer
    	av_write_trailer(ofmtCtx);
    
    #if USE_H264BSF
    	av_bitstream_filter_close(h264bsfc);
    #endif
    #if USE_AACBSF
    	av_bitstream_filter_close(aacbsfc);
    #endif
    
    end:
    	avformat_close_input(&ifmtCtxVideo);
    	avformat_close_input(&ifmtCtxAudio);
    	if (ofmtCtx && !(ofmtCtx->oformat->flags & AVFMT_NOFILE))
    		avio_close(ofmtCtx->pb);
    
    	avformat_free_context(ofmtCtx);
    
    	return 0;
    }

[https_blog.csdn.net_leixiaohua1020_article_details_39802913]: https://blog.csdn.net/leixiaohua1020/article/details/39802913
[20200417215904661.png]: /images/20210923/423bc8e1fcb44d8e92931d87b8e981d0.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2d1b3l1bmZlaTEyMw_size_16_color_FFFFFF_t_70]: /images/20210923/61a027aae34d4ac9b01f221223af89b7.png