我尝试从原始H264视频数据创建片段MP4,以便可以在Internet浏览器的播放器中播放它。我的目标是创建实时流式传输系统,在该系统中,媒体服务器会将碎片化的MP4片段发送到浏览器。服务器将缓冲来自RaspberryPi摄像机的输入数据,该摄像机以H264帧的形式发送视频。然后,它将多路复用该视频数据并将其提供给客户端。浏览器将使用Media Source Extensions播放媒体数据(由服务器混合并通过websocket发送)。
出于测试目的,我编写了以下代码(使用我在intenet中找到的许多示例):
使用avcodec的C ++应用程序,它将原始H264视频复用到片段MP4并将其保存到文件中:
#define READBUFSIZE 4096
#define IOBUFSIZE 4096
#define ERRMSGSIZE 128
#include <cstdint>
#include <iostream>
#include <fstream>
#include <string>
#include <vector>
extern "C"
{
#include <libavformat/avformat.h>
#include <libavutil/error.h>
#include <libavutil/opt.h>
}
enum NalType : uint8_t
{
//NALs containing stream metadata
SEQ_PARAM_SET = 0x7,
PIC_PARAM_SET = 0x8
};
std::vector<uint8_t> outputData;
int mediaMuxCallback(void *opaque, uint8_t *buf, int bufSize)
{
outputData.insert(outputData.end(), buf, buf + bufSize);
return bufSize;
}
std::string getAvErrorString(int errNr)
{
char errMsg[ERRMSGSIZE];
av_strerror(errNr, errMsg, ERRMSGSIZE);
return std::string(errMsg);
}
int main(int argc, char **argv)
{
if(argc < 2)
{
std::cout << "Missing file name" << std::endl;
return 1;
}
std::fstream file(argv[1], std::ios::in | std::ios::binary);
if(!file.is_open())
{
std::cout << "Couldn't open file " << argv[1] << std::endl;
return 2;
}
std::vector<uint8_t> inputMediaData;
do
{
char buf[READBUFSIZE];
file.read(buf, READBUFSIZE);
int size = file.gcount();
if(size > 0)
inputMediaData.insert(inputMediaData.end(), buf, buf + size);
} while(!file.eof());
file.close();
//Initialize avcodec
av_register_all();
uint8_t *ioBuffer;
AVCodec *codec = avcodec_find_decoder(AV_CODEC_ID_H264);
AVCodecContext *codecCtxt = avcodec_alloc_context3(codec);
AVCodecParserContext *parserCtxt = av_parser_init(AV_CODEC_ID_H264);
AVOutputFormat *outputFormat = av_guess_format("mp4", nullptr, nullptr);
AVFormatContext *formatCtxt;
AVIOContext *ioCtxt;
AVStream *videoStream;
int res = avformat_alloc_output_context2(&formatCtxt, outputFormat, nullptr, nullptr);
if(res < 0)
{
std::cout << "Couldn't initialize format context; the error was: " << getAvErrorString(res) << std::endl;
return 3;
}
if((videoStream = avformat_new_stream( formatCtxt, avcodec_find_encoder(formatCtxt->oformat->video_codec) )) == nullptr)
{
std::cout << "Couldn't initialize video stream" << std::endl;
return 4;
}
else if(!codec)
{
std::cout << "Couldn't initialize codec" << std::endl;
return 5;
}
else if(codecCtxt == nullptr)
{
std::cout << "Couldn't initialize codec context" << std::endl;
return 6;
}
else if(parserCtxt == nullptr)
{
std::cout << "Couldn't initialize parser context" << std::endl;
return 7;
}
else if((ioBuffer = (uint8_t*)av_malloc(IOBUFSIZE)) == nullptr)
{
std::cout << "Couldn't allocate I/O buffer" << std::endl;
return 8;
}
else if((ioCtxt = avio_alloc_context(ioBuffer, IOBUFSIZE, 1, nullptr, nullptr, mediaMuxCallback, nullptr)) == nullptr)
{
std::cout << "Couldn't initialize I/O context" << std::endl;
return 9;
}
//Set video stream data
videoStream->id = formatCtxt->nb_streams - 1;
videoStream->codec->width = 1280;
videoStream->codec->height = 720;
videoStream->time_base.den = 60; //FPS
videoStream->time_base.num = 1;
videoStream->codec->flags |= CODEC_FLAG_GLOBAL_HEADER;
formatCtxt->pb = ioCtxt;
//Retrieve SPS and PPS for codec extdata
const uint32_t synchMarker = 0x01000000;
unsigned int i = 0;
int spsStart = -1, ppsStart = -1;
uint16_t spsSize = 0, ppsSize = 0;
while(spsSize == 0 || ppsSize == 0)
{
uint32_t *curr = (uint32_t*)(inputMediaData.data() + i);
if(*curr == synchMarker)
{
unsigned int currentNalStart = i;
i += sizeof(uint32_t);
uint8_t nalType = inputMediaData.data()[i] & 0x1F;
if(nalType == SEQ_PARAM_SET)
spsStart = currentNalStart;
else if(nalType == PIC_PARAM_SET)
ppsStart = currentNalStart;
if(spsStart >= 0 && spsSize == 0 && spsStart != i)
spsSize = currentNalStart - spsStart;
else if(ppsStart >= 0 && ppsSize == 0 && ppsStart != i)
ppsSize = currentNalStart - ppsStart;
}
++i;
}
videoStream->codec->extradata = inputMediaData.data() + spsStart;
videoStream->codec->extradata_size = ppsStart + ppsSize;
//Write main header
AVDictionary *options = nullptr;
av_dict_set(&options, "movflags", "frag_custom+empty_moov", 0);
res = avformat_write_header(formatCtxt, &options);
if(res < 0)
{
std::cout << "Couldn't write container main header; the error was: " << getAvErrorString(res) << std::endl;
return 10;
}
//Retrieve frames from input video and wrap them in container
int currentInputIndex = 0;
int framesInSecond = 0;
while(currentInputIndex < inputMediaData.size())
{
uint8_t *frameBuffer;
int frameSize;
res = av_parser_parse2(parserCtxt, codecCtxt, &frameBuffer, &frameSize, inputMediaData.data() + currentInputIndex,
inputMediaData.size() - currentInputIndex, AV_NOPTS_VALUE, AV_NOPTS_VALUE, 0);
if(frameSize == 0) //No more frames while some data still remains (is that even possible?)
{
std::cout << "Some data left unparsed: " << std::to_string(inputMediaData.size() - currentInputIndex) << std::endl;
break;
}
//Prepare packet with video frame to be dumped into container
AVPacket packet;
av_init_packet(&packet);
packet.data = frameBuffer;
packet.size = frameSize;
packet.stream_index = videoStream->index;
currentInputIndex += frameSize;
//Write packet to the video stream
res = av_write_frame(formatCtxt, &packet);
if(res < 0)
{
std::cout << "Couldn't write packet with video frame; the error was: " << getAvErrorString(res) << std::endl;
return 11;
}
if(++framesInSecond == 60) //We want 1 segment per second
{
framesInSecond = 0;
res = av_write_frame(formatCtxt, nullptr); //Flush segment
}
}
res = av_write_frame(formatCtxt, nullptr); //Flush if something has been left
//Write media data in container to file
file.open("my_mp4.mp4", std::ios::out | std::ios::binary);
if(!file.is_open())
{
std::cout << "Couldn't open output file " << std::endl;
return 12;
}
file.write((char*)outputData.data(), outputData.size());
if(file.fail())
{
std::cout << "Couldn't write to file" << std::endl;
return 13;
}
std::cout << "Media file muxed successfully" << std::endl;
return 0;
}
(我对一些值进行了硬编码,例如视频尺寸或帧速率,但正如我所说的,这只是测试代码。)
使用MSE播放我的MP4片段的简单HTML网页
<!DOCTYPE html>
<html>
<head>
<title>Test strumienia</title>
</head>
<body>
<video width="1280" height="720" controls>
</video>
</body>
<script>
var vidElement = document.querySelector('video');
if (window.MediaSource) {
var mediaSource = new MediaSource();
vidElement.src = URL.createObjectURL(mediaSource);
mediaSource.addEventListener('sourceopen', sourceOpen);
} else {
console.log("The Media Source Extensions API is not supported.")
}
function sourceOpen(e) {
URL.revokeObjectURL(vidElement.src);
var mime = 'video/mp4; codecs="avc1.640028"';
var mediaSource = e.target;
var sourceBuffer = mediaSource.addSourceBuffer(mime);
var videoUrl = 'my_mp4.mp4';
fetch(videoUrl)
.then(function(response) {
return response.arrayBuffer();
})
.then(function(arrayBuffer) {
sourceBuffer.addEventListener('updateend', function(e) {
if (!sourceBuffer.updating && mediaSource.readyState === 'open') {
mediaSource.endOfStream();
}
});
sourceBuffer.appendBuffer(arrayBuffer);
});
}
</script>
</html>
我的C ++应用程序生成的输出MP4文件可以在MPC中播放,但不能在我测试过的任何Web浏览器中播放。它也没有任何持续时间(MPC始终显示00:00)。
为了比较我从上述C ++应用程序获得的输出MP4文件,我还使用FFMPEG从具有原始H264流的同一源文件创建片段MP4文件。我使用了以下命令:
ffmpeg -r 60 -i input.h264 -c:v copy -f mp4 -movflags empty_moov+default_base_moof+frag_keyframe test.mp4
我用于测试的每个网络浏览器均可正确播放FFMPEG生成的文件。它还具有正确的持续时间(但是它也具有尾原子,无论如何我的实时流中都不会出现尾原子,并且由于我需要实时流,因此它没有固定的持续时间)。
两个文件的MP4原子看起来非常相似(当然,它们具有相同的avcc部分)。有趣的是(但不确定是否重要),两个文件的NAL格式都与输入文件不同(RPI摄像机生成附件B格式的视频流,而输出的MP4文件包含AVCC格式的NAL……至少是这样)当我比较mdat原子和输入的H264数据时,情况就是这样。
我假设需要为avcodec设置一些字段(或几个字段),以使其产生可被浏览器播放器正确解码和播放的视频流。但是我需要设置哪些字段?也许问题出在其他地方?我没办法了。
编辑1: 按照建议,我使用十六进制编辑器调查了两个MP4文件(由我的应用和FFMPEG工具生成)的二进制内容。我可以确认的内容:
因此,我想我的代码中创建额外数据没有任何问题-即使我仅使用SPS和PPS NAL进行输入,avcodec也会正确处理它。它会自动转换它们,因此不需要我手动进行。尽管如此,我原来的问题仍然存在。
编辑2:我取得了部分成功-我的应用程序生成的MP4现在可以在Firefox中播放。我将此行添加到了代码中(以及其余的流初始化):
videoStream->codec->time_base = videoStream->time_base;
所以现在我的代码这一部分看起来像这样:
//Set video stream data
videoStream->id = formatCtxt->nb_streams - 1;
videoStream->codec->width = 1280;
videoStream->codec->height = 720;
videoStream->time_base.den = 60; //FPS
videoStream->time_base.num = 1;
videoStream->codec->time_base = videoStream->time_base;
videoStream->codec->flags |= CODEC_FLAG_GLOBAL_HEADER;
formatCtxt->pb = ioCtxt;
答案 0 :(得分:2)
我终于找到了解决方案。我的MP4现在可以在Chrome中播放(同时仍可以在其他经过测试的浏览器中播放)。
在Chrome chrome://media-internals/中显示(某种)MSE日志。当我看着那里时,我发现了一些针对测试玩家的警告:
AV_PKT_FLAG_KEY
这让我开始思考,并鼓励为具有关键帧的数据包设置AVPacket
。我在填充 //Check if keyframe field needs to be set
int allowedNalsCount = 3; //In one packet there would be at most three NALs: SPS, PPS and video frame
packet.flags = 0;
for(int i = 0; i < frameSize && allowedNalsCount > 0; ++i)
{
uint32_t *curr = (uint32_t*)(frameBuffer + i);
if(*curr == synchMarker)
{
uint8_t nalType = frameBuffer[i + sizeof(uint32_t)] & 0x1F;
if(nalType == KEYFRAME)
{
std::cout << "Keyframe detected at frame nr " << framesTotal << std::endl;
packet.flags = AV_PKT_FLAG_KEY;
break;
}
else
i += sizeof(uint32_t) + 1; //We parsed this already, no point in doing it again
--allowedNalsCount;
}
}
结构的部分中添加了以下代码:
KEYFRAME
在我的情况下,一个0x5
常量为{{1}}(片IDR)。
答案 1 :(得分:0)
两个文件的MP4原子看起来非常相似(它们具有相同的avcc 部分)
再次检查一下,提供的代码对我有其他提示。
有趣的是(但不确定是否重要) 文件的NAL格式与输入文件的格式不同(RPI相机生成 附件B格式的视频流,而输出MP4文件则包含NAL AVCC格式...或者至少我比较时看起来是这样 输入H264数据的mdat原子)。
非常重要,mp4不能与附件b一起使用。
答案 2 :(得分:0)
您需要使用AVC解码器配置记录(不只是SPS / PPS)填充额外的数据
以下是记录的外观: AVCDCR
答案 3 :(得分:0)
我们可以在[Chrome来源]中找到此说明 (https://chromium.googlesource.com/chromium/src/+/refs/heads/master/media/formats/mp4/mp4_stream_parser.cc#799)“ chrome媒体源代码”:
// Copyright 2014 The Chromium Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.
// Use |analysis.is_keyframe|, if it was actually determined, for logging
// if the analysis mismatches the container's keyframe metadata for
// |frame_buf|.
if (analysis.is_keyframe.has_value() &&
is_keyframe != analysis.is_keyframe.value()) {
LIMITED_MEDIA_LOG(DEBUG, media_log_, num_video_keyframe_mismatches_,
kMaxVideoKeyframeMismatchLogs)
<< "ISO-BMFF container metadata for video frame indicates that the "
"frame is "
<< (is_keyframe ? "" : "not ")
<< "a keyframe, but the video frame contents indicate the "
"opposite.";
// As of September 2018, it appears that all of Edge, Firefox, Safari
// work with content that marks non-avc-keyframes as a keyframe in the
// container. Encoders/muxers/old streams still exist that produce
// all-keyframe mp4 video tracks, though many of the coded frames are
// not keyframes (likely workaround due to the impact on low-latency
// live streams until https://crbug.com/229412 was fixed). We'll trust
// the AVC frame's keyframe-ness over the mp4 container's metadata if
// they mismatch. If other out-of-order codecs in mp4 (e.g. HEVC, DV)
// implement keyframe analysis in their frame_bitstream_converter, we'll
// similarly trust that analysis instead of the mp4.
is_keyframe = analysis.is_keyframe.value();
}
如代码注释所示,chrome对mp4容器的元数据信任AVC帧的关键帧。因此,H264 / HEVC中的nalu类型应该比mp4容器框sdtp和trun描述更为重要。