FFmpeg 是一套可以用来记录、转换数字音频、视频,并能将其转化为流的开源计算机程序。采用 LGPL 或 GPL 许可证。它提供了录制、转换以及流化音视频的完整解决方案。它包含了非常先进的音频 / 视频编解码库 libavcodec,为了保证高可移植性和编解码质量,libavcodec 里很多 code 都是从头开发的。
FFmpeg 在 Linux 平台下开发,但它同样也可以在其它操作系统环境中编译运行,包括 Windows、Mac OS X 等。这个项目最早由 Fabrice Bellard 发起,2004 年至 2015 年间由 Michael Niedermayer 主要负责维护。许多 FFmpeg 的开发人员都来自 MPlayer 项目,而且当前 FFmpeg 也是放在 MPlayer 项目组的服务器上。项目的名称来自 MPEG 视频编码标准,前面的 “FF” 代表 “Fast Forward”。
FFmpeg 提供了现成的程序用命令行的方式对视频进行采集。
>ffmpeg.exe -list_devices true -f dshow -i dummy
… …
[dshow @ 007bd020] DirectShow video devices (some may be both video and audio devices)
[dshow @ 007bd020] “USB Web Camera - HD"
[dshow @ 007bd020] Alternative name "@device_pnp_\\?\usb#vid_1bcf&pid_288e&mi_00#7&6c75a67&0&0000#{65e8773d-8f56-11d0-a3b9-00a0c9223196}\global"
[dshow @ 003cd000] DirectShow audio devices
[dshow @ 003cd000] "Microphone (Realtek High Defini"
[dshow @ 003cd000] Alternative name "@device_cm_{33D9A762-90C8-11D0-BD43-00A0C911CE86}\Microphone (Realtek High Defini“
在我的电脑上有两个采集设备,一个是用来采集视频的摄像头,一个是用来采集音频的麦克风 “Microphone (Realtek High Defini ”。
>ffmpeg.exe -f dshow -i video="USB Web Camera - HD" d:\test.h264
Input #0, dshow, from 'video=USB Web Camera - HD': ← 输入设备
Duration: N/A, start: 31491.827000, bitrate: N/A
Stream #0:0: Video: rawvideo (YUY2 / 0x32595559), yuyv422, 640x480, 30 fps, 30 tbr, 10000k tbn, 10000k tbc
Stream mapping:
Stream #0:0 -> #0:0 (rawvideo (native) -> h264 (libx264))
No pixel format specified, yuv422p for H.264 encoding chosen.
[libx264 @ 02658fe0] 264 - core 152 r2851 ba24899 - H.264/MPEG-4 AVC codec ← 使用的视频编码器
Output #0, h264, to 'd:\test.h264': ← 输出文件
Metadata:
encoder : Lavf57.71.100
Stream #0:0: Video: h264 (libx264) ([33][0][0][0] / 0x0021), yuv422p, 640x480, q=-1--1, 30 fps, 10000k tbn, 30 tbc
Metadata:
encoder : Lavc57.89.100 libx264
Side data:
cpb: bitrate max/min/avg: 0/0/0 buffer size: 0 vbv_delay: -1
frame= 330 fps= 28 q=-1.0 Lsize= 2635kB time=00:00:10.89 bitrate=1980.2kbits/s dup=259 drop=0 speed=0.93x
video:2630kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.179305% ← 正在录制的视频信息,会实时变化
FFmpeg 在 Windows 上用的是 DirectShow 输入设备进行采集的,然后经由自己的 h.264 encoder 和 file writer 写到磁盘上。
FFmpeg 还提供了完备的 API 对视频进行采集。下面是使用 FFmpeg 采集并编码视频的流程图。
什么是颜色空间(color space)?
颜色空间(又称:彩色模型、色彩空间、 彩色系统)是对色彩的一种描述方式,定义有很多种,区别在于面向不同的应用背景。例如:
想要了解更多可以参考我的另一篇博文:RGB 和 YUV 格式
为什么要做颜色空间转换?
编码器支持的颜色空间(确切的说是 pixel format,如 yuv420p)是有限的,和采集的图像可能不一致,因此在编码前就需要转换源图像颜色空间到目标图像颜色空间。
FFmpeg 提供了转换的API,主要流程如下:
以下是整个 FFmpeg 采集过程的概要代码,略去各个函数的具体实现和资源释放。
本文中的代码基于 FFmpeg 4.1。
av_dict_set(&cam_options, "video_size", "640x480", 0);
char fps[10] = {0};
_itoa_s(FRAME_RATE, fps, 10);
av_dict_set(&cam_options, "r", fps, 0);
hr = open_cap_device(AVMEDIA_TYPE_VIDEO, &cap_fmt_ctx, &cap_codec_ctx, &cam_options);
hr = open_output_video_file(out_file, cap_codec_ctx, 400 * 1000, FRAME_RATE, &out_fmt_ctx, &enc_ctx);
hr = init_cvt_frame_and_sws(AV_PIX_FMT_YUV420P, cap_codec_ctx, &yuv420p_frame, &yuv420p_buffer, &sws_ctx);
hr = avformat_write_header(out_fmt_ctx, NULL);
while (_kbhit() == 0) {
int finished = 0;
hr = video_transcode(
cap_fmt_ctx, cap_codec_ctx,
out_fmt_ctx, enc_ctx,
0, yuv420p_frame, sws_ctx, &finished, false, true );
if (FAILED(hr) || finished)
break;
}
flush_encoder(out_fmt_ctx, enc_ctx, false, true);
hr = av_write_trailer(out_fmt_ctx);
... ... // free resources
在 Windows 上 FFmpeg 使用 DirectShow 的设备进行采集,这里我们先枚举所有的设备,然后选用第一个成功初始化的设备。
int open_cap_device(
AVMediaType cap_type,
AVFormatContext **cap_fmt_ctx,
AVCodecContext **cap_codec_ctx,
AVDictionary** options = NULL)
{
RETURN_IF_NULL(cap_fmt_ctx);
RETURN_IF_NULL(cap_codec_ctx);
*cap_fmt_ctx = NULL;
*cap_codec_ctx = NULL;
int hr = -1;
std::string cap_device_name;
std::vector<std::wstring> cap_devices;
avdevice_register_all();
CoInitialize(NULL);
AVInputFormat* input_fmt = av_find_input_format("dshow");
GOTO_IF_NULL(input_fmt);
switch (cap_type) {
case AVMEDIA_TYPE_VIDEO:
cap_device_name = "video=";
hr = enum_dshow_vcap_devices(cap_devices);
break;
}
GOTO_IF_FAILED(hr);
cap_device_name += unicodeToUtf8(cap_devices[0].c_str());
hr = avformat_open_input(cap_fmt_ctx, cap_device_name.c_str(), input_fmt, options);
GOTO_IF_FAILED(hr);
hr = avformat_find_stream_info(*cap_fmt_ctx, NULL);
GOTO_IF_FAILED(hr);
for (unsigned int i = 0; i < (*cap_fmt_ctx)->nb_streams; i++) {
AVCodecParameters* codec_par = (*cap_fmt_ctx)->streams[i]->codecpar;
if (codec_par->codec_type == cap_type) {
av_dump_format(*cap_fmt_ctx, i, NULL, 0);
AVCodec* decoder = avcodec_find_decoder(codec_par->codec_id);
GOTO_IF_NULL(decoder);
*cap_codec_ctx = avcodec_alloc_context3(decoder);
GOTO_IF_NULL(*cap_codec_ctx);
/** initialize the stream parameters with demuxer information */
hr = avcodec_parameters_to_context(*cap_codec_ctx, codec_par);
GOTO_LABEL_IF_FAILED(hr, OnErr);
hr = avcodec_open2(*cap_codec_ctx, decoder, NULL);
GOTO_IF_FAILED(hr);
break;
}
}
GOTO_IF_NULL(*cap_codec_ctx);
hr = 0;
RESOURCE_FREE:
CoUninitialize();
return hr;
OnErr:
avformat_free_context(*cap_fmt_ctx);
*cap_fmt_ctx = NULL;
if (NULL != *cap_codec_ctx)
avcodec_free_context(cap_codec_ctx);
goto RESOURCE_FREE;
}
下面是使用 DShow 的 API 对视频采集设备进行枚举。
HRESULT enum_dshow_vcap_devices(std::vector<std::wstring>& devices)
{
return enum_dshow_devices(CLSID_VideoInputDeviceCategory, devices);
}
HRESULT enum_dshow_devices(const IID& deviceCategory, std::vector<std::wstring>& devices)
{
HRESULT hr = E_FAIL;
CComPtr <ICreateDevEnum> pDevEnum =NULL;
CComPtr <IEnumMoniker> pClassEnum = NULL;
CComPtr<IMoniker> pMoniker =NULL;
ULONG cFetched = 0;
hr = CoCreateInstance(CLSID_SystemDeviceEnum, NULL, CLSCTX_INPROC, IID_ICreateDevEnum, (void**)&pDevEnum);
RETURN_IF_FAILED(hr);
hr = pDevEnum->CreateClassEnumerator(deviceCategory, &pClassEnum, 0);
RETURN_IF_FAILED(hr);
// If there are no enumerators for the requested type, then
// CreateClassEnumerator will succeed, but pClassEnum will be NULL.
RETURN_IF_NULL(pClassEnum);
while (S_OK == (pClassEnum->Next(1, &pMoniker, &cFetched))) {
CComPtr<IPropertyBag> pPropertyBag = NULL;
hr = pMoniker->BindToStorage(NULL, NULL, IID_IPropertyBag, (void**)&pPropertyBag);
pMoniker = NULL;
if (FAILED(hr))
continue;
CComVariant friendlyName;
friendlyName.vt = VT_BSTR;
hr = pPropertyBag->Read(L"FriendlyName", &friendlyName, NULL) ;
if (SUCCEEDED(hr)) {
std::wstring strFriendlyName(friendlyName.bstrVal);
devices.push_back(strFriendlyName);
}
}
RETURN_IF_TRUE(devices.empty(), E_FAIL);
return S_OK;
}
打开一个输出文件并初始化视频编码器。
int open_output_video_file(
const char *file_name,
AVCodecContext *in_codec_ctx,
int64_t bit_rate,
int frame_rate,
AVFormatContext **out_fmt_ctx,
AVCodecContext **enc_ctx)
{
int hr = -1;
AVCodecContext *codec_ctx = NULL;
hr = open_output_file(file_name, in_codec_ctx->codec_type, out_fmt_ctx, &codec_ctx);
RETURN_IF_FAILED(hr);
hr = init_video_encoder(in_codec_ctx, bit_rate, frame_rate, *out_fmt_ctx, 0, codec_ctx);
GOTO_LABEL_IF_FAILED(hr, OnErr);
/** Save the encoder context for easier access later. */
*enc_ctx = codec_ctx;
return 0;
OnErr:
avcodec_free_context(&codec_ctx);
avio_closep(&(*out_fmt_ctx)->pb);
avformat_free_context(*out_fmt_ctx);
*out_fmt_ctx = NULL;
*enc_ctx = NULL;
return hr;
}
通过文件后缀名 guess 一个最适合的编码器。
int open_output_file(
const char *file_name,
AVMediaType stream_type,
AVFormatContext **out_fmt_ctx,
AVCodecContext **enc_ctx )
{
RETURN_IF_NULL(file_name);
RETURN_IF_NULL(out_fmt_ctx);
RETURN_IF_NULL(enc_ctx);
int hr = -1;
AVIOContext *output_io_ctx = NULL;
/** Open the output file to write to it. */
hr = avio_open(&output_io_ctx, file_name, AVIO_FLAG_WRITE);
RETURN_IF_FAILED(hr);
/** Create a new format context for the output container format. */
*out_fmt_ctx = avformat_alloc_context();
RETURN_IF_NULL(*out_fmt_ctx);
/** Associate the output file (pointer) with the container format context. */
(*out_fmt_ctx)->pb = output_io_ctx;
/** Guess the desired container format based on the file extension. */
(*out_fmt_ctx)->oformat = av_guess_format(NULL, file_name, NULL);
GOTO_LABEL_IF_NULL((*out_fmt_ctx)->oformat, OnErr);
char*& url = (*out_fmt_ctx)->url;
if (NULL == url)
url = av_strdup(file_name);
/** Find the encoder to be used by its name. */
AVCodecID out_codec_id = AV_CODEC_ID_NONE;
switch (stream_type) {
case AVMEDIA_TYPE_VIDEO:
out_codec_id = (*out_fmt_ctx)->oformat->video_codec;
break;
}
int stream_idx = add_stream_and_alloc_enc(out_codec_id, *out_fmt_ctx, enc_ctx);
GOTO_LABEL_IF_FALSE(stream_idx >= 0, OnErr);
return 0;
OnErr:
avio_closep(&(*out_fmt_ctx)->pb);
avformat_free_context(*out_fmt_ctx);
*out_fmt_ctx = NULL;
*enc_ctx = NULL;
return hr;
}
初始化视频的一些基本参数如:比特率、宽高、帧率、时间戳基准等。
enc_ctx->bit_rate = video_info.bit_rate;
enc_ctx->width = video_info.width;
enc_ctx->height = video_info.height;
enc_ctx->sample_aspect_ratio = video_info.sample_aspect_ratio;
enc_ctx->framerate = video_info.frame_rate;
enc_ctx->time_base = av_inv_q(enc_ctx->framerate);
enc_ctx->gop_size = 18;
enc_ctx->max_b_frames = 3;
enc_ctx->qmin = 10;
enc_ctx->qmax = 51;
enc_ctx->pix_fmt = pix_fmt;
switch (enc_ctx->codec->id) {
case AV_CODEC_ID_H264:
av_opt_set(enc_ctx->priv_data, "preset", "slow", 0);
break;
case AV_CODEC_ID_MPEG1VIDEO:
/* Needed to avoid using macroblocks in which some coeffs overflow. */
enc_ctx->mb_decision = 2;
break;
}
if (out_fmt_ctx->oformat->flags & AVFMT_GLOBALHEADER)
enc_ctx->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;
hr = avcodec_open2(enc_ctx, enc_ctx->codec, NULL);
AVStream* stream = out_fmt_ctx->streams[video_stream_idx];
hr = avcodec_parameters_from_context(stream->codecpar, enc_ctx);
初始化 sw scaler 及 color space converter,以及对应的目标 frame。
int init_cvt_frame_and_sws(
AVPixelFormat dst_fmt,
AVCodecContext *src_codec_ctx,
AVFrame** frame,
uint8_t** buffer,
SwsContext** sws_ctx)
{
int width = src_codec_ctx->width;
int height = src_codec_ctx->height;
*frame = av_frame_alloc();
(*frame)->width = width;
(*frame)->height = height;
(*frame)->format = format;
int num_bytes = av_image_get_buffer_size( format, width, height, 1 );
*buffer = (uint8_t *)av_malloc( num_bytes * sizeof(uint8_t) );
int hr = av_image_fill_arrays((*frame)->data, (*frame)->linesize, *buffer, format, width, height, 1);
RETURN_IF_FAILED(hr);
// Fix me: It shouldn't hard code NV12 as HW decoded format, can be refactored with later init
AVPixelFormat src_pix_fmt = (src_codec_ctx->hw_device_ctx != NULL) ? AV_PIX_FMT_NV12 : src_codec_ctx->pix_fmt;
*sws_ctx = sws_getContext(width, height, src_pix_fmt, width, height, dst_fmt, SWS_BICUBIC, NULL, NULL, NULL);
RETURN_IF_NULL(*sws_ctx);
return 0;
}
解码(Raw 的格式其实不需要) → 色彩空间转换 → 编码 的过程。
const int output_frame_size = enc_ctx->frame_size;
std::vector<AVFrame*> decoded_frames;
while (true) {
hr = decode_av_frame(in_fmt_ctx, dec_ctx, video_index, decoded_frames, finished);
for (size_t dec_frame_idx = 0; dec_frame_idx < decoded_frames.size(); ++dec_frame_idx) {
AVFrame* frame = decoded_frames[dec_frame_idx];
// convert to YUV420P format
int height = sws_scale(sws_ctx, (const uint8_t* const*)frame->data, frame->linesize, 0,
dec_ctx->height, yuv420p_frame->data, yuv420p_frame->linesize);
av_frame_copy_props(yuv420p_frame, frame);
yuv420p_frame->pict_type = AV_PICTURE_TYPE_NONE;
int data_written = 0;
hr = encode_av_frame(yuv420p_frame, out_fmt_ctx, enc_ctx, &data_written, interleaved, init_pts);
if (hr == AVERROR(EAGAIN))
continue;
GOTO_IF_FAILED(hr);
}
if (SUCCEEDED(hr))
break;
}
if (*finished)
flush_encoder(out_fmt_ctx, enc_ctx, interleaved, init_pts);
注意:此处已经抛弃了 legacy 的 avcodec_decode_video2,而是使用 avcodec_send_packet 和 avcodec_receive_frame,具体请参考 官方文档。
init_packet(&input_packet);
while (true) {
hr = av_read_frame(in_fmt_ctx, &input_packet);
if (hr == AVERROR_EOF)
*finished = 1;
else
av_packet_rescale_ts(&input_packet, in_fmt_ctx->streams[input_packet.stream_index]->time_base, in_codec_ctx->time_base);
hr = avcodec_send_packet(in_codec_ctx, *finished ? NULL : &input_packet);
if (SUCCEEDED(hr) || (hr == AVERROR(EAGAIN))) {
while (true) {
frame = av_frame_alloc();
hr = avcodec_receive_frame(in_codec_ctx, frame);
if (SUCCEEDED(hr))
frames.push_back(frame);
else if (hr == AVERROR_EOF) {
*finished = 1;
break;
}
else if (hr == AVERROR(EAGAIN)) // need more packets
break;
}
}
else if (hr == AVERROR_EOF)
*finished = 1;
if (*finished || !frames.empty())
break;
}
亲爱的编码函数。
int encode_av_frame(
AVFrame *frame,
AVFormatContext *out_fmt_ctx,
AVCodecContext *enc_ctx,
int* data_written,
bool interleaved,
bool init_pts)
{
// frame can be NULL which means to flush
RETURN_IF_NULL(out_fmt_ctx);
RETURN_IF_NULL(enc_ctx);
RETURN_IF_NULL(data_written);
*data_written = 0;
int hr = -1;
int stream_idx = 0;
for (unsigned int i = 0; i < out_fmt_ctx->nb_streams; ++i) {
if (out_fmt_ctx->streams[i]->codecpar->codec_type == enc_ctx->codec_type) {
stream_idx = i;
break;
}
}
std::vector<AVPacket*> packets;
AVPacket* output_packet = NULL;
if (init_pts)
frame->pts = g_ttl_v_frames++;
hr = avcodec_send_frame(enc_ctx, frame);
if (SUCCEEDED(hr) || (hr == AVERROR(EAGAIN))) {
while (true) {
/** Packet used for temporary storage. */
output_packet = new AVPacket();
init_packet(output_packet);
hr = avcodec_receive_packet(enc_ctx, output_packet);
if (SUCCEEDED(hr)) {
output_packet->stream_index = stream_idx;
packets.push_back(output_packet);
}
else if (hr == AVERROR(EAGAIN)) // need more input frames
break;
else if (hr == AVERROR_EOF)
break;
else
GOTO_IF_FAILED(hr);
}
}
else if (hr != AVERROR_EOF)
GOTO_IF_FAILED(hr);
for (size_t i = 0; i < packets.size(); ++i) {
// set pts based on stream time base.
AVRational stream_tb = get_stream_time_base(out_fmt_ctx, enc_ctx->codec_type);
AVPacket* packet = packets[i];
switch (enc_ctx->codec_type) {
case AVMEDIA_TYPE_VIDEO:
if (init_pts) {
packet->duration = av_rescale_q(1, enc_ctx->time_base, stream_tb);
packet->pts *= packet->duration;
packet->dts *= packet->duration;
}
else
av_packet_rescale_ts(packet, enc_ctx->time_base, stream_tb);
break;
}
/** Write one frame from the temporary packet to the output file. */
if (interleaved)
hr = av_interleaved_write_frame(out_fmt_ctx, packet);
else
hr = av_write_frame(out_fmt_ctx, packet);
GOTO_IF_FAILED(hr);
*data_written = 1;
}
hr = 0;
RESOURCE_FREE:
// free resources
return hr;
}
终于结束了,最后是擦屁股。
int flush_encoder(
AVFormatContext* format_ctx,
AVCodecContext* codec_ctx,
bool interleaved,
bool init_pts)
{
if (!(codec_ctx->codec->capabilities & AV_CODEC_CAP_DELAY))
return 0;
int data_written = 0;
/** Flush the encoder as it may have delayed frames. */
do {
int hr = encode_av_frame(NULL, format_ctx, codec_ctx, &data_written, interleaved, init_pts);
RETURN_IF_FAILED(hr);
} while (data_written);
return 0;
}
请参考对应的文章。
– EOF –