ffmpeg學習十四:轉碼


轉碼指的是把一種音視頻文件的格式(封裝格式+編碼格式)轉換為另一種音視頻文件的格式。其過程如圖所示:
這里寫圖片描述
從圖中可以得知,轉碼涉及了解封裝,解編碼,編碼,再封裝的過程。這個過程基本涵蓋了之前文章的所有內容。對於一個視頻文件而言,要把它轉為另一種格式,意味着首先要改變它的封裝格式,其次,視頻文件可能包含多個流,比如視頻流,音頻流,字幕流等都需要重新編碼。回顧之前的文章,我們單獨分析了解封裝,封裝,編碼音頻,編碼視頻,解碼視頻的過程,唯獨沒有做解碼音頻的單獨分析,但只要對解碼視頻比較了解,解碼音頻也很容易理解。因此,這篇文章分析的轉碼是之前所有文章的學習的知識的一次綜合運用。
ffmpeg已經為我們提供了轉碼的例程,它是很好的學習教材。其路徑為:doc/examples/transcoding.c

我下載的ffmpeg的版本是2.7版本,這個版本的這個例程能順利編譯,但是執行這個程序的時候,會報如下錯誤:
[libx264 @ 00021bb0]broken ffmpeg default settings detected
[libx264 @ 00021bb0]use an encoding preset (vpre)
解決方法:
參考ffmpeg x264編譯與使用介紹這篇博客,

在avcodec_open函數之間增加如下幾個AVCodecContext 的初始化:
/default settings for x264/
ctx->me_range = 16;
ctx->max_qdiff = 4;
ctx->qmin = 10;
ctx->qmax = 51;
ctx->qcompress = 0.6;

也就是在open_input_file和open_output_file函數的avcodec_open2函數之前,為AVCodecContext的實例做如上的附加配置,這樣本人親測可以解決這個問題。修改過的完整的代碼如下:

#include <libavcodec/avcodec.h>
#include <libavformat/avformat.h>
#include <libavfilter/avfiltergraph.h>
#include <libavfilter/buffersink.h>
#include <libavfilter/buffersrc.h>
#include <libavutil/opt.h>
#include <libavutil/pixdesc.h>

static AVFormatContext *ifmt_ctx;
static AVFormatContext *ofmt_ctx;
typedef struct FilteringContext {
AVFilterContext *buffersink_ctx;
AVFilterContext *buffersrc_ctx;
AVFilterGraph *filter_graph;
} FilteringContext;
static FilteringContext *filter_ctx;

static int open_input_file(const char *filename)
{
int ret;
unsigned int i;

ifmt_ctx = NULL;
if ((ret = avformat_open_input(&ifmt_ctx, filename, NULL, NULL)) < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot open input file\n");
return ret;
}

if ((ret = avformat_find_stream_info(ifmt_ctx, NULL)) < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot find stream information\n");
return ret;
}

for (i = 0; i < ifmt_ctx->nb_streams; i++) {
AVStream *stream;
AVCodecContext *codec_ctx;
stream = ifmt_ctx->streams[i];
codec_ctx = stream->codec;
/* Reencode video & audio and remux subtitles etc. */
if (codec_ctx->codec_type == AVMEDIA_TYPE_VIDEO
|| codec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
/* Open decoder */
ret = avcodec_open2(codec_ctx,
avcodec_find_decoder(codec_ctx->codec_id), NULL);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Failed to open decoder for stream #%u\n", i);
return ret;
}
}
}

av_dump_format(ifmt_ctx, 0, filename, 0);
return 0;
}

static int open_output_file(const char *filename)
{
AVStream *out_stream;
AVStream *in_stream;
AVCodecContext *dec_ctx, *enc_ctx;
AVCodec *encoder;
int ret;
unsigned int i;

ofmt_ctx = NULL;
avformat_alloc_output_context2(&ofmt_ctx, NULL, NULL, filename);
if (!ofmt_ctx) {
av_log(NULL, AV_LOG_ERROR, "Could not create output context\n");
return AVERROR_UNKNOWN;
}


for (i = 0; i < ifmt_ctx->nb_streams; i++) {
out_stream = avformat_new_stream(ofmt_ctx, NULL);
if (!out_stream) {
av_log(NULL, AV_LOG_ERROR, "Failed allocating output stream\n");
return AVERROR_UNKNOWN;
}

in_stream = ifmt_ctx->streams[i];
dec_ctx = in_stream->codec;
enc_ctx = out_stream->codec;

if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO
|| dec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
/* in this example, we choose transcoding to same codec */
encoder = avcodec_find_encoder(dec_ctx->codec_id);
if (!encoder) {
av_log(NULL, AV_LOG_FATAL, "Necessary encoder not found\n");
return AVERROR_INVALIDDATA;
}

/* In this example, we transcode to same properties (picture size,
* sample rate etc.). These properties can be changed for output
* streams easily using filters */

if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) {
enc_ctx->height = dec_ctx->height;
enc_ctx->width = dec_ctx->width;
enc_ctx->sample_aspect_ratio = dec_ctx->sample_aspect_ratio;
/* take first format from list of supported formats */
if (encoder->pix_fmts)
enc_ctx->pix_fmt = encoder->pix_fmts[0];
else
enc_ctx->pix_fmt = dec_ctx->pix_fmt;
/* video time_base can be set to whatever is handy and supported by encoder */
enc_ctx->time_base = dec_ctx->time_base;
} else {
enc_ctx->sample_rate = dec_ctx->sample_rate;
enc_ctx->channel_layout = dec_ctx->channel_layout;
enc_ctx->channels = av_get_channel_layout_nb_channels(enc_ctx->channel_layout);
/* take first format from list of supported formats */
enc_ctx->sample_fmt = encoder->sample_fmts[0];
enc_ctx->time_base = (AVRational){1, enc_ctx->sample_rate};
}

/* Third parameter can be used to pass settings to encoder */
ret = avcodec_open2(enc_ctx, encoder, NULL);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot open video encoder for stream #%u\n", i);
return ret;
}
} else if (dec_ctx->codec_type == AVMEDIA_TYPE_UNKNOWN) {
av_log(NULL, AV_LOG_FATAL, "Elementary stream #%d is of unknown type, cannot proceed\n", i);
return AVERROR_INVALIDDATA;
} else {
/* if this stream must be remuxed */
ret = avcodec_copy_context(ofmt_ctx->streams[i]->codec,
ifmt_ctx->streams[i]->codec);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Copying stream context failed\n");
return ret;
}
}

if (ofmt_ctx->oformat->flags & AVFMT_GLOBALHEADER)
enc_ctx->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;

}
av_dump_format(ofmt_ctx, 0, filename, 1);

if (!(ofmt_ctx->oformat->flags & AVFMT_NOFILE)) {
ret = avio_open(&ofmt_ctx->pb, filename, AVIO_FLAG_WRITE);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Could not open output file '%s'", filename);
return ret;
}
}

/* init muxer, write output file header */
ret = avformat_write_header(ofmt_ctx, NULL);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Error occurred when opening output file\n");
return ret;
}

return 0;
}

static int init_filter(FilteringContext* fctx, AVCodecContext *dec_ctx,
AVCodecContext *enc_ctx, const char *filter_spec)
{
char args[512];
int ret = 0;
AVFilter *buffersrc = NULL;
AVFilter *buffersink = NULL;
AVFilterContext *buffersrc_ctx = NULL;
AVFilterContext *buffersink_ctx = NULL;
AVFilterInOut *outputs = avfilter_inout_alloc();
AVFilterInOut *inputs = avfilter_inout_alloc();
AVFilterGraph *filter_graph = avfilter_graph_alloc();

if (!outputs || !inputs || !filter_graph) {
ret = AVERROR(ENOMEM);
goto end;
}

if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) {
buffersrc = avfilter_get_by_name("buffer");
buffersink = avfilter_get_by_name("buffersink");
if (!buffersrc || !buffersink) {
av_log(NULL, AV_LOG_ERROR, "filtering source or sink element not found\n");
ret = AVERROR_UNKNOWN;
goto end;
}

snprintf(args, sizeof(args),
"video_size=%dx%d:pix_fmt=%d:time_base=%d/%d:pixel_aspect=%d/%d",
dec_ctx->width, dec_ctx->height, dec_ctx->pix_fmt,
dec_ctx->time_base.num, dec_ctx->time_base.den,
dec_ctx->sample_aspect_ratio.num,
dec_ctx->sample_aspect_ratio.den);

ret = avfilter_graph_create_filter(&buffersrc_ctx, buffersrc, "in",
args, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create buffer source\n");
goto end;
}

ret = avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out",
NULL, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create buffer sink\n");
goto end;
}

ret = av_opt_set_bin(buffersink_ctx, "pix_fmts",
(uint8_t*)&enc_ctx->pix_fmt, sizeof(enc_ctx->pix_fmt),
AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output pixel format\n");
goto end;
}
} else if (dec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
buffersrc = avfilter_get_by_name("abuffer");
buffersink = avfilter_get_by_name("abuffersink");
if (!buffersrc || !buffersink) {
av_log(NULL, AV_LOG_ERROR, "filtering source or sink element not found\n");
ret = AVERROR_UNKNOWN;
goto end;
}

if (!dec_ctx->channel_layout)
dec_ctx->channel_layout =
av_get_default_channel_layout(dec_ctx->channels);
snprintf(args, sizeof(args),
"time_base=%d/%d:sample_rate=%d:sample_fmt=%s:channel_layout=0x%"PRIx64,
dec_ctx->time_base.num, dec_ctx->time_base.den, dec_ctx->sample_rate,
av_get_sample_fmt_name(dec_ctx->sample_fmt),
dec_ctx->channel_layout);
ret = avfilter_graph_create_filter(&buffersrc_ctx, buffersrc, "in",
args, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create audio buffer source\n");
goto end;
}

ret = avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out",
NULL, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create audio buffer sink\n");
goto end;
}

ret = av_opt_set_bin(buffersink_ctx, "sample_fmts",
(uint8_t*)&enc_ctx->sample_fmt, sizeof(enc_ctx->sample_fmt),
AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output sample format\n");
goto end;
}

ret = av_opt_set_bin(buffersink_ctx, "channel_layouts",
(uint8_t*)&enc_ctx->channel_layout,
sizeof(enc_ctx->channel_layout), AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output channel layout\n");
goto end;
}

ret = av_opt_set_bin(buffersink_ctx, "sample_rates",
(uint8_t*)&enc_ctx->sample_rate, sizeof(enc_ctx->sample_rate),
AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output sample rate\n");
goto end;
}
} else {
ret = AVERROR_UNKNOWN;
goto end;
}

/* Endpoints for the filter graph. */
outputs->name = av_strdup("in");
outputs->filter_ctx = buffersrc_ctx;
outputs->pad_idx = 0;
outputs->next = NULL;

inputs->name = av_strdup("out");
inputs->filter_ctx = buffersink_ctx;
inputs->pad_idx = 0;
inputs->next = NULL;

if (!outputs->name || !inputs->name) {
ret = AVERROR(ENOMEM);
goto end;
}

if ((ret = avfilter_graph_parse_ptr(filter_graph, filter_spec,
&inputs, &outputs, NULL)) < 0)
goto end;

if ((ret = avfilter_graph_config(filter_graph, NULL)) < 0)
goto end;

/* Fill FilteringContext */
fctx->buffersrc_ctx = buffersrc_ctx;
fctx->buffersink_ctx = buffersink_ctx;
fctx->filter_graph = filter_graph;

end:
avfilter_inout_free(&inputs);
avfilter_inout_free(&outputs);

return ret;
}

static int init_filters(void)
{
const char *filter_spec;
unsigned int i;
int ret;
filter_ctx = av_malloc_array(ifmt_ctx->nb_streams, sizeof(*filter_ctx));
if (!filter_ctx)
return AVERROR(ENOMEM);

for (i = 0; i < ifmt_ctx->nb_streams; i++) {
filter_ctx[i].buffersrc_ctx = NULL;
filter_ctx[i].buffersink_ctx = NULL;
filter_ctx[i].filter_graph = NULL;
if (!(ifmt_ctx->streams[i]->codec->codec_type == AVMEDIA_TYPE_AUDIO
|| ifmt_ctx->streams[i]->codec->codec_type == AVMEDIA_TYPE_VIDEO))
continue;


if (ifmt_ctx->streams[i]->codec->codec_type == AVMEDIA_TYPE_VIDEO)
filter_spec = "null"; /* passthrough (dummy) filter for video */
else
filter_spec = "anull"; /* passthrough (dummy) filter for audio */
ret = init_filter(&filter_ctx[i], ifmt_ctx->streams[i]->codec,
ofmt_ctx->streams[i]->codec, filter_spec);
if (ret)
return ret;
}
return 0;
}

static int encode_write_frame(AVFrame *filt_frame, unsigned int stream_index, int *got_frame) {
int ret;
int got_frame_local;
AVPacket enc_pkt;
int (*enc_func)(AVCodecContext *, AVPacket *, const AVFrame *, int *) =
(ifmt_ctx->streams[stream_index]->codec->codec_type ==
AVMEDIA_TYPE_VIDEO) ? avcodec_encode_video2 : avcodec_encode_audio2;

if (!got_frame)
got_frame = &got_frame_local;

av_log(NULL, AV_LOG_INFO, "Encoding frame\n");
/* encode filtered frame */
enc_pkt.data = NULL;
enc_pkt.size = 0;
av_init_packet(&enc_pkt);
ret = enc_func(ofmt_ctx->streams[stream_index]->codec, &enc_pkt,
filt_frame, got_frame);
av_frame_free(&filt_frame);
if (ret < 0)
return ret;
if (!(*got_frame))
return 0;

/* prepare packet for muxing */
enc_pkt.stream_index = stream_index;
av_packet_rescale_ts(&enc_pkt,
ofmt_ctx->streams[stream_index]->codec->time_base,
ofmt_ctx->streams[stream_index]->time_base);

av_log(NULL, AV_LOG_DEBUG, "Muxing frame\n");
/* mux encoded frame */
ret = av_interleaved_write_frame(ofmt_ctx, &enc_pkt);
return ret;
}

static int filter_encode_write_frame(AVFrame *frame, unsigned int stream_index)
{
int ret;
AVFrame *filt_frame;

av_log(NULL, AV_LOG_INFO, "Pushing decoded frame to filters\n");
/* push the decoded frame into the filtergraph */
ret = av_buffersrc_add_frame_flags(filter_ctx[stream_index].buffersrc_ctx,
frame, 0);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Error while feeding the filtergraph\n");
return ret;
}

/* pull filtered frames from the filtergraph */
while (1) {
filt_frame = av_frame_alloc();
if (!filt_frame) {
ret = AVERROR(ENOMEM);
break;
}
av_log(NULL, AV_LOG_INFO, "Pulling filtered frame from filters\n");
ret = av_buffersink_get_frame(filter_ctx[stream_index].buffersink_ctx,
filt_frame);
if (ret < 0) {
/* if no more frames for output - returns AVERROR(EAGAIN)
* if flushed and no more frames for output - returns AVERROR_EOF
* rewrite retcode to 0 to show it as normal procedure completion
*/

if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
ret = 0;
av_frame_free(&filt_frame);
break;
}

filt_frame->pict_type = AV_PICTURE_TYPE_NONE;
ret = encode_write_frame(filt_frame, stream_index, NULL);
if (ret < 0)
break;
}

return ret;
}

static int flush_encoder(unsigned int stream_index)
{
int ret;
int got_frame;

if (!(ofmt_ctx->streams[stream_index]->codec->codec->capabilities &
AV_CODEC_CAP_DELAY))
return 0;

while (1) {
av_log(NULL, AV_LOG_INFO, "Flushing stream #%u encoder\n", stream_index);
ret = encode_write_frame(NULL, stream_index, &got_frame);
if (ret < 0)
break;
if (!got_frame)
return 0;
}
return ret;
}

int main(int argc, char **argv)
{
int ret;
AVPacket packet = { .data = NULL, .size = 0 };
AVFrame *frame = NULL;
enum AVMediaType type;
unsigned int stream_index;
unsigned int i;
int got_frame;
int (*dec_func)(AVCodecContext *, AVFrame *, int *, const AVPacket *);

if (argc != 3) {
av_log(NULL, AV_LOG_ERROR, "Usage: %s <input file> <output file>\n", argv[0]);
return 1;
}

av_register_all();
avfilter_register_all();

if ((ret = open_input_file(argv[1])) < 0)
goto end;
if ((ret = open_output_file(argv[2])) < 0)
goto end;
if ((ret = init_filters()) < 0)
goto end;

/* read all packets */
while (1) {
if ((ret = av_read_frame(ifmt_ctx, &packet)) < 0)
break;
stream_index = packet.stream_index;
type = ifmt_ctx->streams[packet.stream_index]->codec->codec_type;
av_log(NULL, AV_LOG_DEBUG, "Demuxer gave frame of stream_index %u\n",
stream_index);

if (filter_ctx[stream_index].filter_graph) {
av_log(NULL, AV_LOG_DEBUG, "Going to reencode&filter the frame\n");
frame = av_frame_alloc();
if (!frame) {
ret = AVERROR(ENOMEM);
break;
}
av_packet_rescale_ts(&packet,
ifmt_ctx->streams[stream_index]->time_base,
ifmt_ctx->streams[stream_index]->codec->time_base);
dec_func = (type == AVMEDIA_TYPE_VIDEO) ? avcodec_decode_video2 :
avcodec_decode_audio4;
ret = dec_func(ifmt_ctx->streams[stream_index]->codec, frame,
&got_frame, &packet);
if (ret < 0) {
av_frame_free(&frame);
av_log(NULL, AV_LOG_ERROR, "Decoding failed\n");
break;
}

if (got_frame) {
frame->pts = av_frame_get_best_effort_timestamp(frame);
ret = filter_encode_write_frame(frame, stream_index);
av_frame_free(&frame);
if (ret < 0)
goto end;
} else {
av_frame_free(&frame);
}
} else {
/* remux this frame without reencoding */
av_packet_rescale_ts(&packet,
ifmt_ctx->streams[stream_index]->time_base,
ofmt_ctx->streams[stream_index]->time_base);

ret = av_interleaved_write_frame(ofmt_ctx, &packet);
if (ret < 0)
goto end;
}
av_packet_unref(&packet);
}

/* flush filters and encoders */
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
/* flush filter */
if (!filter_ctx[i].filter_graph)
continue;
ret = filter_encode_write_frame(NULL, i);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Flushing filter failed\n");
goto end;
}

/* flush encoder */
ret = flush_encoder(i);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Flushing encoder failed\n");
goto end;
}
}

av_write_trailer(ofmt_ctx);
end:
av_packet_unref(&packet);
av_frame_free(&frame);
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
avcodec_close(ifmt_ctx->streams[i]->codec);
if (ofmt_ctx && ofmt_ctx->nb_streams > i && ofmt_ctx->streams[i] && ofmt_ctx->streams[i]->codec)
avcodec_close(ofmt_ctx->streams[i]->codec);
if (filter_ctx && filter_ctx[i].filter_graph)
avfilter_graph_free(&filter_ctx[i].filter_graph);
}
av_free(filter_ctx);
avformat_close_input(&ifmt_ctx);
if (ofmt_ctx && !(ofmt_ctx->oformat->flags & AVFMT_NOFILE))
avio_closep(&ofmt_ctx->pb);
avformat_free_context(ofmt_ctx);

if (ret < 0)
av_log(NULL, AV_LOG_ERROR, "Error occurred: %s\n", av_err2str(ret));

return ret ? 1 : 0;
}

轉碼的整個過程可用如下流程圖來概述:
這里寫圖片描述

重要函數的簡要介紹:
open_input_file():打開輸入文件,並初始化相關的結構體。
其中的avformat_open_input()函數可參考 ffmpeg學習五:avformat_open_input函數源碼分析(以mp4文件為例)一文。avformat_find_stream_info()可參考ffmpeg學習七:avformat_find_stream_info函數源碼分析一文。avcodec_open2()函數可參考 ffmpeg學習六:avcodec_open2函數源碼分析一文。
open_output_file():打開輸出文件,並初始化相關的結構體。會寫入格式相關的文件頭部信息
init_filters():初始化AVFilter相關的結構體。可參考ffmpeg學習十二:濾鏡(實現視頻縮放,裁剪,水印等)一文。
av_read_frame():從輸入文件中讀取一個AVPacket。
avcodec_decode_video2():解碼一個視頻AVPacket(存儲H.264等壓縮碼流數據)為AVFrame(存儲YUV等非壓縮的像素數據)。
avcodec_decode_video4():解碼一個音頻AVPacket(存儲MP3等壓縮碼流數據)為AVFrame(存儲PCM采樣數據)。
filter_encode_write_frame():首先會對AVFrame做濾鏡處理,然后編碼一個AVFrame,最后寫入文件。
此外,音頻編碼可參考ffmpeg學習十:將pcm格式的音頻編碼為aac格式一文。
視頻編碼可參考ffmpeg學習八:軟件生成yuv420p視頻並將其編碼為H264格式一文。
封裝可參考 ffmpeg學習十一:封裝音視頻到同一個文件(muxing.c源碼分析)一文。
解封裝與解碼可參考ffmpeg學習四:寫第一個程序-視頻解封裝與解碼一文。


注意!

本站转载的文章为个人学习借鉴使用,本站对版权不负任何法律责任。如果侵犯了您的隐私权益,请联系我们删除。



 
粤ICP备14056181号  © 2014-2020 ITdaan.com