我的代码如下:
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
extern "C"
{
#include <libavcodec/avcodec.h>
#include <libavformat/avformat.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 StreamContext {
AVCodecContext *dec_ctx;
AVCodecContext *enc_ctx;
} StreamContext;
static StreamContext *stream_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;
}
stream_ctx = (StreamContext *) av_mallocz_array(ifmt_ctx->nb_streams, sizeof(*stream_ctx));
if (!stream_ctx)
return AVERROR(ENOMEM);
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
AVStream *stream = ifmt_ctx->streams[i];
AVCodec *dec = avcodec_find_decoder(stream->codecpar->codec_id);
AVCodecContext *codec_ctx;
if (!dec) {
av_log(NULL, AV_LOG_ERROR, "Failed to find decoder for stream #%u\n", i);
return AVERROR_DECODER_NOT_FOUND;
}
codec_ctx = avcodec_alloc_context3(dec);
if (!codec_ctx) {
av_log(NULL, AV_LOG_ERROR, "Failed to allocate the decoder context for stream #%u\n", i);
return AVERROR(ENOMEM);
}
ret = avcodec_parameters_to_context(codec_ctx, stream->codecpar);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Failed to copy decoder parameters to input decoder context "
"for stream #%u\n", i);
return ret;
}
/* Reencode video & audio and remux subtitles etc. */
if (codec_ctx->codec_type == AVMEDIA_TYPE_VIDEO
|| codec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
if (codec_ctx->codec_type == AVMEDIA_TYPE_VIDEO)
codec_ctx->framerate = av_guess_frame_rate(ifmt_ctx, stream, NULL);
/* Open decoder */
ret = avcodec_open2(codec_ctx, dec, NULL);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Failed to open decoder for stream #%u\n", i);
return ret;
}
}
stream_ctx[i].dec_ctx = codec_ctx;
}
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 = stream_ctx[i].dec_ctx;
//ofmt_ctx->bit_rate = ifmt_ctx->bit_rate;
ofmt_ctx->duration = ifmt_ctx->duration;
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;
}
enc_ctx = avcodec_alloc_context3(encoder);
if (!enc_ctx) {
av_log(NULL, AV_LOG_FATAL, "Failed to allocate the encoder context\n");
return AVERROR(ENOMEM);
}
/* 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->gop_size = dec_ctx->gop_size;
enc_ctx->bit_rate = dec_ctx->bit_rate;
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 = av_inv_q(dec_ctx->framerate);
enc_ctx->framerate = av_guess_frame_rate(ifmt_ctx, in_stream, NULL);
}
else {
enc_ctx->gop_size = dec_ctx->gop_size;
enc_ctx->bit_rate = dec_ctx->bit_rate;
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 };
enc_ctx->time_base.num = 1;
enc_ctx->time_base.den = enc_ctx->sample_rate;
enc_ctx->framerate = av_guess_frame_rate(ifmt_ctx, in_stream, NULL);
}
/* 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;
}
ret = avcodec_parameters_from_context(out_stream->codecpar, enc_ctx);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Failed to copy encoder parameters to output stream #%u\n", i);
return ret;
}
if (ofmt_ctx->oformat->flags & AVFMT_GLOBALHEADER)
enc_ctx->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;
out_stream->time_base = enc_ctx->time_base;
stream_ctx[i].enc_ctx = enc_ctx;
}
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_parameters_copy(out_stream->codecpar, in_stream->codecpar);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Copying parameters for stream #%u failed\n", i);
return ret;
}
out_stream->time_base = in_stream->time_base;
}
}
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;
}
int main(int argc, char **argv)
{
int ret;
AVPacket packet = {0};
packet.data = NULL;
packet.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;
/* 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]->codecpar->codec_type;
av_log(NULL, AV_LOG_DEBUG, "Demuxer gave frame of stream_index %u\n", stream_index);
/* 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);
}
av_write_trailer(ofmt_ctx);
end:
av_packet_unref(&packet);
av_frame_free(&frame);
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
avcodec_free_context(&stream_ctx[i].dec_ctx);
if (ofmt_ctx && ofmt_ctx->nb_streams > i && ofmt_ctx->streams[i] && stream_ctx[i].enc_ctx)
avcodec_free_context(&stream_ctx[i].enc_ctx);
}
av_free(stream_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);
return ret ? 1 : 0;
}
这是使用名为transcoding.c的ffmpeg的官方示例稍加改动的代码
我只读取一个流中的数据包并将其写入另一个流。它工作正常。
然后我添加主要条件。如果它是带有视频帧的数据包,我将对其进行解码,然后编码并写入另一个流。 没有框架的其他操作。
我的加法代码如下:
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 *) = avcodec_encode_video2 ;
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(stream_ctx[stream_index].enc_ctx, &enc_pkt,
filt_frame, got_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,
stream_ctx[stream_index].enc_ctx->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;
av_log(NULL, AV_LOG_INFO, "Pushing decoded frame to filters\n");
while (1) {
av_log(NULL, AV_LOG_INFO, "Pulling filtered frame from filters\n");
ret = encode_write_frame(frame, stream_index, NULL);
if (ret < 0)
break;
break;
}
return ret;
}
int main(int argc, char **argv)
{
int ret;
AVPacket packet = {0};
packet.data = NULL;
packet.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;
/* 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]->codecpar->codec_type;
av_log(NULL, AV_LOG_DEBUG, "Demuxer gave frame of stream_index %u\n",
stream_index);
if (type == AVMEDIA_TYPE_VIDEO)
{
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,
stream_ctx[stream_index].dec_ctx->time_base);
dec_func = avcodec_decode_video2;
ret = dec_func(stream_ctx[stream_index].dec_ctx, 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 = frame->best_effort_timestamp;
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);
}
av_write_trailer(ofmt_ctx);
end:
av_packet_unref(&packet);
av_frame_free(&frame);
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
avcodec_free_context(&stream_ctx[i].dec_ctx);
if (ofmt_ctx && ofmt_ctx->nb_streams > i && ofmt_ctx->streams[i] && stream_ctx[i].enc_ctx)
avcodec_free_context(&stream_ctx[i].enc_ctx);
}
av_free(stream_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);
return ret ? 1 : 0;
}
结果不同。
对于测试我采用了SampleVideo_1280x720_1mb.flv。 它有
文件大小:1.00 MiB 总比特率:1 630 kb / s
在我的解码/编码操作后,结果变为:
文件大小:1.23 MiB 总比特率:2 005 kb / s
我做错了什么?如何控制整体比特率?我想,编码器/解码器有问题,但是什么?
UPD:
我在函数open_input_file
写的时候得到了
if (codec_ctx->codec_type == AVMEDIA_TYPE_VIDEO)
{
codec_ctx->framerate = av_guess_frame_rate(ifmt_ctx, stream, NULL);
}
我得到的东西(更大的尺寸和比特率)。
在这个函数中我写
if (codec_ctx->codec_type == AVMEDIA_TYPE_VIDEO)
{
codec_ctx = ifmt_ctx->streams[i]->codec;
}
我的尺寸和比特率更小。
文件大小:900 KiB 总比特率:1 429 kb / s
但是如何获得原始文件中的确切大小和帧速率?