我想使用ffmpeg实现:读取视频-》opencv处理视频-》存储处理后的视频。
但是opencv和ffmpeg的格式是不同的,opencv主要采用bgr或者hsv格式的,而ffmpeg为了压缩方便主要采用yuv420的帧格式。所以很是不方便。
下面的代码主要是提取ffmpeg的example的muxing.c的代码,为了阅读方便我自己加了注释,方便我自己以后阅读。
代码的作用是实现存储视频。不对的地方还请指正。ffmpeg的版本为2.0版本(我写的时候是最新的版本);
#ifdef __cplusplus
extern "C" {
#endif
#include<libavformat\avformat.h>
#include<libavcodec\avcodec.h>
#include<libswscale\swscale.h>
#include<libavdevice\avdevice.h>
#include<libavfilter\avfilter.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <math.h>
#include <libavutil/opt.h>
#include <libavutil/mathematics.h>
#include <libavformat/avformat.h>
#include <libswscale/swscale.h>
#include <libswresample/swresample.h>
#ifdef __cplusplus
}
#endif
/* 5 seconds stream duration */
#define STREAM_DURATION 200.0//视频流时长。。以秒计数。
#define STREAM_FRAME_RATE 25 /* 25 images/s */
#define STREAM_NB_FRAMES ((int)(STREAM_DURATION * STREAM_FRAME_RATE))
#define STREAM_PIX_FMT AV_PIX_FMT_YUV420P /* default pix_fmt */
static int sws_flags = SWS_BICUBIC;
/* Add an output stream. */
//返回AVStream,并给codec赋值,但此时codec并未打开。
AVStream *add_stream(AVFormatContext *oc, AVCodec **codec,
enum AVCodecID codec_id)
{
AVCodecContext *c;
AVStream *st;
/* find the encoder */
*codec = avcodec_find_encoder(codec_id);//通过codec_id找到编码器。
if (!(*codec)) {
fprintf(stderr, "Could not find encoder for '%s'\n",
avcodec_get_name(codec_id));
exit(1);
}
st = avformat_new_stream(oc, *codec);//When muxing, should be called by the user before avformat_write_header(). 详细得看看如何清理内存。
if (!st) {
fprintf(stderr, "Could not allocate stream\n");
exit(1);
}
st->id = oc->nb_streams-1;//????why?
c = st->codec;//?
switch ((*codec)->type) {
case AVMEDIA_TYPE_AUDIO://音频。
c->sample_fmt = AV_SAMPLE_FMT_FLTP;
c->bit_rate = 64000;//码流
c->sample_rate = 44100;//
c->channels = 2;//双声道。
break;
case AVMEDIA_TYPE_VIDEO://视频。
c->codec_id = codec_id;//编解码器的id
c->bit_rate = 400000;//?????????
/* Resolution must be a multiple of two. */
c->width = 352;//视频的宽高。
c->height = 288;
/* timebase: This is the fundamental unit of time (in seconds) in terms
* of which frame timestamps are represented. For fixed-fps content,
* timebase should be 1/framerate and timestamp increments should be
* identical to 1. */
c->time_base.den = STREAM_FRAME_RATE;//视频的帧率。
c->time_base.num = 1;//
c->gop_size = 12; /* emit one intra frame every twelve frames at most */
c->pix_fmt = STREAM_PIX_FMT;//规定视频编码的方式为YUV420;可以见define定义。
if (c->codec_id == AV_CODEC_ID_MPEG2VIDEO) {
/* just for testing, we also add B frames */
c->max_b_frames = 2;
}
if (c->codec_id == AV_CODEC_ID_MPEG1VIDEO) {
/* Needed to avoid using macroblocks in which some coeffs overflow.
* This does not happen with normal video, it just happens here as
* the motion of the chroma plane does not match the luma plane. */
c->mb_decision = 2;
}
break;
default:
break;
}
/* Some formats want stream headers to be separate. */
if (oc->oformat->flags & AVFMT_GLOBALHEADER)
c->flags |= CODEC_FLAG_GLOBAL_HEADER;
return st;//返回这个函数中产生的AVStream。
}
/**************************************************************/
/* audio output */
static float t, tincr, tincr2;
static uint8_t **src_samples_data;
static int src_samples_linesize;
static int src_nb_samples;
static int max_dst_nb_samples;
uint8_t **dst_samples_data;
int dst_samples_linesize;
int dst_samples_size;
struct SwrContext *swr_ctx = NULL;
static void open_audio(AVFormatContext *oc, AVCodec *codec, AVStream *st)
{
AVCodecContext *c;
int ret;
c = st->codec;
/* open it */
ret = avcodec_open2(c, codec, NULL);//打开解码器。
if (ret < 0) {
//fprintf(stderr, "Could not open audio codec: %s\n", av_err2str(ret));
exit(1);
}
/* init signal generator */
t = 0;
tincr = 2 * M_PI * 110.0 / c->sample_rate;
/* increment frequency by 110 Hz per second */
tincr2 = 2 * M_PI * 110.0 / c->sample_rate / c->sample_rate;
src_nb_samples = c->codec->capabilities & CODEC_CAP_VARIABLE_FRAME_SIZE ?
10000 : c->frame_size;
ret = av_samples_alloc_array_and_samples(&src_samples_data, &src_samples_linesize, c->channels,
src_nb_samples, c->sample_fmt, 0);
if (ret < 0) {
fprintf(stderr, "Could not allocate source samples\n");
exit(1);
}
/* create resampler context */
if (c->sample_fmt != AV_SAMPLE_FMT_S16) {
swr_ctx = swr_alloc();
if (!swr_ctx) {
fprintf(stderr, "Could not allocate resampler context\n");
exit(1);
}
/* set options */
av_opt_set_int (swr_ctx, "in_channel_count", c->channels, 0);
av_opt_set_int (swr_ctx, "in_sample_rate", c->sample_rate, 0);
av_opt_set_sample_fmt(swr_ctx, "in_sample_fmt", AV_SAMPLE_FMT_S16, 0);
av_opt_set_int (swr_ctx, "out_channel_count", c->channels, 0);
av_opt_set_int (swr_ctx, "out_sample_rate", c->sample_rate, 0);
av_opt_set_sample_fmt(swr_ctx, "out_sample_fmt", c->sample_fmt, 0);
/* initialize the resampling context */
if ((ret = swr_init(swr_ctx)) < 0) {
fprintf(stderr, "Failed to initialize the resampling context\n");
exit(1);
}
}
/* compute the number of converted samples: buffering is avoided
* ensuring that the output buffer will contain at least all the
* converted input samples */
max_dst_nb_samples = src_nb_samples;
ret = av_samples_alloc_array_and_samples(&dst_samples_data, &dst_samples_linesize, c->channels,
max_dst_nb_samples, c->sample_fmt, 0);
if (ret < 0) {
fprintf(stderr, "Could not allocate destination samples\n");
exit(1);
}
dst_samples_size = av_samples_get_buffer_size(NULL, c->channels, max_dst_nb_samples,
c->sample_fmt, 0);
}
/* Prepare a 16 bit dummy audio frame of 'frame_size' samples and
* 'nb_channels' channels. */
static void get_audio_frame(int16_t *samples, int frame_size, int nb_channels)
{
int j, i, v;
int16_t *q;
q = samples;
for (j = 0; j < frame_size; j++) {
v = (int)(sin(t) * 10000);
for (i = 0; i < nb_channels; i++)
*q++ = v;
t += tincr;
tincr += tincr2;
}
}
static void write_audio_frame(AVFormatContext *oc, AVStream *st)
{
AVCodecContext *c;
AVPacket pkt = { 0 }; // data and size must be 0;
AVFrame *frame = avcodec_alloc_frame();
int got_packet, ret, dst_nb_samples;
av_init_packet(&pkt);
c = st->codec;
get_audio_frame((int16_t *)src_samples_data[0], src_nb_samples, c->channels);
/* convert samples from native format to destination codec format, using the resampler */
if (swr_ctx) {
/* compute destination number of samples */
dst_nb_samples = av_rescale_rnd(swr_get_delay(swr_ctx, c->sample_rate) + src_nb_samples,
c->sample_rate, c->sample_rate, AV_ROUND_UP);
if (dst_nb_samples > max_dst_nb_samples) {
av_free(dst_samples_data[0]);
ret = av_samples_alloc(dst_samples_data, &dst_samples_linesize, c->channels,
dst_nb_samples, c->sample_fmt, 0);
if (ret < 0)
exit(1);
max_dst_nb_samples = dst_nb_samples;
dst_samples_size = av_samples_get_buffer_size(NULL, c->channels, dst_nb_samples,
c->sample_fmt, 0);
}
/* convert to destination format */
ret = swr_convert(swr_ctx,
dst_samples_data, dst_nb_samples,
(const uint8_t **)src_samples_data, src_nb_samples);
if (ret < 0) {
fprintf(stderr, "Error while converting\n");
exit(1);
}
} else {
dst_samples_data[0] = src_samples_data[0];
dst_nb_samples = src_nb_samples;
}
frame->nb_samples = dst_nb_samples;
avcodec_fill_audio_frame(frame, c->channels, c->sample_fmt,
dst_samples_data[0], dst_samples_size, 0);
ret = avcodec_encode_audio2(c, &pkt, frame, &got_packet);
if (ret < 0) {
//fprintf(stderr, "Error encoding audio frame: %s\n", av_err2str(ret));
exit(1);
}
if (!got_packet)
return;
pkt.stream_index = st->index;
/* Write the compressed frame to the media file. */
ret = av_interleaved_write_frame(oc, &pkt);
if (ret != 0) {
/*fprintf(stderr, "Error while writing audio frame: %s\n",
av_err2str(ret));*/
exit(1);
}
avcodec_free_frame(&frame);
}
static void close_audio(AVFormatContext *oc, AVStream *st)
{
avcodec_close(st->codec);
av_free(src_samples_data[0]);
av_free(dst_samples_data[0]);
}
/**************************************************************/
/* video output */
static AVFrame *frame;
static AVPicture src_picture, dst_picture;
static int frame_count;
/*
作用打开编码器,申请各种内存,包括:frame,src_picture,dst_picture,其中dst_pciture和frame是一回事。
*/
static void open_video(AVFormatContext *oc, AVCodec *codec, AVStream *st)
{
int ret;
AVCodecContext *c = st->codec;//
/* open the codec */
ret = avcodec_open2(c, codec, NULL);//打开编码器。
if (ret < 0) {
//fprintf(stderr, "Could not open video codec: %s\n", av_err2str(ret));
exit(1);
}
/* allocate and init a re-usable frame */
frame = avcodec_alloc_frame();//这是个静态变量。作用:获得内存。
if (!frame) {
fprintf(stderr, "Could not allocate video frame\n");
exit(1);
}
/* Allocate the encoded raw picture. */
ret = avpicture_alloc(&dst_picture, c->pix_fmt, c->width, c->height);//申请一段内存,并给dst_picture指针。
if (ret < 0) {
//fprintf(stderr, "Could not allocate picture: %s\n", av_err2str(ret));
exit(1);
}
/* If the output format is not YUV420P, then a temporary YUV420P
* picture is needed too. It is then converted to the required
* output format. */
if (c->pix_fmt != AV_PIX_FMT_YUV420P) {
ret = avpicture_alloc(&src_picture, AV_PIX_FMT_YUV420P, c->width, c->height);
if (ret < 0) {
/*fprintf(stderr, "Could not allocate temporary picture: %s\n",
av_err2str(ret));*/
exit(1);
}
}
/* copy data and linesize picture pointers to frame */
*((AVPicture *)frame) = dst_picture;
}
/* Prepare a dummy image. */
static void fill_yuv_image(AVPicture *pict, int frame_index,
int width, int height)
{
int x, y, i;
i = frame_index;
/* Y */
for (y = 0; y < height; y++)
for (x = 0; x < width; x++)
pict->data[0][y * pict->linesize[0] + x] = x + y + i * 3;
/* Cb and Cr */
for (y = 0; y < height / 2; y++) {
for (x = 0; x < width / 2; x++) {
pict->data[1][y * pict->linesize[1] + x] = 128 + y + i * 2;
pict->data[2][y * pict->linesize[2] + x] = 64 + x + i * 5;
}
}
}
static void write_video_frame(AVFormatContext *oc, AVStream *st)
{
int ret;
static struct SwsContext *sws_ctx = NULL;//=NULl这是我加的,以适应vs的编译环境。
AVCodecContext *c = st->codec;
if (frame_count >= STREAM_NB_FRAMES) {
/* No more frames to compress. The codec has a latency of a few
* frames if using B-frames, so we get the last frames by
* passing the same picture again. */
} else {
if (c->pix_fmt != AV_PIX_FMT_YUV420P) {//不是默认的YUV420P格式,则进行格式转换。
/* as we only generate a YUV420P picture, we must convert it
* to the codec pixel format if needed */
if (!sws_ctx) {
sws_ctx = sws_getContext(c->width, c->height, AV_PIX_FMT_YUV420P,
c->width, c->height, c->pix_fmt,
sws_flags, NULL, NULL, NULL);
if (!sws_ctx) {
fprintf(stderr,
"Could not initialize the conversion context\n");
exit(1);
}
}
fill_yuv_image(&src_picture, frame_count, c->width, c->height);//向src_picture中填充数据。。
sws_scale(sws_ctx,
(const uint8_t * const *)src_picture.data, src_picture.linesize,
0, c->height, dst_picture.data, dst_picture.linesize);//从src中向dst进行格式转换。
} else {
fill_yuv_image(&dst_picture, frame_count, c->width, c->height);//如果是默认的YUV420P格式,则不进行格式转换。
}
}
if (oc->oformat->flags & AVFMT_RAWPICTURE) {
/* Raw video case - directly store the picture in the packet */
AVPacket pkt;
av_init_packet(&pkt);
pkt.flags |= AV_PKT_FLAG_KEY;//在我试验的rm格式中,未执行这段if语句,所以搞不清这句话的意思。
pkt.stream_index = st->index;
pkt.data = dst_picture.data[0];
pkt.size = sizeof(AVPicture);
ret = av_interleaved_write_frame(oc, &pkt);
} else {
AVPacket pkt = { 0 };
int got_packet;
av_init_packet(&pkt);//好像是必须调用的。
/* encode the image */
ret = avcodec_encode_video2(c, &pkt, frame, &got_packet);//frame指的是全局变量frame。、、从frame中压缩到pkt中。frame== dst_picture的,这是open_video()函数中定义的。
if (ret < 0) {
// fprintf(stderr, "Error encoding video frame: %s\n", av_err2str(ret));
exit(1);
}
/* If size is zero, it means the image was buffered. */
if (!ret && got_packet && pkt.size) {
pkt.stream_index = st->index;
/* Write the compressed frame to the media file. */
ret = av_interleaved_write_frame(oc, &pkt);
} else {
ret = 0;
}
}
if (ret != 0) {
//fprintf(stderr, "Error while writing video frame: %s\n", av_err2str(ret));
exit(1);
}
frame_count++;
}
static void close_video(AVFormatContext *oc, AVStream *st)
{
avcodec_close(st->codec);
av_free(src_picture.data[0]);
av_free(dst_picture.data[0]);
av_free(frame);
}
/**************************************************************/
/* media file output */
int main(int argc, char **argv)
{
const char *filename;
AVOutputFormat *fmt;
AVFormatContext *oc;
AVStream *audio_st, *video_st;
AVCodec *audio_codec, *video_codec;
double audio_time, video_time;
int ret;
/* Initialize libavcodec, and register all codecs and formats. */
av_register_all();//注册所有的解码器,编码器。fillter等。
filename = "hello.rm";//最终产生的文件名字为“hello.avi”
/* allocate the output media context */
avformat_alloc_output_context2(&oc, NULL, NULL, filename);//这个是最重要的函数,因为他给oc赋值了。
if (!oc) {
printf("Could not deduce output format from file extension: using MPEG.\n");
avformat_alloc_output_context2(&oc, NULL, "mpeg", filename);//如果找不到编码器,那就采用默认的mpeg编码。
}
if (!oc) {
return 1;
}
fmt = oc->oformat;
/* Add the audio and video streams using the default format codecs
* and initialize the codecs. */
video_st = NULL;
audio_st = NULL;
if (fmt->video_codec != AV_CODEC_ID_NONE) {
video_st = add_stream(oc, &video_codec, fmt->video_codec);//产生一个ideoStream指针。//这里的ideo_codec的命名不好,容易误解成fmt->video_codec
}
if (fmt->audio_codec != AV_CODEC_ID_NONE) {
audio_st = add_stream(oc, &audio_codec, fmt->audio_codec);//产生一个AVsTream
}
/* Now that all the parameters are set, we can open the audio and
* video codecs and allocate the necessary encode buffers. */
if (video_st)//如果产生AVStream成功了。
open_video(oc, video_codec, video_st);//打开视频Stream。
if (audio_st)
open_audio(oc, audio_codec, audio_st);
av_dump_format(oc, 0, filename, 1);///??????????????????????????????????????
/* open the output file, if needed */
if (!(fmt->flags & AVFMT_NOFILE)) {//这个文件是赋值了的。是可以被ffmpeg打开的。
ret = avio_open(&oc->pb, filename, AVIO_FLAG_WRITE);//以可写的形式打开文件。
if (ret < 0) {
/*fprintf(stderr, "Could not open '%s': %s\n", filename,
av_err2str(ret));*/
return 1;
}
}
/* Write the stream header, if any. */
ret = avformat_write_header(oc, NULL);//写视频文件的文件头,
if (ret < 0) {
/*fprintf(stderr, "Error occurred when opening output file: %s\n",
av_err2str(ret));*/
return 1;
}
if (frame)//这个frame是在open_video函数中赋值的。
frame->pts = 0;//起始的帧为0;
for (;;) {//
/* Compute current audio and video time. */
audio_time = audio_st ? audio_st->pts.val * av_q2d(audio_st->time_base) : 0.0;//似乎是画蛇添足的。。。。我认为可以直接:
//audio_time = audio_st->pts.val*av_q2d(audio_st->time_base);
video_time = video_st ? video_st->pts.val * av_q2d(video_st->time_base) : 0.0;
if ((!audio_st || audio_time >= STREAM_DURATION) &&
(!video_st || video_time >= STREAM_DURATION))//如果超时,或者AVStream为空了,终止for循环。
break;
/* write interleaved audio and video frames */
if (!video_st || (video_st && audio_st && audio_time < video_time)) {
write_audio_frame(oc, audio_st);
} else {
write_video_frame(oc, video_st);
frame->pts += av_rescale_q(1, video_st->codec->time_base, video_st->time_base);
}
}
/* Write the trailer, if any. The trailer must be written before you
* close the CodecContexts open when you wrote the header; otherwise
* av_write_trailer() may try to use memory that was freed on
* av_codec_close(). */
av_write_trailer(oc);
/* Close each codec. */
if (video_st)
close_video(oc, video_st);
if (audio_st)
close_audio(oc, audio_st);
if (!(fmt->flags & AVFMT_NOFILE))
/* Close the output file. */
avio_close(oc->pb);
/* free the stream */
avformat_free_context(oc);
return 0;
}