近日需要做一个视频转码服务器，对我这样一个在该领域的新手来说却是够我折腾一番，在别人的建议下开始研究开源ffmpeg项目，下面是在代码中看到的一 段例子代码，对我的学习非常有帮助。该例子代码包含音频的解码/编码和视频的编码/解码，其中主要用到编解码的libavcodec组件。以下是完整的例 子，代码自身的注释足够清晰了。
/**
* @file
* libavcodec API use example.
*
* Note that libavcodec only handles codecs (mpeg, mpeg4, etc...),
* not file formats (avi, vob, mp4, mov, mkv, mxf, flv, mpegts, mpegps, etc...).
* See library ‘libavformat‘ for the format handling
* @example doc/examples/decoding_encoding.c
*/
#include <math.h>
#include <libavutil/opt.h>
#include <libavcodec/avcodec.h>
#include <libavutil/channel_layout.h>
#include <libavutil/common.h>
#include <libavutil/imgutils.h>
#include <libavutil/mathematics.h>
#include <libavutil/samplefmt.h>
#define INBUF_SIZE 4096
#define AUDIO_INBUF_SIZE 20480
#define AUDIO_REFILL_THRESH 4096
/* check that a given sample format is supported by the encoder */
static int check_sample_fmt(AVCodec *codec, enum AVSampleFormat sample_fmt)
{
const enum AVSampleFormat *p = codec->sample_fmts;
while (*p != AV_SAMPLE_FMT_NONE) {
if (*p == sample_fmt)
return 1;
p++;
}
return 0;
}
/* just pick the highest supported samplerate */
static int select_sample_rate(AVCodec *codec)
{
const int *p;
int best_samplerate = 0;
if (!codec->supported_samplerates)
return 44100;
p = codec->supported_samplerates;
while (*p) {
best_samplerate = FFMAX(*p, best_samplerate);
p++;
}
return best_samplerate;
}
/* select layout with the highest channel count */
static int select_channel_layout(AVCodec *codec)
{
const uint64_t *p;
uint64_t best_ch_layout = 0;
int best_nb_channells = 0;
if (!codec->channel_layouts)
return AV_CH_LAYOUT_STEREO;
p = codec->channel_layouts;
while (*p) {
int nb_channels = av_get_channel_layout_nb_channels(*p);
if (nb_channels > best_nb_channells) {
best_ch_layout = *p;
best_nb_channells = nb_channels;
}
p++;
}
return best_ch_layout;
}
/*
* Audio encoding example
*/
static void audio_encode_example(const char *filename)
{
AVCodec *codec;
AVCodecContext *c= NULL;
AVFrame *frame;
AVPacket pkt;
int i, j, k, ret, got_output;
int buffer_size;
FILE *f;
uint16_t *samples;
float t, tincr;
printf("Encode audio file %s\n", filename);
/* find the MP2 encoder */
codec = avcodec_find_encoder(AV_CODEC_ID_MP2);
if (!codec) {
fprintf(stderr, "Codec not found\n");
exit(1);
}
c = avcodec_alloc_context3(codec);
if (!c) {
fprintf(stderr, "Could not allocate audio codec context\n");
exit(1);
}
/* put sample parameters */
c->bit_rate = 64000;
/* check that the encoder supports s16 pcm input */
c->sample_fmt = AV_SAMPLE_FMT_S16;
if (!check_sample_fmt(codec, c->sample_fmt)) {
fprintf(stderr, "Encoder does not support sample format %s",
av_get_sample_fmt_name(c->sample_fmt));
exit(1);
}
/* select other audio parameters supported by the encoder */
c->sample_rate = select_sample_rate(codec);
c->channel_layout = select_channel_layout(codec);
c->channels = av_get_channel_layout_nb_channels(c->channel_layout);
/* open it */
if (avcodec_open2(c, codec, NULL) < 0) {
fprintf(stderr, "Could not open codec\n");
exit(1);
}
f = fopen(filename, "wb");
if (!f) {
fprintf(stderr, "Could not open %s\n", filename);
exit(1);
}
/* frame containing input raw audio */
frame = avcodec_alloc_frame();
if (!frame) {
fprintf(stderr, "Could not allocate audio frame\n");
exit(1);
}
frame->nb_samples = c->frame_size;
frame->format = c->sample_fmt;
frame->channel_layout = c->channel_layout;
/* the codec gives us the frame size, in samples,
* we calculate the size of the samples buffer in bytes */
buffer_size = av_samples_get_buffer_size(NULL, c->channels, c->frame_size,
c->sample_fmt, 0);
samples = av_malloc(buffer_size);
if (!samples) {
fprintf(stderr, "Could not allocate %d bytes for samples buffer\n",
buffer_size);
exit(1);
}
/* setup the data pointers in the AVFrame */
ret = avcodec_fill_audio_frame(frame, c->channels, c->sample_fmt,
(const uint8_t*)samples, buffer_size, 0);
if (ret < 0) {
fprintf(stderr, "Could not setup audio frame\n");
exit(1);
}
/* encode a single tone sound */
t = 0;
tincr = 2 * M_PI * 440.0 / c->sample_rate;
for(i=0;i<200;i++) {
av_init_packet(&pkt);
pkt.data = NULL; // packet data will be allocated by the encoder
pkt.size = 0;
for (j = 0; j < c->frame_size; j++) {
samples[2*j] = (int)(sin(t) * 10000);
for (k = 1; k < c->channels; k++)
samples[2*j + k] = samples[2*j];
t += tincr;
}
/* encode the samples */
ret = avcodec_encode_audio2(c, &pkt, frame, &got_output);
if (ret < 0) {
fprintf(stderr, "Error encoding audio frame\n");
exit(1);
}
if (got_output) {
fwrite(pkt.data, 1, pkt.size, f);
av_free_packet(&pkt);
}
}
/* get the delayed frames */
for (got_output = 1; got_output; i++) {
ret = avcodec_encode_audio2(c, &pkt, NULL, &got_output);
if (ret < 0) {
fprintf(stderr, "Error encoding frame\n");
exit(1);
}
if (got_output) {
fwrite(pkt.data, 1, pkt.size, f);
av_free_packet(&pkt);
}
}
fclose(f);
av_freep(&samples);
avcodec_free_frame(&frame);
avcodec_close(c);
av_free(c);
}
/*
* Audio decoding.
*/
static void audio_decode_example(const char *outfilename, const char *filename)
{
AVCodec *codec;
AVCodecContext *c= NULL;
int len;
FILE *f, *outfile;
uint8_t inbuf[AUDIO_INBUF_SIZE + FF_INPUT_BUFFER_PADDING_SIZE];
AVPacket avpkt;
AVFrame *decoded_frame = NULL;
av_init_packet(&avpkt);
printf("Decode audio file %s to %s\n", filename, outfilename);
/* find the mpeg audio decoder */
codec = avcodec_find_decoder(AV_CODEC_ID_MP2);
if (!codec) {
fprintf(stderr, "Codec not found\n");
exit(1);
}
c = avcodec_alloc_context3(codec);
if (!c) {
fprintf(stderr, "Could not allocate audio codec context\n");
exit(1);
}
/* open it */
if (avcodec_open2(c, codec, NULL) < 0) {
fprintf(stderr, "Could not open codec\n");
exit(1);
}
f = fopen(filename, "rb");
if (!f) {
fprintf(stderr, "Could not open %s\n", filename);
exit(1);
}
outfile = fopen(outfilename, "wb");
if (!outfile) {
av_free(c);
exit(1);
}
/* decode until eof */
avpkt.data = inbuf;
avpkt.size = fread(inbuf, 1, AUDIO_INBUF_SIZE, f);
while (avpkt.size > 0) {
int got_frame = 0;
if (!decoded_frame) {
if (!(decoded_frame = avcodec_alloc_frame())) {
fprintf(stderr, "Could not allocate audio frame\n");
exit(1);
}
} else
avcodec_get_frame_defaults(decoded_frame);
len = avcodec_decode_audio4(c, decoded_frame, &got_frame, &avpkt);
if (len < 0) {
fprintf(stderr, "Error while decoding\n");
exit(1);
}
if (got_frame) {
/* if a frame has been decoded, output it */
int data_size = av_samples_get_buffer_size(NULL, c->channels,
decoded_frame->nb_samples,
c->sample_fmt, 1);
fwrite(decoded_frame->data[0], 1, data_size, outfile);
}
avpkt.size -= len;
avpkt.data += len;
avpkt.dts =
avpkt.pts = AV_NOPTS_VALUE;
if (avpkt.size < AUDIO_REFILL_THRESH) {
/* Refill the input buffer, to avoid trying to decode
* incomplete frames. Instead of this, one could also use
* a parser, or use a proper container format through
* libavformat. */
memmove(inbuf, avpkt.data, avpkt.size);
avpkt.data = inbuf;
len = fread(avpkt.data + avpkt.size, 1,
AUDIO_INBUF_SIZE - avpkt.size, f);
if (len > 0)
avpkt.size += len;
}
}
fclose(outfile);
fclose(f);
avcodec_close(c);
av_free(c);
avcodec_free_frame(&decoded_frame);
}
/*
* Video encoding example
*/
static void video_encode_example(const char *filename, int codec_id)
{
AVCodec *codec;
AVCodecContext *c= NULL;
int i, ret, x, y, got_output;
FILE *f;
AVFrame *frame;
AVPacket pkt;
uint8_t endcode[] = { 0, 0, 1, 0xb7 };
printf("Encode video file %s\n", filename);
/* find the mpeg1 video encoder */
codec = avcodec_find_encoder(codec_id);
if (!codec) {
fprintf(stderr, "Codec not found\n");
exit(1);
}
c = avcodec_alloc_context3(codec);
if (!c) {
fprintf(stderr, "Could not allocate video codec context\n");
exit(1);
}
/* put sample parameters */
c->bit_rate = 400000;
/* resolution must be a multiple of two */
c->width = 352;
c->height = 288;
/* frames per second */
c->time_base= (AVRational){1,25};
c->gop_size = 10; /* emit one intra frame every ten frames */
c->max_b_frames=1;
c->pix_fmt = AV_PIX_FMT_YUV420P;
if(codec_id == AV_CODEC_ID_H264)
av_opt_set(c->priv_data, "preset", "slow", 0);
/* open it */
if (avcodec_open2(c, codec, NULL) < 0) {
fprintf(stderr, "Could not open codec\n");
exit(1);
}
f = fopen(filename, "wb");
if (!f) {
fprintf(stderr, "Could not open %s\n", filename);
exit(1);
}
frame = avcodec_alloc_frame();
if (!frame) {
fprintf(stderr, "Could not allocate video frame\n");
exit(1);
}
frame->format = c->pix_fmt;
frame->width = c->width;
frame->height = c->height;
/* the image can be allocated by any means and av_image_alloc() is
* just the most convenient way if av_malloc() is to be used */
ret = av_image_alloc(frame->data, frame->linesize, c->width, c->height,
c->pix_fmt, 32);
if (ret < 0) {
fprintf(stderr, "Could not allocate raw picture buffer\n");
exit(1);
}
/* encode 1 second of video */
for(i=0;i<25;i++) {
av_init_packet(&pkt);
pkt.data = NULL; // packet data will be allocated by the encoder
pkt.size = 0;
fflush(stdout);
/* prepare a dummy image */
/* Y */
for(y=0;y<c->height;y++) {
for(x=0;x<c->width;x++) {
frame->data[0][y * frame->linesize[0] + x] = x + y + i * 3;
}
}
/* Cb and Cr */
for(y=0;y<c->height/2;y++) {
for(x=0;x<c->width/2;x++) {
frame->data[1][y * frame->linesize[1] + x] = 128 + y + i * 2;
frame->data[2][y * frame->linesize[2] + x] = 64 + x + i * 5;
}
}
frame->pts = i;
/* encode the image */
ret = avcodec_encode_video2(c, &pkt, frame, &got_output);
if (ret < 0) {
fprintf(stderr, "Error encoding frame\n");
exit(1);
}
if (got_output) {
printf("Write frame %3d (size=%5d)\n", i, pkt.size);
fwrite(pkt.data, 1, pkt.size, f);
av_free_packet(&pkt);
}
}
/* get the delayed frames */
for (got_output = 1; got_output; i++) {
fflush(stdout);
ret = avcodec_encode_video2(c, &pkt, NULL, &got_output);
if (ret < 0) {
fprintf(stderr, "Error encoding frame\n");
exit(1);
}
if (got_output) {
printf("Write frame %3d (size=%5d)\n", i, pkt.size);
fwrite(pkt.data, 1, pkt.size, f);
av_free_packet(&pkt);
}
}
/* add sequence end code to have a real mpeg file */
fwrite(endcode, 1, sizeof(endcode), f);
fclose(f);
avcodec_close(c);
av_free(c);
av_freep(&frame->data[0]);
avcodec_free_frame(&frame);
printf("\n");
}
/*
* Video decoding example
*/
static void pgm_save(unsigned char *buf, int wrap, int xsize, int ysize,
char *filename)
{
FILE *f;
int i;
f=fopen(filename,"w");
fprintf(f,"P5\n%d %d\n%d\n",xsize,ysize,255);
for(i=0;i<ysize;i++)
fwrite(buf + i * wrap,1,xsize,f);
fclose(f);
}
static int decode_write_frame(const char *outfilename, AVCodecContext *avctx,
AVFrame *frame, int *frame_count, AVPacket *pkt, int last)
{
int len, got_frame;
char buf[1024];
len = avcodec_decode_video2(avctx, frame, &got_frame, pkt);
if (len < 0) {
fprintf(stderr, "Error while decoding frame %d\n", *frame_count);
return len;
}
if (got_frame) {
printf("Saving %sframe %3d\n", last ? "last " : "", *frame_count);
fflush(stdout);
/* the picture is allocated by the decoder, no need to free it */
snprintf(buf, sizeof(buf), outfilename, *frame_count);
pgm_save(frame->data[0], frame->linesize[0],
avctx->width, avctx->height, buf);
(*frame_count)++;
}
if (pkt->data) {
pkt->size -= len;
pkt->data += len;
}
return 0;
}
static void video_decode_example(const char *outfilename, const char *filename)
{
AVCodec *codec;
AVCodecContext *c= NULL;
int frame_count;
FILE *f;
AVFrame *frame;
uint8_t inbuf[INBUF_SIZE + FF_INPUT_BUFFER_PADDING_SIZE];
AVPacket avpkt;
av_init_packet(&avpkt);
/* set end of buffer to 0 (this ensures that no overreading happens for damaged mpeg streams) */
memset(inbuf + INBUF_SIZE, 0, FF_INPUT_BUFFER_PADDING_SIZE);
printf("Decode video file %s to %s\n", filename, outfilename);
/* find the mpeg1 video decoder */
codec = avcodec_find_decoder(AV_CODEC_ID_MPEG1VIDEO);
if (!codec) {
fprintf(stderr, "Codec not found\n");
exit(1);
}
c = avcodec_alloc_context3(codec);
if (!c) {
fprintf(stderr, "Could not allocate video codec context\n");
exit(1);
}
if(codec->capabilities&CODEC_CAP_TRUNCATED)
c->flags|= CODEC_FLAG_TRUNCATED; /* we do not send complete frames */
/* For some codecs, such as msmpeg4 and mpeg4, width and height
MUST be initialized there because this information is not
available in the bitstream. */
/* open it */
if (avcodec_open2(c, codec, NULL) < 0) {
fprintf(stderr, "Could not open codec\n");
exit(1);
}
f = fopen(filename, "rb");
if (!f) {
fprintf(stderr, "Could not open %s\n", filename);
exit(1);
}
frame = avcodec_alloc_frame();
if (!frame) {
fprintf(stderr, "Could not allocate video frame\n");
exit(1);
}
frame_count = 0;
for(;;) {
avpkt.size = fread(inbuf, 1, INBUF_SIZE, f);
if (avpkt.size == 0)
break;
/* NOTE1: some codecs are stream based (mpegvideo, mpegaudio)
and this is the only method to use them because you cannot
know the compressed data size before analysing it.
BUT some other codecs (msmpeg4, mpeg4) are inherently frame
based, so you must call them with all the data for one
frame exactly. You must also initialize ‘width‘ and
‘height‘ before initializing them. */
/* NOTE2: some codecs allow the raw parameters (frame size,
sample rate) to be changed at any frame. We handle this, so
you should also take care of it */
/* here, we use a stream based decoder (mpeg1video), so we
feed decoder and see if it could decode a frame */
avpkt.data = inbuf;
while (avpkt.size > 0)
if (decode_write_frame(outfilename, c, frame, &frame_count, &avpkt, 0) < 0)
exit(1);
}
/* some codecs, such as MPEG, transmit the I and P frame with a
latency of one frame. You must do the following to have a
chance to get the last frame of the video */
avpkt.data = NULL;
avpkt.size = 0;
decode_write_frame(outfilename, c, frame, &frame_count, &avpkt, 1);
fclose(f);
avcodec_close(c);
av_free(c);
avcodec_free_frame(&frame);
printf("\n");
}
int main(int argc, char **argv)
{
const char *output_type;
/* register all the codecs */
avcodec_register_all();
if (argc < 2) {
printf("usage: %s output_type\n"
"API example program to decode/encode a media stream with libavcodec.\n"
"This program generates a synthetic stream and encodes it to a file\n"
"named test.h264, test.mp2 or test.mpg depending on output_type.\n"
"The encoded stream is then decoded and written to a raw data output.\n"
"output_type must be choosen between ‘h264‘, ‘mp2‘, ‘mpg‘.\n",
argv[0]);
return 1;
}
output_type = argv[1];
if (!strcmp(output_type, "h264")) {
video_encode_example("test.h264", AV_CODEC_ID_H264);
} else if (!strcmp(output_type, "mp2")) {
audio_encode_example("test.mp2");
audio_decode_example("test.sw", "test.mp2");
} else if (!strcmp(output_type, "mpg")) {
video_encode_example("test.mpg", AV_CODEC_ID_MPEG1VIDEO);
video_decode_example("test%02d.pgm", "test.mpg");
} else {
fprintf(stderr, "Invalid output type ‘%s‘, choose between ‘h264‘, ‘mp2‘, or ‘mpg‘\n",
output_type);
return 1;
}
return 0;
}
基于ffmpeg的简单音视频编解码的例子
时间： 2024-10-10 20:10:33
基于ffmpeg的简单音视频编解码的例子的相关文章
各种音视频编解码学习详解
各种音视频编解码学习详解 媒体业务是网络的主要业务之间.尤其移动互联网业务的兴起,在运营商和应用开发商中,媒体业务份量极重,其中媒体的编解码服务涉及需求分析.应用开发.释放license收费等等.最近因为项目的关系,需要理清媒体的codec,比较搞的是,在豆丁网上看运营商的规范 标准,同一运营商同样的业务在不同文档中不同的要求,而且有些要求就我看来应当是历史的延续,也就是现在已经很少采用了.所以豆丁上看不出所以然,从 wiki上查.中文的wiki信息量有限,很短,而wiki的英文内容内多,删减版
音视频编解码（一）——解码：代码实现
前言:对于从未接触过音视频编解码的同学来说,使用FFmpeg的学习曲线恐怕略显陡峭.本人由于工作需要,正好需要在项目中使用.因此特地将开发过程总结下来.只当提供给有兴趣的同学参考和学习. 由于FFmpeg是使用C语言开发,所有和函数调用都是面向过程的.以我目前的学习经验来说,通常我会把一个功能的代码全部放在main函数中实现.经过测试和修改认为功能正常,再以C++面向对象的方式逐步将代码分解和封装.因此在对本套指南中我也会采用先代码实现再功能封装的步骤. 一.开发前的准备工作 开发工具为VS20
音视频编解码技术的陷阱与出路，一个研发人员的思考
原来做过挺长时间的音视频编解码的东西,该做个总结了.这里就说下关于音视频编码这类工作的得失与取舍,其实主要是舍,有没有道理,权当一听.各位读者自行判断吧. 拿视频编码标准H.264来说,这真是个好事,视频编码标准化之后,兼容问题就“有法可依”了,利于影片.视频等的传播.但是,却给研究人员带来一个大问题.那就是在同样的标准下,各家公司如何竞争的问题.算法一旦标准化,就失去了发挥的灵活性,每个人.每个公司都是做这些东西.同时也成为了实力雄厚的大公司必须争夺的一个技术高地.其它公司如果也想争一下,就基
各种音视频编解码标准
各种音视频编解码标准
FFmpeg音视频编解码实践总结
PS:由于目前开发RTSP服务器 传输模块时用到了h264文件,所以攻了一段时间去实现h264的视频编解码,借用FFmpeg SDK实现了任意文件格式之间的转换,并实现了流媒体实时播放,目前音视频同步需要稍加完善,视频编码代码已成功移植到Visual Stdio平台,如有需要的留下邮箱 以下文档来自FFmpeg工程组(http://www.ffmpeg.com.cn/index.php开发事例) 实现转码一个普通视频文件为视频mpeg4,音频mp3的功能的程序 本程序源引自FFmpeg工程组,实
使用FFmpeg进行音视频编解码
FFmpeg下载地址:http://ffmpeg.org/ 跳转后进入http://ffmpeg.zeranoe.com/builds/,下载Static版本 解压缩后如下图 说明:ffmpeg是下载后的文件包 3.MP4是待转换的MP4文件 打开命令行工工具 输入一下命令 :{classpath}\ffmpeg\bin\ffmpeg.exe -i {classpath}\3.mp4 -acodec libvorbis {classpath}\3.ogg classpath:为路径地址 以上为例
视频编解码的理论和实践2：Ffmpeg视频编解码
近几年,视频编解码技术在理论及应用方面都取得了重大的进展,越来越多的人想要了解编解码技术.因此,网易云信研发工程师为大家进行了归纳梳理,从理论及实践两个方面简单介绍视频编解码技术. 相关阅读推荐 <视频直播关键技术:流畅.拥塞和延时追赶> <视频直播技术详解:直播的推流调度> <音视频通话:小议音频处理与压缩技术> <视频编解码的理论和实践1:基础知识介绍> 1.Ffmpeg介绍 <视频编解码的理论和实践1:基础知识介绍>介绍了视频编码的基础
音视频开发的视频编解码技术
2012年8月,爱立信公司推出了首款H.265[1]编解码器,而在仅仅六个月之后,国际电联(ITU)就正式批准通过了HEVC/H.265标准,标准全称为高效视频编码(High Efficiency Video Coding),相较于之前的H.264标准有了相当大的改善,中国华为公司拥有最多的核心专利,是该标准的主导者.国内拥有领先音视频开发技术的AnyChat解决方案,目前采用的是H.264视频编解码技术,相信不久会紧跟趋势采用H.265视频编解码技术. H.265/HEVC的编码架构大致上和H
转:利用ffmpeg和opencv进行视频的解码播放
引子 OpenCV中有自己的用于处理图片和视频的类 VideoCapture ,可以很方便的读入文件和显示. 现在视频数据流是ffmpeg解码h264文件得到的,由于要依赖该数据源进行相应的后续处理,所以需要将ffmpeg中得到的数据缓存转换成可以被OpenCV处理的Mat类对象. ffmpeg介绍 FFmpeg是一个开源免费跨平台的视频和音频流方案,属于自由软件,采用LGPL或GPL许可证(依据你选择的组件).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