ffmpeg解码视频
目录
一、前言
二、ffmpeg解码API介绍
三、ffmpeg解码示例
四、ffmpeg解码框架设计
《ffmpeg解码H264/H265为yuv代码实现》链接：
https://edu.csdn.net/learn/38258/606144?spm=1003.2001.3001.4157
一、前言
当下音视频开发中解码视频的方案有很多，比如GPU解码器、CPU解码等。其中CPU解码通常使用纯软件的方法对视频解码。ffmpeg是最受欢迎的一款开源解码库。ffmpeg不仅仅支持视频解码还支持视频的编码、以及音频的编解码、同时还支持图像滤波处理以及音视频文件的转封装等。 ffmpeg github路径：GitHub - FFmpeg/FFmpeg: Mirror of https://git.ffmpeg.org/ffmpeg.git在本文中重点介绍如何使用ffmpeg解码H264/H265视频，并输出YUV420的格式。
二、ffmpeg解码API介绍
1、AVCodec *avcodec_find_decoder(enum AVCodecID id);
该函数用于查找一个解码器，并返回解码器。输入参数id为解码器的枚举值，AVCodecID中定义了上百中编解码器ID。H264和H265的ID值如下。
enum AVCodecID {
......
AV_CODEC_ID_H264,
......
AV_CODEC_ID_HEVC,
#define AV_CODEC_ID_H265 AV_CODEC_ID_HEVC
......
};返回值为AVCodec 类型的指针。AVCodec为解码器属性的结构体，定义如下。
/**
* AVCodec.
*/
typedef struct AVCodec {
/**
* Name of the codec implementation.
* The name is globally unique among encoders and among decoders (but an
* encoder and a decoder can share the same name).
* This is the primary way to find a codec from the user perspective.
*/
const char *name;
/**
* Descriptive name for the codec, meant to be more human readable than name.
* You should use the NULL_IF_CONFIG_SMALL() macro to define it.
*/
const char *long_name;
enum AVMediaType type;
enum AVCodecID id;
/**
* Codec capabilities.
* see AV_CODEC_CAP_*
*/
int capabilities;
uint8_t max_lowres; ///< maximum value for lowres supported by the decoder
const AVRational *supported_framerates; ///< array of supported framerates, or NULL if any, array is terminated by {0,0}
const enum AVPixelFormat *pix_fmts; ///< array of supported pixel formats, or NULL if unknown, array is terminated by -1
const int *supported_samplerates; ///< array of supported audio samplerates, or NULL if unknown, array is terminated by 0
const enum AVSampleFormat *sample_fmts; ///< array of supported sample formats, or NULL if unknown, array is terminated by -1
#if FF_API_OLD_CHANNEL_LAYOUT
/**
* @deprecated use ch_layouts instead
*/
attribute_deprecated
const uint64_t *channel_layouts; ///< array of support channel layouts, or NULL if unknown. array is terminated by 0
#endif
const AVClass *priv_class; ///< AVClass for the private context
const AVProfile *profiles; ///< array of recognized profiles, or NULL if unknown, array is terminated by {FF_PROFILE_UNKNOWN}
/**
* Group name of the codec implementation.
* This is a short symbolic name of the wrapper backing this codec. A
* wrapper uses some kind of external implementation for the codec, such
* as an external library, or a codec implementation provided by the OS or
* the hardware.
* If this field is NULL, this is a builtin, libavcodec native codec.
* If non-NULL, this will be the suffix in AVCodec.name in most cases
* (usually AVCodec.name will be of the form "_").
*/
const char *wrapper_name;
/**
* Array of supported channel layouts, terminated with a zeroed layout.
*/
const AVChannelLayout *ch_layouts;
} AVCodec; 2、AVCodecContext *avcodec_alloc_context3(const AVCodec *codec);
该函数用户为解码器分配上下文内存，返回解码器上下文参数。输入codec参数为解码器，即avcodec_find_decoder函数返回值。返回值为上下文AVCodecContext的指针。AVCodecContext这个结构体在avcodec.h中定义，由于结构体的成员定义太多这里就不在展示。
3、int avcodec_open2(AVCodecContext *avctx, const AVCodec *codec, AVDictionary **options);
打开解码器。avctx参数为解码器的上下文参数变量，即avcodec_alloc_context3函数返回值；codec参数为编码器参数指针，即avcodec_find_decoder函数返回值；options参数为解码器的配置参数，该值通常设置为空，即不配置参数采用解码器默认设置。
4、int avcodec_send_packet(AVCodecContext *avctx, const AVPacket *avpkt);
还函数用于发送待解码的H264/H265编码数据到解码器中。参数avctx为码器上下文参数即avcodec_alloc_context3函数返回值。avpkt参数为输入的带解码的数据。avpkt为AVPacket类型的参数；AVPacket结构体的定义如下。主要包含视频码流数据地址uint8_t *data;视频码流大小 int size;视频码流的时间戳int64_t pts。
typedef struct AVPacket {
/**
* A reference to the reference-counted buffer where the packet data is
* stored.
* May be NULL, then the packet data is not reference-counted.
*/
AVBufferRef *buf;
/**
* Presentation timestamp in AVStream->time_base units; the time at which
* the decompressed packet will be presented to the user.
* Can be AV_NOPTS_VALUE if it is not stored in the file.
* pts MUST be larger or equal to dts as presentation cannot happen before
* decompression, unless one wants to view hex dumps. Some formats misuse
* the terms dts and pts/cts to mean something different. Such timestamps
* must be converted to true pts/dts before they are stored in AVPacket.
*/
int64_t pts;
/**
* Decompression timestamp in AVStream->time_base units; the time at which
* the packet is decompressed.
* Can be AV_NOPTS_VALUE if it is not stored in the file.
*/
int64_t dts;
uint8_t *data;
int size;
int stream_index;
/**
* A combination of AV_PKT_FLAG values
*/
int flags;
/**
* Additional packet data that can be provided by the container.
* Packet can contain several types of side information.
*/
AVPacketSideData *side_data;
int side_data_elems;
/**
* Duration of this packet in AVStream->time_base units, 0 if unknown.
* Equals next_pts - this_pts in presentation order.
*/
int64_t duration;
int64_t pos; ///< byte position in stream, -1 if unknown
/**
* for some private data of the user
*/
void *opaque;
/**
* AVBufferRef for free use by the API user. FFmpeg will never check the
* contents of the buffer ref. FFmpeg calls av_buffer_unref() on it when
* the packet is unreferenced. av_packet_copy_props() calls create a new
* reference with av_buffer_ref() for the target packet's opaque_ref field.
*
* This is unrelated to the opaque field, although it serves a similar
* purpose.
*/
AVBufferRef *opaque_ref;
/**
* Time base of the packet's timestamps.
* In the future, this field may be set on packets output by encoders or
* demuxers, but its value will be by default ignored on input to decoders
* or muxers.
*/
AVRational time_base;
} AVPacket;5、int avcodec_receive_frame(AVCodecContext *avctx, AVFrame *frame);
该函数用于从解码器中接收已经解码完成的数据(如YUV)。参数avctx为码器上下文参数即avcodec_alloc_context3函数返回值。AVFrame *frame为输入解码数据的变量，AVFrame的成员变量定义比较多这里就不再全部展示，其主要的成员定义如下：
typedef struct AVFrame {
#define AV_NUM_DATA_POINTERS 8
//解码后YUV的分辨率
int width, height;
//解码后的时间戳
int64_t pts;
//解码后的数据地址
uint8_t *data[AV_NUM_DATA_POINTERS];
//解码后图像各个分量的跨距
int linesize[AV_NUM_DATA_POINTERS];
} AVFrame;6、void avcodec_free_context(AVCodecContext **avctx);
该函数用于释放编码器上下文。avctx参数为解码器的上下文参数变量，即avcodec_alloc_context3函数返回值。
三、ffmpeg解码示例
1、视频解码器初始化核心代码
int video_denc_init(int vencType)
{
enum AVCodecID codecId = vencType ? AV_CODEC_ID_H265 : AV_CODEC_ID_H264;
g_videoDencMng.pAVCodecDecoder = (AVCodec*)avcodec_find_decoder(codecId);//查找对应的解码器
if (!g_videoDencMng.pAVCodecDecoder){
printf("can not find H26x (%d) codec\n",codecId);
return -1;
}
//根据解码器分配编解码器上下文
g_videoDencMng.pAVCodecCtxDecoder = avcodec_alloc_context3(g_videoDencMng.pAVCodecDecoder);
if (g_videoDencMng.pAVCodecCtxDecoder == NULL) {
printf("Could not alloc video context!\n");
return -1;
}
//打开编码器
if (avcodec_open2(g_videoDencMng.pAVCodecCtxDecoder, g_videoDencMng.pAVCodecDecoder, NULL) < 0){
printf("Failed to open h264 decoder");
video_denc_release();
return -1;
}
return 0;
}2、解码一帧视频数据的核心代码
int video_denc_decode(unsigned char *inbuf, int inSize,long pts)
{
if (0==g_videoDencMng.bInit || !inbuf || inSize <=0)
{
return -1;
}
av_frame_unref(g_videoDencMng.pAVFrameDecoder);
av_frame_unref(g_videoDencMng.pFrameYUVDecoder);
g_videoDencMng.mAVPacketDecoder.data = inbuf;
g_videoDencMng.mAVPacketDecoder.size = inSize;
g_videoDencMng.mAVPacketDecoder.pts = pts;
int ret = avcodec_send_packet(g_videoDencMng.pAVCodecCtxDecoder, &g_videoDencMng.mAVPacketDecoder);
if (ret != 0)
{
printf("avcodec_send_packet error(%d)\n",ret);
return -1;
}
ret = avcodec_receive_frame(g_videoDencMng.pAVCodecCtxDecoder, g_videoDencMng.pAVFrameDecoder);//默认输出yuv420p
if (ret == 0)
{
g_videoDencMng.mFrameNum++;
std::shared_ptr pYuv = std::make_shared();
pYuv->width = g_videoDencMng.pAVFrameDecoder->width;
pYuv->height = g_videoDencMng.pAVFrameDecoder->height;
pYuv->pts = g_videoDencMng.pAVFrameDecoder->pts;
pYuv->seq = g_videoDencMng.mFrameNum;
pYuv->lineSize[0] = g_videoDencMng.pAVFrameDecoder->linesize[0];
pYuv->lineSize[1] = g_videoDencMng.pAVFrameDecoder->linesize[1];
pYuv->lineSize[2] = g_videoDencMng.pAVFrameDecoder->linesize[2];
pYuv->pData = new unsigned char [pYuv->width * pYuv->height * 3 / 2];
for(int i = 0;i < pYuv->height;i++)
{
memcpy(pYuv->pData+i*pYuv->width, g_videoDencMng.pAVFrameDecoder->data[0]+i*g_videoDencMng.pAVFrameDecoder->linesize[0], pYuv->width);
}
for(int i = 0;i < pYuv->height / 2;i++)
{
memcpy(pYuv->pData+pYuv->width*pYuv->height+i*pYuv->width / 2, g_videoDencMng.pAVFrameDecoder->data[1]+i*g_videoDencMng.pAVFrameDecoder->linesize[1], pYuv->width / 2);
memcpy(pYuv->pData+pYuv->width*pYuv->height + pYuv->width / 2 *pYuv->height / 2+i*pYuv->width/2, g_videoDencMng.pAVFrameDecoder->data[2]+i*g_videoDencMng.pAVFrameDecoder->linesize[2], pYuv->width / 2);
}
//存储YUV到输出缓存队列中。 略
。。。。。。
return (pYuv->width * pYuv->height * 3 / 2);
}
else if (ret == AVERROR(EAGAIN))
{
printf("avcodec_receive_frame :EAGAIN %d\n",ret);
return 0;
}
printf("avcodec_receive_frame error %d\n",ret);
return -1;
} 3、解码器关闭的核心代码
static int video_denc_release()
{
if (g_videoDencMng.pAVCodecCtxDecoder != NULL) {
avcodec_free_context(&g_videoDencMng.pAVCodecCtxDecoder);
g_videoDencMng.pAVCodecCtxDecoder = NULL;
}
return 0;
}四、ffmpeg解码框架设计
