FFmpeg有两个存储帧数据的结构体,其中AVPacket是解封装后保存压缩数据包,AVFrame是解码后保存音视频帧。
AVPacket结构体以前放在avcodec.h头文件中,在FFmpeg4.4以后放在单独packet.h头文件。官方对AVPacket的说明如下:
/**
* This structure stores compressed data. It is typically exported by demuxers
* and then passed as input to decoders, or received as output from encoders and
* then passed to muxers.
*
* For video, it should typically contain one compressed frame. For audio it may
* contain several compressed frames. Encoders are allowed to output empty
* packets, with no compressed data, containing only side data
* (e.g. to update some stream parameters at the end of encoding).
*
*/
AVPacket结构体定义如下:
typedef struct AVPacket {
AVBufferRef *buf;
// 显示时间戳,单位为AVStream->time_base
int64_t pts;
// 解码时间戳,单位为AVStream->time_base
int64_t dts;
// 音视频数据
uint8_t *data;
// 数据包大小
int size;
// 码流索引下标
int stream_index;
// 帧类型
int flags;
// 额外数据
AVPacketSideData *side_data;
int side_data_elems;
// 帧显示时长,单位为AVStream->time_base
int64_t duration;
// 数据包所在码流的position
int64_t pos;
} AVPacket;
AVPacket的分配与释放有对应的API,需要注意的是释放所传的参数为AVPacket指针的地址。API与示例如下:
API:
AVPacket *av_packet_alloc(void);
void av_packet_unref(AVPacket *pkt);
void av_packet_free(AVPacket **pkt);
demo:
AVPacket *pkt = av_packet_alloc();
av_packet_unref(pkt);
av_packet_free(&pkt);
AVFrame结构体位于frame.h头文件,用于存储解码后的音视频帧数据,使用av_frame_alloc进行分配,使用av_frame_free进行释放,AVFrame分配一次,多次复用,使用av_frame_unref可以去引用。官方关于AVFrame的描述如下:
/**
* This structure describes decoded (raw) audio or video data.
*
* AVFrame must be allocated using av_frame_alloc(). Note that this only
* allocates the AVFrame itself, the buffers for the data must be managed
* through other means (see below).
* AVFrame must be freed with av_frame_free().
*
* AVFrame is typically allocated once and then reused multiple times to hold
* different data (e.g. a single AVFrame to hold frames received from a
* decoder). In such a case, av_frame_unref() will free any references held by
* the frame and reset it to its original clean state before it
* is reused again.
*/
AVFrame是解码后用于存储音视频帧,包括:data数组、width、height、pts、pkt_dts、pkt_size、pkt_duration、pkt_pos等信息,我们在判断是否为关键帧时,用key_frame参数进行判断。结构体的定义如下:
typedef struct AVFrame {
#define AV_NUM_DATA_POINTERS 8
// pointer to the picture/channel planes.
uint8_t *data[AV_NUM_DATA_POINTERS];
/**
* For video, size in bytes of each picture line.
* For audio, size in bytes of each plane.
*
* For audio, only linesize[0] may be set. For planar audio, each channel
* plane must be the same size.
*
* For video the linesizes should be multiples of the CPUs alignment
* preference, this is 16 or 32 for modern desktop CPUs.
* Some code requires such alignment other code can be slower without
* correct alignment, for yet other it makes no difference.
*/
int linesize[AV_NUM_DATA_POINTERS];
/**
* pointers to the data planes/channels.
*
* For video, this should simply point to data[].
*
* For planar audio, each channel has a separate data pointer, and
* linesize[0] contains the size of each channel buffer.
* For packed audio, there is just one data pointer, and linesize[0]
* contains the total size of the buffer for all channels.
*/
uint8_t **extended_data;
/**
* @name Video dimensions
*/
int width, height;
/**
* number of audio samples (per channel) described by this frame
*/
int nb_samples;
/**
* format of the frame, -1 if unknown or unset
* Values correspond to enum AVPixelFormat for video frames,
* enum AVSampleFormat for audio)
*/
int format;
/**
* 1 -> keyframe, 0-> not
*/
int key_frame;
/**
* Picture type of the frame.
*/
enum AVPictureType pict_type;
/**
* Sample aspect ratio for the video frame, 0/1 if unknown/unspecified.
*/
AVRational sample_aspect_ratio;
/**
* Presentation timestamp in time_base units.
*/
int64_t pts;
/**
* DTS copied from the AVPacket that triggered returning this frame.
* This is also the Presentation time of this AVFrame calculated from
* only AVPacket.dts values without pts values.
*/
int64_t pkt_dts;
/**
* picture number in bitstream order
*/
int coded_picture_number;
/**
* picture number in display order
*/
int display_picture_number;
/**
* quality (between 1 (good) and FF_LAMBDA_MAX (bad))
*/
int quality;
/**
* for some private data of the user
*/
void *opaque;
/**
* When decoding, this signals how much the picture must be delayed.
* extra_delay = repeat_pict / (2*fps)
*/
int repeat_pict;
/**
* The content of the picture is interlaced.
*/
int interlaced_frame;
/**
* If the content is interlaced, is top field displayed first.
*/
int top_field_first;
/**
* Tell user application that palette has changed from previous frame.
*/
int palette_has_changed;
/**
* reordered opaque 64 bits.
*/
int64_t reordered_opaque;
/**
* Sample rate of the audio data.
*/
int sample_rate;
/**
* Channel layout of the audio data.
*/
uint64_t channel_layout;
/**
* AVBuffer references backing the data for this frame.
* If all elements of this array are NULL,
* then this frame is not reference counted.
*/
AVBufferRef *buf[AV_NUM_DATA_POINTERS];
/**
* For planar audio which requires more than AV_NUM_DATA_POINTERS
* AVBufferRef pointers, this array will hold all the references which
* cannot fit into AVFrame.buf.
*/
AVBufferRef **extended_buf;
/**
* Number of elements in extended_buf.
*/
int nb_extended_buf;
AVFrameSideData **side_data;
int nb_side_data;
/**
* The frame data may be corrupted, e.g. due to decoding errors.
*/
#define AV_FRAME_FLAG_CORRUPT (1 << 0)
/**
* A flag to mark the frames which need to be decoded.
*/
#define AV_FRAME_FLAG_DISCARD (1 << 2)
/**
* Frame flags, a combination of @ref lavu_frame_flags
*/
int flags;
/**
* MPEG vs JPEG YUV range.
* - encoding: Set by user
* - decoding: Set by libavcodec
*/
enum AVColorRange color_range;
enum AVColorPrimaries color_primaries;
enum AVColorTransferCharacteristic color_trc;
/**
* YUV colorspace type.
* - encoding: Set by user
* - decoding: Set by libavcodec
*/
enum AVColorSpace colorspace;
enum AVChromaLocation chroma_location;
/**
* frame timestamp estimated using various heuristics, in stream time base
* - encoding: unused
* - decoding: set by libavcodec, read by user.
*/
int64_t best_effort_timestamp;
/**
* reordered pos from the last AVPacket that has been input into the decoder
* - encoding: unused
* - decoding: Read by user.
*/
int64_t pkt_pos;
/**
* duration of the corresponding packet, expressed in
* AVStream->time_base units, 0 if unknown.
* - encoding: unused
* - decoding: Read by user.
*/
int64_t pkt_duration;
/**
* metadata.
* - encoding: Set by user.
* - decoding: Set by libavcodec.
*/
AVDictionary *metadata;
/**
* decode error flags of the frame, set to a combination of
* FF_DECODE_ERROR_xxx flags if the decoder produced a frame,
* but there were errors during the decoding.
*/
int decode_error_flags;
#define FF_DECODE_ERROR_INVALID_BITSTREAM 1
#define FF_DECODE_ERROR_MISSING_REFERENCE 2
#define FF_DECODE_ERROR_CONCEALMENT_ACTIVE 4
#define FF_DECODE_ERROR_DECODE_SLICES 8
// number of audio channels, only used for audio.
int channels;
// size of the corresponding packet containing the compressed frame.
int pkt_size;
/**
* For hwaccel-format frames, this should be a reference to the
* AVHWFramesContext describing the frame.
*/
AVBufferRef *hw_frames_ctx;
/**
* 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 frame is unreferenced. av_frame_copy_props() calls create a new
* reference with av_buffer_ref() for the target frame's opaque_ref field.
*/
AVBufferRef *opaque_ref;
/**
* Video frames only. The number of pixels to discard from the the
* top/bottom/left/right border of the frame to obtain the sub-rectangle of
* the frame intended for presentation.
*/
size_t crop_top;
size_t crop_bottom;
size_t crop_left;
size_t crop_right;
/**
* AVBufferRef for internal use by a single libav* library.
* Must not be used to transfer data between libraries.
*/
AVBufferRef *private_ref;
} AVFrame;
其中,帧类型使用AVPictureType(位于libavutil/avutil.h)表示,枚举定义如下:
enum AVPictureType {
AV_PICTURE_TYPE_NONE = 0, ///< Undefined
AV_PICTURE_TYPE_I, ///< Intra
AV_PICTURE_TYPE_P, ///< Predicted
AV_PICTURE_TYPE_B, ///< Bi-dir predicted
AV_PICTURE_TYPE_S, ///< S(GMC)-VOP MPEG-4
AV_PICTURE_TYPE_SI, ///< Switching Intra
AV_PICTURE_TYPE_SP, ///< Switching Predicted
AV_PICTURE_TYPE_BI, ///< BI type
};
AVFrame的分配与释放也有相应API,具体API以及使用实例如下:
API:
AVFrame *av_frame_alloc(void);
void av_frame_unref(AVFrame *frame);
void av_frame_free(AVFrame **frame);
demo:
AVFrame *frame = av_frame_alloc();
av_frame_unref(frame);
av_frame_free(&frame);