uint8_t *data[AV_NUM_DATA_POINTERS]：指针数组，存放YUV数据的地方。如图所示，一般占用前3个指针，分别指向Y，U，V数据。
对于packed格式的数据（例如RGB24），会存到data[0]里面。
对于planar格式的数据（例如YUV420P），则会分开成data[0]，data[1]，data[2]…（YUV420P中data[0]存Y，data[1]存U，data[2]存V）
int linesize[AV_NUM_DATA_POINTERS]：图像各个分量数据在此结构体中的的宽度。注意这并不是图像的宽度。在此例子中图像的尺寸为672X272，而亮度分量的宽度为704，应该是图像宽度经过64对齐后的结果。
uint8_t **extended_data：指向了图像数据。
int width, height：图像的宽高。
int nb_samples：此帧音频的点数。
int format：像素类型（视频），样点类型（音频）
int key_frame：是否关键帧，此例中为视频的第一帧，当然是关键帧了。
enum AVPictureType pict_type：图像类型，I，P，B等，同样，第一帧是I帧。
补充： 以下宏直接写在代码里就好如， frame->pict_type = AV_PICTURE_TYPE_I;
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 };
AVRational sample_aspect_ratio：像素的宽高比，注意不是图像的。
int64_t pts，pkt_pts，pkt_dts：和时间戳有关的变量，以后会详细介绍。
int coded_picture_number：编码顺序的图像num。
int display_picture_number：播放顺序的图像num。
int interlaced_frame：图像是否是隔行的。
int top_field_first：图像的top field first变量。
int64_t pkt_duration：对应packet的显示时长。
int pkt_size：对应packet的尺寸。
int8_t *qscale_table：据推测是存放qp（量化参数）的数组
AVBufferRef *qp_table_buf：成员data指向qscale_table。
以下可参考：
typedef struct AVMediaPacket
{
BYTE* m_data[TL_NUM_DATA_POINTERS];
int m_linesize[TL_NUM_DATA_POINTERS];
BYTE* m_pBuf;
int m_buf_size;
int m_max_size;
int m_cur_size;//ES包使用
int m_packet_type;//0ES包 1Frame
//enum AVPixelFormat for video frames
//enum AVSampleFormat for audio
int m_pixel_format;
int m_channel_count;
LONGLONG m_channel_layout;
int m_nb_samples; // 单个声道音频样本个数
int m_sample_rate; // 音频采样率
int m_width;
int m_height;
/**
* The content of the picture is interlaced.
* - encoding: Set by user.
* - decoding: Set by libavcodec. (default 0)
/
int m_interlaced_frame;//0逐行帧，1隔行帧
/*
* If the content is interlaced, is top field displayed first.
* - encoding: Set by user.
* - decoding: Set by libavcodec.
*/
int m_top_field_first;//0偶底场优先，1上奇场优先
int m_pict_type;
int m_es_stream_type;//是视频帧还是音频帧
LONGLONG m_pos;
LONGLONG m_origin_size;//原始ES包的字节数
LONGLONG m_dts;//ES包使用
LONGLONG m_pts;
LONGLONG m_origin_ts;
LONGLONG m_sys_pts;//转换成系统时间的pts(毫秒)
LONGLONG m_duration;//帧时长
LONGLONG m_sys_duration;//转换成系统时间的长度(毫秒)
int m_align;//数据的对齐方式
int m_scale_mod;//视频帧用到的变换方式(该帧是经过该变换方式得来的)
int m_stream_index;//同AVPacket的stream_index
int m_flags;//同AVPacket的flags
}AVMediaPacket;
//源码：
typedef struct AVFrame {
#define AV_NUM_DATA_POINTERS 8
/**
* pointer to the picture/channel planes.
* This might be different from the first allocated byte
*
* Some decoders access areas outside 0,0 - width,height, please
* see avcodec_align_dimensions2(). Some filters and swscale can read
* up to 16 bytes beyond the planes, if these filters are to be used,
* then 16 extra bytes must be allocated.
*
* NOTE: Except for hwaccel formats, pointers not needed by the format
* MUST be set to NULL.
*/
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.
*
* @note The linesize may be larger than the size of usable data -- there
* may be extra padding present for performance reasons.
*/
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.
*
* Note: Both data and extended_data should always be set in a valid frame,
* but for planar audio with more channels that can fit in data,
* extended_data must be used in order to access all channels.
*/
uint8_t **extended_data;
/**
* @name Video dimensions
* Video frames only. The coded dimensions (in pixels) of the video frame,
* i.e. the size of the rectangle that contains some well-defined values.
*
* @note The part of the frame intended for display/presentation is further
* restricted by the @ref cropping "Cropping rectangle".
* @{
*/
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 (time when frame should be shown to user).
*/
int64_t pts;
#if FF_API_PKT_PTS
/**
* PTS copied from the AVPacket that was decoded to produce this frame.
* @deprecated use the pts field instead
*/
attribute_deprecated
int64_t pkt_pts;
#endif
/**
* DTS copied from the AVPacket that triggered returning this frame. (if frame threading isn't used)
* 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;
#if FF_API_ERROR_FRAME
/**
* @deprecated unused
*/
attribute_deprecated
uint64_t error[AV_NUM_DATA_POINTERS];
#endif
/**
* 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 (generally an integer or a double precision float
* PTS but can be anything).
* The user sets AVCodecContext.reordered_opaque to represent the input at
* that time,
* the decoder reorders values as needed and sets AVFrame.reordered_opaque
* to exactly one of the values provided by the user through AVCodecContext.reordered_opaque
*/
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. This array
* must be filled contiguously -- if buf[i] is non-NULL then buf[j] must
* also be non-NULL for all j < i.
*
* There may be at most one AVBuffer per data plane, so for video this array
* always contains all the references. For planar audio with more than
* AV_NUM_DATA_POINTERS channels, there may be more buffers than can fit in
* this array. Then the extra AVBufferRef pointers are stored in the
* extended_buf array.
*/
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.
*
* Note that this is different from AVFrame.extended_data, which always
* contains all the pointers. This array only contains the extra pointers,
* which cannot fit into AVFrame.buf.
*
* This array is always allocated using av_malloc() by whoever constructs
* the frame. It is freed in av_frame_unref().
*/
AVBufferRef **extended_buf;
/**
* Number of elements in extended_buf.
*/
int nb_extended_buf;
AVFrameSideData **side_data;
int nb_side_data;
/**
* @defgroup lavu_frame_flags AV_FRAME_FLAGS
* @ingroup lavu_frame
* Flags describing additional frame properties.
*
* @{
*/
/**
* 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, but shouldn't be output.
*/
#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.
* - encoding: unused
* - decoding: set by libavcodec, read by user.
*/
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.
* - encoding: unused
* - decoding: Read by user.
*/
int channels;
/**
* size of the corresponding packet containing the compressed
* frame.
* It is set to a negative value if unknown.
* - encoding: unused
* - decoding: set by libavcodec, read by user.
*/
int pkt_size;
#if FF_API_FRAME_QP
/**
* QP table
*/
attribute_deprecated
int8_t *qscale_table;
/**
* QP store stride
*/
attribute_deprecated
int qstride;
attribute_deprecated
int qscale_type;
attribute_deprecated
AVBufferRef *qp_table_buf;
#endif
/**
* 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.
*
* This is unrelated to the opaque field, although it serves a similar
* purpose.
*/
AVBufferRef *opaque_ref;
/**
* @anchor cropping
* @name Cropping
* 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.
* Has to be NULL when ownership of the frame leaves the respective library.
*
* Code outside the FFmpeg libs should never check or change 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 private_ref field.
*/
AVBufferRef *private_ref;
} AVFrame;