AVFrame结构体

2020-12-20

AVFrame结构体是存储音视频原始数据（即未被编码的数据）的结构体。该结构体位于libavutil/frame.h中。分析一下结构体中里的重要变量的含义和作用，首先看一下结构体的定义：

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;

AVFrame结构体一般是用来存储原始数据（视频数据是YUV 和RGB，音频数据是PCM）。编码的时候也存储了一些相关的信息，在使用ffmpeg进行开发的时候，AVFrame是一个很重要的结构体。

接下来我们看下结构体中重要的变量和作用：

uint8_t *data[AV_NUM_DATA_POINTERS]; 解码后的原始数据，视频数据是YUV 和RGB，音频数据是PCM）
int linesize[AV_NUM_DATA_POINTERS];data中“一行“数据的大小，一般大于图像的宽
int width, height; 对视频而言指视频的宽和高
int nb_samples; 音频中一个AVFrame包含多个音频帧，表示音频帧的数量
int format; 帧的格式，原始数据的类型
int key_frame; 是否为关键帧
enum AVPictureType pict_type; 帧的类型
AVRational sample_aspect_ratio; 宽高比
int64_t pts; 显示时间戳
int64_t pkt_dts;每一帧的时间
int coded_picture_number;编码帧的序号
int display_picture_number;显示帧的序号
int sample_rate; 采样率（音频）
uint64_t channel_layout; 声道格式（音频）
int channels; 声道数量（编码未使用），解码只读
int interlaced_frame;是否隔行扫描
int8_t *qscale_table;QP表
int quality; 帧的质量，1表示好 FF_LAMBDA_MAX表示bad
enum AVColorRange color_range; MPEG,JPEG,YUV的色彩范围
enum AVColorSpace colorspace; YUV的色彩空间
int64_t pkt_duration; 相关包的流逝时间
AVDictionary *metadata;元数据

其他的变量不再一一列举，重点学习一下一定要理解的数据：

\1. uint8_t *data[AV_NUM_DATA_POINTERS]；

对于packed格式的数据会存到data[0]中,例如RGB24

对于plannar格式的数据会存到data[0],data[1]…,例如YUV420P，会分开存到Y : data[0],U :data[1],V:data[2]

\2. enum AVPictureType pict_type;包含以下类型：

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
};

\3. AVRational sample_aspect_ratio;

宽高比是一个分数，FFMPEG中使用AVRational表示分数

typedef struct AVRational{
 int num; ///< Numerator
 int den; ///< Denominator
} AVRational;

\4. int8_t *qscale_table;

QP表指向一块内存，里面存储的是每个宏块的QP值。宏块的标号是从左往右，一行一行的来的。每个宏块对应1个QP。qscale_table[0]就是第1行第1列宏块的QP值；qscale_table[1]就是第1行第2列宏块的QP值；qscale_table[2]就是第1行第3列宏块的QP值。以此类推…

宏块的个数用下式计算：

注：宏块大小是16x16的。

每行宏块数：

1	int mb_stride = pCodecCtx->width/16+1

宏块的总数：

1	int mb_sum = ((pCodecCtx->height+15)>>4)*(pCodecCtx->width/16+1)

5.uint64_t channel_layout; 声道格式（音频）

#define AV_CH_FRONT_LEFT             0x00000001
#define AV_CH_FRONT_RIGHT            0x00000002
#define AV_CH_FRONT_CENTER           0x00000004
#define AV_CH_LOW_FREQUENCY          0x00000008
#define AV_CH_BACK_LEFT              0x00000010
#define AV_CH_BACK_RIGHT             0x00000020
#define AV_CH_FRONT_LEFT_OF_CENTER   0x00000040
#define AV_CH_FRONT_RIGHT_OF_CENTER  0x00000080
#define AV_CH_BACK_CENTER            0x00000100
#define AV_CH_SIDE_LEFT              0x00000200
#define AV_CH_SIDE_RIGHT             0x00000400
#define AV_CH_TOP_CENTER             0x00000800
#define AV_CH_TOP_FRONT_LEFT         0x00001000
#define AV_CH_TOP_FRONT_CENTER       0x00002000
#define AV_CH_TOP_FRONT_RIGHT        0x00004000
#define AV_CH_TOP_BACK_LEFT          0x00008000
#define AV_CH_TOP_BACK_CENTER        0x00010000
#define AV_CH_TOP_BACK_RIGHT         0x00020000
#define AV_CH_STEREO_LEFT            0x20000000  ///< Stereo downmix.
#define AV_CH_STEREO_RIGHT           0x40000000  ///< See AV_CH_STEREO_LEFT.
#define AV_CH_WIDE_LEFT              0x0000000080000000ULL
#define AV_CH_WIDE_RIGHT             0x0000000100000000ULL
#define AV_CH_SURROUND_DIRECT_LEFT   0x0000000200000000ULL
#define AV_CH_SURROUND_DIRECT_RIGHT  0x0000000400000000ULL
#define AV_CH_LOW_FREQUENCY_2        0x0000000800000000ULL

/** Channel mask value used for AVCodecContext.request_channel_layout
    to indicate that the user requests the channel order of the decoder output
    to be the native codec channel order. */
#define AV_CH_LAYOUT_NATIVE          0x8000000000000000ULL

/**
 * @}
 * @defgroup channel_mask_c Audio channel layouts
 * @{
 * */
#define AV_CH_LAYOUT_MONO              (AV_CH_FRONT_CENTER)
#define AV_CH_LAYOUT_STEREO            (AV_CH_FRONT_LEFT|AV_CH_FRONT_RIGHT)
#define AV_CH_LAYOUT_2POINT1           (AV_CH_LAYOUT_STEREO|AV_CH_LOW_FREQUENCY)
#define AV_CH_LAYOUT_2_1               (AV_CH_LAYOUT_STEREO|AV_CH_BACK_CENTER)
#define AV_CH_LAYOUT_SURROUND          (AV_CH_LAYOUT_STEREO|AV_CH_FRONT_CENTER)
#define AV_CH_LAYOUT_3POINT1           (AV_CH_LAYOUT_SURROUND|AV_CH_LOW_FREQUENCY)
#define AV_CH_LAYOUT_4POINT0           (AV_CH_LAYOUT_SURROUND|AV_CH_BACK_CENTER)
#define AV_CH_LAYOUT_4POINT1           (AV_CH_LAYOUT_4POINT0|AV_CH_LOW_FREQUENCY)
#define AV_CH_LAYOUT_2_2               (AV_CH_LAYOUT_STEREO|AV_CH_SIDE_LEFT|AV_CH_SIDE_RIGHT)
#define AV_CH_LAYOUT_QUAD              (AV_CH_LAYOUT_STEREO|AV_CH_BACK_LEFT|AV_CH_BACK_RIGHT)
#define AV_CH_LAYOUT_5POINT0           (AV_CH_LAYOUT_SURROUND|AV_CH_SIDE_LEFT|AV_CH_SIDE_RIGHT)
#define AV_CH_LAYOUT_5POINT1           (AV_CH_LAYOUT_5POINT0|AV_CH_LOW_FREQUENCY)
#define AV_CH_LAYOUT_5POINT0_BACK      (AV_CH_LAYOUT_SURROUND|AV_CH_BACK_LEFT|AV_CH_BACK_RIGHT)
#define AV_CH_LAYOUT_5POINT1_BACK      (AV_CH_LAYOUT_5POINT0_BACK|AV_CH_LOW_FREQUENCY)
#define AV_CH_LAYOUT_6POINT0           (AV_CH_LAYOUT_5POINT0|AV_CH_BACK_CENTER)
#define AV_CH_LAYOUT_6POINT0_FRONT     (AV_CH_LAYOUT_2_2|AV_CH_FRONT_LEFT_OF_CENTER|AV_CH_FRONT_RIGHT_OF_CENTER)
#define AV_CH_LAYOUT_HEXAGONAL         (AV_CH_LAYOUT_5POINT0_BACK|AV_CH_BACK_CENTER)
#define AV_CH_LAYOUT_6POINT1           (AV_CH_LAYOUT_5POINT1|AV_CH_BACK_CENTER)
#define AV_CH_LAYOUT_6POINT1_BACK      (AV_CH_LAYOUT_5POINT1_BACK|AV_CH_BACK_CENTER)
#define AV_CH_LAYOUT_6POINT1_FRONT     (AV_CH_LAYOUT_6POINT0_FRONT|AV_CH_LOW_FREQUENCY)
#define AV_CH_LAYOUT_7POINT0           (AV_CH_LAYOUT_5POINT0|AV_CH_BACK_LEFT|AV_CH_BACK_RIGHT)
#define AV_CH_LAYOUT_7POINT0_FRONT     (AV_CH_LAYOUT_5POINT0|AV_CH_FRONT_LEFT_OF_CENTER|AV_CH_FRONT_RIGHT_OF_CENTER)
#define AV_CH_LAYOUT_7POINT1           (AV_CH_LAYOUT_5POINT1|AV_CH_BACK_LEFT|AV_CH_BACK_RIGHT)
#define AV_CH_LAYOUT_7POINT1_WIDE      (AV_CH_LAYOUT_5POINT1|AV_CH_FRONT_LEFT_OF_CENTER|AV_CH_FRONT_RIGHT_OF_CENTER)
#define AV_CH_LAYOUT_7POINT1_WIDE_BACK (AV_CH_LAYOUT_5POINT1_BACK|AV_CH_FRONT_LEFT_OF_CENTER|AV_CH_FRONT_RIGHT_OF_CENTER)
#define AV_CH_LAYOUT_OCTAGONAL         (AV_CH_LAYOUT_5POINT0|AV_CH_BACK_LEFT|AV_CH_BACK_CENTER|AV_CH_BACK_RIGHT)
#define AV_CH_LAYOUT_HEXADECAGONAL     (AV_CH_LAYOUT_OCTAGONAL|AV_CH_WIDE_LEFT|AV_CH_WIDE_RIGHT|AV_CH_TOP_BACK_LEFT|AV_CH_TOP_BACK_RIGHT|AV_CH_TOP_BACK_CENTER|AV_CH_TOP_FRONT_CENTER|AV_CH_TOP_FRONT_LEFT|AV_CH_TOP_FRONT_RIGHT)
#define AV_CH_LAYOUT_STEREO_DOWNMIX    (AV_CH_STEREO_LEFT|AV_CH_STEREO_RIGHT)

PS: 参考雷神博客FFMPEG结构体分析：AVFrame_雷霄骅(leixiaohua1020)的专栏-CSDN博客