ffmpeg 基本數據結構和對象（一）： AVPacket、AVPicture、AVFrame

來源：http://blog.csdn.net/chance_yin/article/details/16817957

 

1、AVPacket

/**
 * AVPacket 做爲解碼器的輸入 或 編碼器的輸出。
 * 看成爲解碼器的輸入時，它由demuxer生成，而後傳遞給解碼器
 * 看成爲編碼器的輸出時，由編碼器生成，而後傳遞給muxer
 * 在視頻中，AVPacket 只能包含不大於1幀的內容，而視頻的1幀可能要包含在多個AVPacket中，AVPacket < AVFrame
 *
 *
 * AVPacket 是ffmpeg中少數的幾個公共ABI，它只能被libavcodec和libformat在棧上分配
 *
 * The side data is always allocated with av_malloc() and is freed in
 * av_free_packet().
 */
typedef struct AVPacket {
    /**
     * packet的內存空間來自於一個叫作「引用計數緩衝區」的地方，這個指針就指向一塊引用計數緩衝區
     */
    AVBufferRef *buf;
    /**
     * 顯示時間戳 單位是 AVStream->time_base units
     */
    int64_t pts;
    /**
     * 解壓時間戳，在這個時刻該包須要被解碼
     */
    int64_t dts;
    uint8_t *data;
    int   size;
    int   stream_index;
    /**
     * A combination of AV_PKT_FLAG values
     */
    int   flags;
    /**
     * 存放額外的包信息
     */
    struct {
        uint8_t *data;
        int      size;
        enum AVPacketSideDataType type;
    } *side_data;
    int side_data_elems;

    /**
     * 這個包的時間長度 in AVStream->time_base units, 設置0 表示未知.
     * duration = next_pts - this_pts i.
     */
    int   duration;

    int64_t pos;                            ///< 在數據流中的字節偏移量, -1 if unknown

    int64_t convergence_duration;
} AVPacket;

2、AVPicture

typedef struct AVPicture {
    uint8_t *data[AV_NUM_DATA_POINTERS];    ///< pointers to the image data planes
    int linesize[AV_NUM_DATA_POINTERS];     ///< number of bytes per line
}

3、AVFrame

/**
 * AVFrame表示解碼事後的一個數據幀
 *
 * AVFrame 經過使用 av_frame_alloc()來建立. 這個函數只是建立了AVFrame結構自己，在結構
 * 中定義的指向其餘內存塊的緩衝區指針要用其餘方法來分配
 * 使用 av_frame_free()來釋放AVFrame.
 *
 */
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.
     */
    int linesize[AV_NUM_DATA_POINTERS];

    /**
     * pointers to the data planes/channels.
     */
    uint8_t **extended_data;

    /**
     * width and height of the video frame
     */
    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
     */
    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;

    /**
     * PTS copied from the AVPacket that was decoded to produce this frame.
     */
    int64_t pkt_pts;

    /**
     * DTS copied from the AVPacket that triggered returning this frame. (if frame threading isnt 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;

    /**
     * error
     */
    uint64_t error[AV_NUM_DATA_POINTERS];

    /**
     * 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;

    /**
     * Sample rate of the audio data.
     */
    int sample_rate;

    /**
     * Channel layout of the audio data.
     */
    uint64_t channel_layout;

    /**
     * 指向這個幀要用到的AVBuffer中的數據緩衝區.
     *
     * 通常每一個圖像位面（就時data[0],data[1] data[2]）只有一個指向AVBuffer的緩衝區, 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.
     */
    AVBufferRef **extended_buf;
    /**
     * Number of elements in extended_buf.
     */
    int        nb_extended_buf;

    AVFrameSideData **side_data;
    int            nb_side_data;

/**
 * 可能由於解碼錯誤，數據幀Frame會成爲無效的幀，下面的結構就是當數據幀無效時使用的
 */
#define AV_FRAME_FLAG_CORRUPT       (1 << 0)

    /**
     * Frame flags, a combination of AV_FRAME_FLAG_*
     */
    int flags;


    int64_t best_effort_timestamp;


    int64_t pkt_pos;


    int64_t pkt_duration;


    AVDictionary *metadata;


    int decode_error_flags;
#define FF_DECODE_ERROR_INVALID_BITSTREAM   1
#define FF_DECODE_ERROR_MISSING_REFERENCE   2


    int channels;


    int pkt_size;


    enum AVColorSpace colorspace;


    enum AVColorRange color_range;


    /**
     * Not to be accessed directly from outside libavutil
     */
    AVBufferRef *qp_table_buf;
} AVFrame;