FFmpeg结构体分析(1)--AVFrame

结构体AVFrame定义在frame.h中，主要用于描述解码后的原始音频数据或者视频数据。

/**
 * 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.
 *
 * The data described by an AVFrame is usually reference counted through the
 * AVBuffer API. The underlying buffer references are stored in AVFrame.buf /
 * AVFrame.extended_buf. An AVFrame is considered to be reference counted if at
 * least one reference is set, i.e. if AVFrame.buf[0] != NULL. In such a case,
 * every single data plane must be contained in one of the buffers in
 * AVFrame.buf or AVFrame.extended_buf.
 * There may be a single buffer for all the data, or one separate buffer for
 * each plane, or anything in between.
 *
 * sizeof(AVFrame) is not a part of the public ABI, so new fields may be added
 * to the end with a minor bump.
 *
 * Fields can be accessed through AVOptions, the name string used, matches the
 * C structure field name for fields accessible through AVOptions. The AVClass
 * for AVFrame can be obtained from avcodec_get_frame_class()
 */
typedef struct AVFrame {
#define AV_NUM_DATA_POINTERS 8
    /**
     * pointer to the picture/channel planes.
     * This might be different from the first allocated byte. For video,
     * it could even point to the end of the image data.
     *
     * All pointers in data and extended_data must point into one of the
     * AVBufferRef in buf or extended_buf.
     *
     * 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: Pointers not needed by the format MUST be set to NULL.
     *
     * @attention In case of video, the data[] pointers can point to the
     * end of image data in order to reverse line order, when used in
     * combination with negative values in the linesize[] array.
     */
    uint8_t *data[AV_NUM_DATA_POINTERS];

    /**
     * For video, a positive or negative value, which is typically indicating
     * the size in bytes of each picture line, but it can also be:
     * - the negative byte size of lines for vertical flipping
     *   (with data[n] pointing to the end of the data
     * - a positive or negative multiple of the byte size as for accessing
     *   even and odd fields of a frame (possibly flipped)
     *
     * 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.
     *
     * @attention In case of video, line size values can be negative to achieve
     * a vertically inverted iteration over image lines.
     */
    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;

    /**
     * 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;

    /**
     * Time base for the timestamps in this frame.
     * In the future, this field may be set on frames output by decoders or
     * filters, but its value will be by default ignored on input to encoders
     * or filters.
     */
    AVRational time_base;

    /**
     * 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 (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. All the pointers in
     * data and extended_data must point inside one of the buffers in buf or
     * extended_buf. 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;

    /**
     * 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;

常用的变量
uint8_t *data[AV_NUM_DATA_POINTERS]; 存储解码后原始数据，视频流数据（YUV、RGB）音频流数据（PCM）。
int linesize[AV_NUM_DATA_POINTERS]; 主要用于视频流数据，表示data中一幅图像的宽。
int width, height; 视频流数据中的宽和高，即分辨率。常见的有1920x1080，1280x720…
int nb_samples; 音频采样数(每个通道) 。
int format; 解码后原始数据类型，视频流数据可以查看enum AVPixelFormat，音频流数据可以查看enum AVSampleFormat。
int key_frame; 是否是关键帧，1表示关键帧，0表示非关键帧。
enum AVPictureType pict_type; 帧类型，即所说的I帧、B帧、P帧。
int64_t pts; 显示时间戳。
int sample_rate; 音频流采样率。
uint64_t channel_layout; 音频通道格式类型，如单声道、双声道…
int channels; 音频流的声道数，如1，2…