AVFrame结构体中变量解释

简介: AVFrame结构体中变量解释

AVPacket结构体内几个变量分析


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;


thxchtb3wcn3k_d11fc1ff3db9431d8ad7575e9297ae48.png

相关文章
|
4月前
|
存储 C语言
向函数传递结构体: C语言中的结构体参数传递详解
向函数传递结构体: C语言中的结构体参数传递详解
245 0
|
4月前
|
C语言
结构体变量的初始化
结构体变量的初始化。
28 3
|
4月前
|
C语言
【C语言】库宏offsetof(结构体成员偏移量计算宏)
【C语言】库宏offsetof(结构体成员偏移量计算宏)
37 0
|
10月前
|
C语言
写一个宏,计算结构体中某变量相对于首地址的偏移,并给出说明(C语言)
写一个宏,计算结构体中某变量相对于首地址的偏移,并给出说明(C语言)
50 0
|
4月前
|
存储 编译器 Linux
【C语言】自定义类型:结构体深入解析(二)结构体内存对齐&&宏offsetof计算偏移量&&结构体传参
【C语言】自定义类型:结构体深入解析(二)结构体内存对齐&&宏offsetof计算偏移量&&结构体传参
|
4月前
|
存储 程序员 C++
定义和使用结构体变量
定义和使用结构体变量
36 1
|
2月前
结构体变量传递
【7月更文挑战第7天】结构体变量传递。
19 6
|
4月前
|
C++
结构体变量与结构体变量指针作为函数参数
结构体变量与结构体变量指针作为函数参数
25 0
|
4月前
函数与结构体
函数与结构体
31 3
|
4月前
|
C语言
用结构体变量和结构体变量的指针做函数参数
用结构体变量和结构体变量的指针做函数参数
44 3