AVFrame用來存儲解碼後的（或原圖）音頻或視頻數據，位於avcodec.h文件中。
AVFrame必須由av_frame_alloc()分配內存，同時必須由av_frame_free()釋放。
AVFrame分配內存後通過av_frame_ref 能夠被多次用來存儲不同的數據（例如：decoder解碼後的幀），類似與引用的概念。與av_frame_ref 對應的av_frame_unref釋放任何持幀的引用，將結構體還原到未被使用的狀態。
解碼後需要調用av_frame_unref，刪除當前幀引用，否則會有內存泄露。
一 源碼
/*
*雷霄驊
*[email protected]
*中國傳媒大學/數字電視技術
*/
/**
* Audio Video Frame.
* New fields can be added to the end of AVFRAME with minor version
* bumps. Similarly fields that are marked as to be only accessed by
* av_opt_ptr() can be reordered. This allows 2 forks to add fields
* without breaking compatibility with each other.
* Removal, reordering and changes in the remaining cases require
* a major version bump.
* sizeof(AVFrame) must not be used outside libavcodec.
*/
typedef struct AVFrame {
#define AV_NUM_DATA_POINTERS 8
/**圖像數據
* pointer to the picture/channel planes.
* This might be different from the first allocated byte
* - encoding: Set by user
* - decoding: set by AVCodecContext.get_buffer()
*/
uint8_t *data[AV_NUM_DATA_POINTERS];
/**
* Size, in bytes, of the data for each picture/channel plane.
*
* For audio, only linesize[0] may be set. For planar audio, each channel
* plane must be the same size.
*
* - encoding: Set by user
* - decoding: set by AVCodecContext.get_buffer()
*/
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 will always be set by get_buffer(),
* but for planar audio with more channels that can fit in data,
* extended_data must be used by the decoder in order to access all
* channels.
*
* encoding: unused
* decoding: set by AVCodecContext.get_buffer()
*/
uint8_t **extended_data;
/**寬高
* width and height of the video frame
* - encoding: unused
* - decoding: Read by user.
*/
int width, height;
/**
* number of audio samples (per channel) described by this frame
* - encoding: Set by user
* - decoding: Set by libavcodec
*/
int nb_samples;
/**
* format of the frame, -1 if unknown or unset
* Values correspond to enum AVPixelFormat for video frames,
* enum AVSampleFormat for audio)
* - encoding: unused
* - decoding: Read by user.
*/
int format;
/**是否是關鍵幀
* 1 -> keyframe, 0-> not
* - encoding: Set by libavcodec.
* - decoding: Set by libavcodec.
*/
int key_frame;
/**幀類型（I,B,P）
* Picture type of the frame, see ?_TYPE below.
* - encoding: Set by libavcodec. for coded_picture (and set by user for input).
* - decoding: Set by libavcodec.
*/
enum AVPictureType pict_type;
/**
* pointer to the first allocated byte of the picture. Can be used in get_buffer/release_buffer.
* This isn't used by libavcodec unless the default get/release_buffer() is used.
* - encoding:
* - decoding:
*/
uint8_t *base[AV_NUM_DATA_POINTERS];
/**
* sample aspect ratio for the video frame, 0/1 if unknown/unspecified
* - encoding: unused
* - decoding: Read by user.
*/
AVRational sample_aspect_ratio;
/**
* presentation timestamp in time_base units (time when frame should be shown to user)
* If AV_NOPTS_VALUE then frame_rate = 1/time_base will be assumed.
* - encoding: MUST be set by user.
* - decoding: Set by libavcodec.
*/
int64_t pts;
/**
* reordered pts from the last AVPacket that has been input into the decoder
* - encoding: unused
* - decoding: Read by user.
*/
int64_t pkt_pts;
/**
* dts from the last AVPacket that has been input into the decoder
* - encoding: unused
* - decoding: Read by user.
*/
int64_t pkt_dts;
/**
* picture number in bitstream order
* - encoding: set by
* - decoding: Set by libavcodec.
*/
int coded_picture_number;
/**
* picture number in display order
* - encoding: set by
* - decoding: Set by libavcodec.
*/
int display_picture_number;
/**
* quality (between 1 (good) and FF_LAMBDA_MAX (bad))
* - encoding: Set by libavcodec. for coded_picture (and set by user for input).
* - decoding: Set by libavcodec.
*/
int quality;
/**
* is this picture used as reference
* The values for this are the same as the MpegEncContext.picture_structure
* variable, that is 1->top field, 2->bottom field, 3->frame/both fields.
* Set to 4 for delayed, non-reference frames.
* - encoding: unused
* - decoding: Set by libavcodec. (before get_buffer() call)).
*/
int reference;
/**QP表
* QP table
* - encoding: unused
* - decoding: Set by libavcodec.
*/
int8_t *qscale_table;
/**
* QP store stride
* - encoding: unused
* - decoding: Set by libavcodec.
*/
int qstride;
/**
*
*/
int qscale_type;
/**跳過宏塊表
* mbskip_table[mb]>=1 if MB didn't change
* stride= mb_width = (width+15)>>4
* - encoding: unused
* - decoding: Set by libavcodec.
*/
uint8_t *mbskip_table;
/**運動矢量表
* motion vector table
* @code
* example:
* int mv_sample_log2= 4 - motion_subsample_log2;
* int mb_width= (width+15)>>4;
* int mv_stride= (mb_width << mv_sample_log2) + 1;
* motion_val[direction][x + y*mv_stride][0->mv_x, 1->mv_y];
* @endcode
* - encoding: Set by user.
* - decoding: Set by libavcodec.
*/
int16_t (*motion_val[2])[2];
/**宏塊類型表
* macroblock type table
* mb_type_base + mb_width + 2
* - encoding: Set by user.
* - decoding: Set by libavcodec.
*/
uint32_t *mb_type;
/**DCT係數
* DCT coefficients
* - encoding: unused
* - decoding: Set by libavcodec.
*/
short *dct_coeff;
/**參考幀列表
* motion reference frame index
* the order in which these are stored can depend on the codec.
* - encoding: Set by user.
* - decoding: Set by libavcodec.
*/
int8_t *ref_index[2];
/**
* for some private data of the user
* - encoding: unused
* - decoding: Set by user.
*/
void *opaque;
/**
* error
* - encoding: Set by libavcodec. if flags&CODEC_FLAG_PSNR.
* - decoding: unused
*/
uint64_t error[AV_NUM_DATA_POINTERS];
/**
* type of the buffer (to keep track of who has to deallocate data[*])
* - encoding: Set by the one who allocates it.
* - decoding: Set by the one who allocates it.
* Note: User allocated (direct rendering) & internal buffers cannot coexist currently.
*/
int type;
/**
* When decoding, this signals how much the picture must be delayed.
* extra_delay = repeat_pict / (2*fps)
* - encoding: unused
* - decoding: Set by libavcodec.
*/
int repeat_pict;
/**
* The content of the picture is interlaced.
* - encoding: Set by user.
* - decoding: Set by libavcodec. (default 0)
*/
int interlaced_frame;
/**
* If the content is interlaced, is top field displayed first.
* - encoding: Set by user.
* - decoding: Set by libavcodec.
*/
int top_field_first;
/**
* Tell user application that palette has changed from previous frame.
* - encoding: ??? (no palette-enabled encoder yet)
* - decoding: Set by libavcodec. (default 0).
*/
int palette_has_changed;
/**
* codec suggestion on buffer type if != 0
* - encoding: unused
* - decoding: Set by libavcodec. (before get_buffer() call)).
*/
int buffer_hints;
/**
* Pan scan.
* - encoding: Set by user.
* - decoding: Set by libavcodec.
*/
AVPanScan *pan_scan;
/**
* reordered opaque 64bit (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
* @deprecated in favor of pkt_pts
* - encoding: unused
* - decoding: Read by user.
*/
int64_t reordered_opaque;
/**
* hardware accelerator private data (FFmpeg-allocated)
* - encoding: unused
* - decoding: Set by libavcodec
*/
void *hwaccel_picture_private;
/**
* the AVCodecContext which ff_thread_get_buffer() was last called on
* - encoding: Set by libavcodec.
* - decoding: Set by libavcodec.
*/
struct AVCodecContext *owner;
/**
* used by multithreading to store frame-specific info
* - encoding: Set by libavcodec.
* - decoding: Set by libavcodec.
*/
void *thread_opaque;
/**
* log2 of the size of the block which a single vector in motion_val represents:
* (4->16x16, 3->8x8, 2-> 4x4, 1-> 2x2)
* - encoding: unused
* - decoding: Set by libavcodec.
*/
uint8_t motion_subsample_log2;
/**（音頻）採樣率
* Sample rate of the audio data.
*
* - encoding: unused
* - decoding: read by user
*/
int sample_rate;
/**
* Channel layout of the audio data.
*
* - encoding: unused
* - decoding: read by user.
*/
uint64_t channel_layout;
/**
* frame timestamp estimated using various heuristics, in stream time base
* Code outside libavcodec should access this field using:
* av_frame_get_best_effort_timestamp(frame)
* - 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
* Code outside libavcodec should access this field using:
* av_frame_get_pkt_pos(frame)
* - encoding: unused
* - decoding: Read by user.
*/
int64_t pkt_pos;
/**
* duration of the corresponding packet, expressed in
* AVStream->time_base units, 0 if unknown.
* Code outside libavcodec should access this field using:
* av_frame_get_pkt_duration(frame)
* - encoding: unused
* - decoding: Read by user.
*/
int64_t pkt_duration;
/**
* metadata.
* Code outside libavcodec should access this field using:
* av_frame_get_metadata(frame)
* - 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.
* Code outside libavcodec should access this field using:
* av_frame_get_decode_error_flags(frame)
* - 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
/**
* number of audio channels, only used for audio.
* Code outside libavcodec should access this field using:
* av_frame_get_channels(frame)
* - encoding: unused
* - decoding: Read by user.
*/
int64_t channels;
} AVFrame;
二 AVFrame 重點字段
AVFrame結構體一般用於存儲原始數據（即非壓縮數據，例如對視頻來說是YUV，RGB，對音頻來說是PCM），此外還包含了一些相關的信息。比如說，解碼的時候存儲了宏塊類型表，QP表，運動矢量表等數據。編碼的時候也存儲了相關的數據。因此在使用FFMPEG進行碼流分析的時候，AVFrame是一個很重要的結構體。
下面看幾個主要變量的作用（在這裏考慮解碼的情況）：
uint8_t *data[AV_NUM_DATA_POINTERS]：解碼後原始數據（對視頻來說是YUV，RGB，對音頻來說是PCM）
int linesize[AV_NUM_DATA_POINTERS]：data中“一行”數據的大小。注意：未必等於圖像的寬，一般大於圖像的寬。
int width, height：視頻幀寬和高（1920x1080,1280x720...）
int nb_samples：音頻的一個AVFrame中可能包含多個音頻幀，在此標記包含了幾個
int format：解碼後原始數據類型（YUV420，YUV422，RGB24...）
int key_frame：是否是關鍵幀
enum AVPictureType pict_type：幀類型（I,B,P...）
AVRational sample_aspect_ratio：寬高比（16:9，4:3...）
int64_t pts：顯示時間戳
int coded_picture_number：編碼幀序號
int display_picture_number：顯示幀序號
int8_t *qscale_table：QP表
uint8_t *mbskip_table：跳過宏塊表
int16_t (*motion_val[2])[2]：運動矢量表
uint32_t *mb_type：宏塊類型表
short *dct_coeff：DCT係數，這個沒有提取過
int8_t *ref_index[2]：運動估計參考幀列表（貌似H.264這種比較新的標準纔會涉及到多參考幀）
int interlaced_frame：是否是隔行掃描
uint8_t motion_subsample_log2：一個宏塊中的運動矢量採樣個數，取log的
其他的變量不再一一列舉，源代碼中都有詳細的說明。在這裏重點分析一下幾個需要一定的理解的變量：
1.data[]
對於packed格式的數據（例如RGB24），會存到data[0]裏面。
對於planar格式的數據（例如YUV420P），則會分開成data[0]，data[1]，data[2]...（YUV420P中data[0]存Y，data[1]存U，data[2]存V）
2.pict_type
包含以下類型：
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 MPEG4
AV_PICTURE_TYPE_SI, ///< Switching Intra
AV_PICTURE_TYPE_SP, ///< Switching Predicted
AV_PICTURE_TYPE_BI, ///< BI type
};
3.sample_aspect_ratio
寬高比是一個分數，FFMPEG中用AVRational表達分數：
/**
* rational number numerator/denominator
*/
typedef struct AVRational{
int num; ///< numerator
int den; ///< denominator
} AVRational;
4.qscale_table
QP表指向一塊內存，裏面存儲的是每個宏塊的QP值。宏塊的標號是從左往右，一行一行的來的。每個宏塊對應1個QP。
qscale_table[0]就是第1行第1列宏塊的QP值；qscale_table[1]就是第1行第2列宏塊的QP值；qscale_table[2]就是第1行第3列宏塊的QP值。以此類推...
宏塊的個數用下式計算：
注：宏塊大小是16x16的。
每行宏塊數：
int mb_stride = pCodecCtx->width/16+1
宏塊的總數：
int mb_sum = ((pCodecCtx->height+15)>>4)*(pCodecCtx->width/16+1)