FFMPeg代码分析：AVFrame结构体及其相关的函数

AVFrame结构体保存的是解码后和原始的音视频信息。AVFrame通过函数av_frame_alloc()初始化，该函数仅仅分配AVFrame实例本身，而没有分配其内部的缓存。AVFrame实例由av_frame_free()释放；AVFrame实例通常分配一次，重复使用，如分配一个AVFrame实例来保留解码器中输出的视频帧（此时应在恰当的时候使用av_frame_unref()清理参考帧并将AVFrame归零）。该类所描述的数据通常由AVBuffer的API来保存一个引用计数，并保存于AVFrame.buf /AVFrame.extended_buf，在至少存在一个参考的时候（如AVFrame.buf[0] != NULL），则该对象被标记为“被引用”。在此情况下，AVFrame所包含的每一组数据必须包含于AVFrame的缓存中。AVFrame的定义如下：[cpp] view plaincopy在CODE上查看代码片派生到我的代码片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. */ uint8_t *data[AV_NUM_DATA_POINTERS];//指向实际音视频数据的指针 /** * 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 multiplies 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; /** * width and height of the video frame */ int width, height;//视频的分辨率 /** * number of audio samples (per channel) described by this frame */ int nb_samples;//音频采样频率 /** * format of the frame, -1 if unknown or unset * Values correspond to enum AVPixelFormat for video frames, * enum AVSampleFormat for audio) */ int format;//解码后的视频帧的格式，为AVPixelFormat 枚举类型（YUV420，YUV422，RGB24等） /** * 1 -> keyframe, 0-> not */ int key_frame;//是否关键帧，1是0否 /** * Picture type of the frame. */ enum AVPictureType pict_type;//帧类型，IPB #if FF_API_AVFRAME_LAVC attribute_deprecated uint8_t *base[AV_NUM_DATA_POINTERS]; #endif /** * Sample aspect ratio for the video frame, 0/1 if unknown/unspecified. */ AVRational sample_aspect_ratio;//视频的宽高比 /** * Presentation timestamp in time_base units (time when frame should be shown to user). */ int64_t pts;//当前帧的显示时间戳 /** * 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;//当前帧以解码顺序的编号 /** * picture number in display order */ int display_picture_number;//当前帧以输出顺序的编号 /** * quality (between 1 (good) and FF_LAMBDA_MAX (bad)) */ int quality; #if FF_API_AVFRAME_LAVC attribute_deprecated int reference; /** * QP table */ attribute_deprecated int8_t *qscale_table;//量化参数表 /** * QP store stride */ attribute_deprecated int qstride; attribute_deprecated int qscale_type; /** * mbskip_table[mb]>=1 if MB didn't change * stride= mb_width = (width+15)>>4 */ attribute_deprecated uint8_t *mbskip_table; /** * 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 */ attribute_deprecated int16_t (*motion_val[2])[2];//运动矢量表 /** * macroblock type table * mb_type_base + mb_width + 2 */ attribute_deprecated uint32_t *mb_type;//宏块类型 /** * DCT coefficients */ attribute_deprecated short *dct_coeff;//变换系数 /** * motion reference frame index * the order in which these are stored can depend on the codec. */ attribute_deprecated int8_t *ref_index[2];//参考帧索引 #endif /** * for some private data of the user */ void *opaque; /** * error */ uint64_t error[AV_NUM_DATA_POINTERS]; #if FF_API_AVFRAME_LAVC attribute_deprecated int type; #endif /** * When decoding, this signals how much the picture must be delayed. * extra_delay = repeat_pict / (2*fps) */ int repeat_pict;//表示有多少帧被延迟显示，延迟即重复。 /** * The content of the picture is interlaced. */ int interlaced_frame;//隔行视频标识 /** * 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; #if FF_API_AVFRAME_LAVC attribute_deprecated int buffer_hints; /** * Pan scan. */ attribute_deprecated struct AVPanScan *pan_scan; #endif /** * 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 */ int64_t reordered_opaque; #if FF_API_AVFRAME_LAVC /** * @deprecated this field is unused */ attribute_deprecated void *hwaccel_picture_private; attribute_deprecated struct AVCodecContext *owner; attribute_deprecated 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) */ attribute_deprecated uint8_t motion_subsample_log2; #endif /** * 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. * * 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; /** * 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. */ int channels; /** * size of the corresponding packet containing the compressed * frame. It must be accessed using av_frame_get_pkt_size() and * av_frame_set_pkt_size(). * It is set to a negative value if unknown. * - encoding: unused * - decoding: set by libavcodec, read by user. */ int pkt_size; /** * YUV colorspace type. * It must be accessed using av_frame_get_colorspace() and * av_frame_set_colorspace(). * - encoding: Set by user * - decoding: Set by libavcodec */ enum AVColorSpace colorspace; /** * MPEG vs JPEG YUV range. * It must be accessed using av_frame_get_color_range() and * av_frame_set_color_range(). * - encoding: Set by user * - decoding: Set by libavcodec */ enum AVColorRange color_range; /** * Not to be accessed directly from outside libavutil */ AVBufferRef *qp_table_buf; } AVFrame; 通过对其内部的成员变量的研究可以看出，除了基本的储存像素的缓存之外，其成员大多还是与编解码相关的一些参数，如分辨率、帧类型、量化参数表、参考帧列表等。所以从大体上看，AVFrame就是一个容器类，同AVPacket不同的是所容纳的是原始的像素数据，相同点是都有很多编解码相关的参数作为补充数据。