AVFrame
结构体
typedef struct AVFrame { #define AV_NUM_DATA_POINTERS 8 /**图像数据 * 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; /**宽高 * 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; /**是否是关键帧 * 1 -> keyframe, 0-> not * - encoding: Set by libavcodec. * - decoding: Set by libavcodec. */ int key_frame; /**帧类型(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; /**跳过宏块表 * 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; /**运动矢量表 * 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]; /**宏块类型表 * macroblock type table * mb_type_base + mb_width + 2 * - encoding: Set by user. * - decoding: Set by libavcodec. */ uint32_t *mb_type; /**DCT系数 * DCT coefficients * - encoding: unused * - decoding: Set by libavcodec. */ short *dct_coeff; /**参考帧列表 * 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; /**(音频)采样率 * 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;
主要变量含义
uint8_t *data[AV_NUM_DATA_POINTERS]:解码后原始数据(对视频来说是YUV,RGB,对音频来说是PCM) int linesize[AV_NUM_DATA_POINTERS]:data中“一行”数据的大小。注意:未必等于图像的宽,一般大于图像的宽。 int width, height:视频帧宽和高(1920x1080,1280x720...) int nb_samples:音频的一个AVFrame中可能包含多个音频帧,在此标记包含了几个 int format:解码后原始数据类型(YUV420,YUV422,RGB24...) int key_frame:是否是关键帧 enum AVPictureType pict_type:帧类型(I,B,P...) AVRational sample_aspect_ratio:宽高比(16:9,4:3...) int64_t pts:显示时间戳 int coded_picture_number:编码帧序号 int display_picture_number:显示帧序号 int8_t *qscale_table:QP表 uint8_t *mbskip_table:跳过宏块表 int16_t (*motion_val[2])[2]:运动矢量表 uint32_t *mb_type:宏块类型表 short *dct_coeff:DCT系数,这个没有提取过 int8_t *ref_index[2]:运动估计参考帧列表(貌似H.264这种比较新的标准才会涉及到多参考帧) int interlaced_frame:是否是隔行扫描 uint8_t motion_subsample_log2:一个宏块中的运动矢量采样个数,取log的
补充
比如
yuv数据
data[0] 存储 y数组,data[1]存储 u数组,data[2] 存储v数组
linesize[0] 存储y 一行的size ,linesize[1] 存储 u 一行的size,linesize[2] 存储 v一行的size
width/height不必解释
format 表示数据格式 yuv420/yuv444/rgb24 etc.
基于YUV420 AVFrame的裁剪
原图
AVFormatContext
AVStream
裁剪功能实现
左上角裁剪
思路
由于默认显示起始点就是从左上角开始的,所以实际上我们只需要改变avframe显示的宽高即可
实现
... //AVFrame* pCropFrame 获取之后 int wDst = pCropFrame->width * 2 / 4; int hDst = pCropFrame->height * 2 / 4; //修改宽高都为之前一半 pCropFrame->width = wDst; pCropFrame->height = hDst; ... //显示pCropFrame即可
右上角裁剪
思路
起始坐标从 1/2 原图片宽开始 将右上角部分替换到左上角位置,最后修改avframe 宽高为原来一半
用 右上角 1/2 hSrc * 1/2 wSrc 像素内容 替换 左上角内容
实现
//获得pCropFrame ... int wDst = pCropFrame->width * 2 / 4; int hDst = pCropFrame->height * 2 /4 ; int wSrc = pCropFrame->width ; int hSrc = pCropFrame->height; //左上角 //pCropFrame->width = wDst; //pCropFrame->height = hDst; //右上角 int lineSizeY = pCropFrame->linesize[0]; int lineSizeU = pCropFrame->linesize[1]; int lineSizeV = pCropFrame->linesize[2]; //crop Y for (size_t line = 0; line < hDst; line++) //行循环 { //起始[0] + 行中心 memcpy(pCropFrame->data[0]+ line*lineSizeY, pCropFrame->data[0]+ line*lineSizeY + lineSizeY / 2, lineSizeY/2); } //crop U for (size_t line = 0; line < hDst/2; line++)//行循环 { memcpy(pCropFrame->data[1] + line*lineSizeU, pCropFrame->data[1] + lineSizeU / 2 + line*lineSizeU, lineSizeU / 2); } //crop V for (size_t line = 0; line < hDst/2; line++)//行循环 { memcpy(pCropFrame->data[2] + line*lineSizeV, pCropFrame->data[2] + lineSizeV / 2 + line*lineSizeV, lineSizeV / 2); } pCropFrame->width = wDst; pCropFrame->height = hDst; ... //显示pCropFrame