FFmpeg之AVCodec

发布时间:2023年12月17日

这一节是最重要的一节,ffmpeg的解码,还是和以前一样,一定是先来一个上下文context,再一个具体的解码器类。
AVCodecContext和

下面是一个解码器定义,三部分组成,第一部分是设置参数,第二部分是基类,第三部分是具体实现。
如果你要实现自己的一个解码器,实现第三部分的那几个回调函数就可以了。

#define OFFSET(x) offsetof(H264Context, x)
#define VD AV_OPT_FLAG_VIDEO_PARAM | AV_OPT_FLAG_DECODING_PARAM
#define VDX VD | AV_OPT_FLAG_EXPORT
static const AVOption h264_options[] = {
    { "is_avc", "is avc", OFFSET(is_avc), AV_OPT_TYPE_BOOL, {.i64 = 0}, 0, 1, VDX },
    { "nal_length_size", "nal_length_size", OFFSET(nal_length_size), AV_OPT_TYPE_INT, {.i64 = 0}, 0, 4, VDX },
    { "enable_er", "Enable error resilience on damaged frames (unsafe)", OFFSET(enable_er), AV_OPT_TYPE_BOOL, { .i64 = -1 }, -1, 1, VD },
    { "x264_build", "Assume this x264 version if no x264 version found in any SEI", OFFSET(x264_build), AV_OPT_TYPE_INT, {.i64 = -1}, -1, INT_MAX, VD },
    { NULL },
};

static const AVClass h264_class = {
    .class_name = "H264 Decoder",
    .item_name  = av_default_item_name,
    .option     = h264_options,
    .version    = LIBAVUTIL_VERSION_INT,
};

const AVCodec ff_h264_decoder = {
    .name                  = "h264",
    .long_name             = NULL_IF_CONFIG_SMALL("H.264 / AVC / MPEG-4 AVC / MPEG-4 part 10"),
    .type                  = AVMEDIA_TYPE_VIDEO,
    .id                    = AV_CODEC_ID_H264,
    .priv_data_size        = sizeof(H264Context),
    .init                  = h264_decode_init,
    .close                 = h264_decode_end,
    .decode                = h264_decode_frame,
    .capabilities          = /*AV_CODEC_CAP_DRAW_HORIZ_BAND |*/ AV_CODEC_CAP_DR1 |
                             AV_CODEC_CAP_DELAY | AV_CODEC_CAP_SLICE_THREADS |
                             AV_CODEC_CAP_FRAME_THREADS,
    }

结构体定义


/**
 * main external API structure.
 * New fields can be added to the end with minor version bumps.
 * Removal, reordering and changes to existing fields require a major
 * version bump.
 * You can use AVOptions (av_opt* / av_set/get*()) to access these fields from user
 * applications.
 * The name string for AVOptions options matches the associated command line
 * parameter name and can be found in libavcodec/options_table.h
 * The AVOption/command line parameter names differ in some cases from the C
 * structure field names for historic reasons or brevity.
 * sizeof(AVCodecContext) must not be used outside libav*.
 */
typedef struct AVCodecContext {
    /**
     * information on struct for av_log
     * - set by avcodec_alloc_context3
     */
    const AVClass *av_class;
    int log_level_offset;

    enum AVMediaType codec_type; /* see AVMEDIA_TYPE_xxx */
    const struct AVCodec  *codec;
    enum AVCodecID     codec_id; /* see AV_CODEC_ID_xxx */

    /**
     * fourcc (LSB first, so "ABCD" -> ('D'<<24) + ('C'<<16) + ('B'<<8) + 'A').
     * This is used to work around some encoder bugs.
     * A demuxer should set this to what is stored in the field used to identify the codec.
     * If there are multiple such fields in a container then the demuxer should choose the one
     * which maximizes the information about the used codec.
     * If the codec tag field in a container is larger than 32 bits then the demuxer should
     * remap the longer ID to 32 bits with a table or other structure. Alternatively a new
     * extra_codec_tag + size could be added but for this a clear advantage must be demonstrated
     * first.
     * - encoding: Set by user, if not then the default based on codec_id will be used.
     * - decoding: Set by user, will be converted to uppercase by libavcodec during init.
     */
    unsigned int codec_tag;

    void *priv_data;

    /**
     * Private context used for internal data.
     *
     * Unlike priv_data, this is not codec-specific. It is used in general
     * libavcodec functions.
     */
    struct AVCodecInternal *internal;

    /**
     * Private data of the user, can be used to carry app specific stuff.
     * - encoding: Set by user.
     * - decoding: Set by user.
     */
    void *opaque;

    /**
     * the average bitrate
     * - encoding: Set by user; unused for constant quantizer encoding.
     * - decoding: Set by user, may be overwritten by libavcodec
     *             if this info is available in the stream
     */
    int64_t bit_rate;

    /**
     * number of bits the bitstream is allowed to diverge from the reference.
     *           the reference can be CBR (for CBR pass1) or VBR (for pass2)
     * - encoding: Set by user; unused for constant quantizer encoding.
     * - decoding: unused
     */
    int bit_rate_tolerance;

    /**
     * Global quality for codecs which cannot change it per frame.
     * This should be proportional to MPEG-1/2/4 qscale.
     * - encoding: Set by user.
     * - decoding: unused
     */
    int global_quality;

    /**
     * - encoding: Set by user.
     * - decoding: unused
     */
    int compression_level;
#define FF_COMPRESSION_DEFAULT -1

    /**
     * AV_CODEC_FLAG_*.
     * - encoding: Set by user.
     * - decoding: Set by user.
     */
    int flags;

    /**
     * AV_CODEC_FLAG2_*
     * - encoding: Set by user.
     * - decoding: Set by user.
     */
    int flags2;

    /**
     * some codecs need / can use extradata like Huffman tables.
     * MJPEG: Huffman tables
     * rv10: additional flags
     * MPEG-4: global headers (they can be in the bitstream or here)
     * The allocated memory should be AV_INPUT_BUFFER_PADDING_SIZE bytes larger
     * than extradata_size to avoid problems if it is read with the bitstream reader.
     * The bytewise contents of extradata must not depend on the architecture or CPU endianness.
     * Must be allocated with the av_malloc() family of functions.
     * - encoding: Set/allocated/freed by libavcodec.
     * - decoding: Set/allocated/freed by user.
     */
    uint8_t *extradata;
    int extradata_size;

    /**
     * This is the fundamental unit of time (in seconds) in terms
     * of which frame timestamps are represented. For fixed-fps content,
     * timebase should be 1/framerate and timestamp increments should be
     * identically 1.
     * This often, but not always is the inverse of the frame rate or field rate
     * for video. 1/time_base is not the average frame rate if the frame rate is not
     * constant.
     *
     * Like containers, elementary streams also can store timestamps, 1/time_base
     * is the unit in which these timestamps are specified.
     * As example of such codec time base see ISO/IEC 14496-2:2001(E)
     * vop_time_increment_resolution and fixed_vop_rate
     * (fixed_vop_rate == 0 implies that it is different from the framerate)
     *
     * - encoding: MUST be set by user.
     * - decoding: the use of this field for decoding is deprecated.
     *             Use framerate instead.
     */
    AVRational time_base;

    /**
     * For some codecs, the time base is closer to the field rate than the frame rate.
     * Most notably, H.264 and MPEG-2 specify time_base as half of frame duration
     * if no telecine is used ...
     *
     * Set to time_base ticks per frame. Default 1, e.g., H.264/MPEG-2 set it to 2.
     */
    int ticks_per_frame;

    /**
     * Codec delay.
     *
     * Encoding: Number of frames delay there will be from the encoder input to
     *           the decoder output. (we assume the decoder matches the spec)
     * Decoding: Number of frames delay in addition to what a standard decoder
     *           as specified in the spec would produce.
     *
     * Video:
     *   Number of frames the decoded output will be delayed relative to the
     *   encoded input.
     *
     * Audio:
     *   For encoding, this field is unused (see initial_padding).
     *
     *   For decoding, this is the number of samples the decoder needs to
     *   output before the decoder's output is valid. When seeking, you should
     *   start decoding this many samples prior to your desired seek point.
     *
     * - encoding: Set by libavcodec.
     * - decoding: Set by libavcodec.
     */
    int delay;


    /* video only */
    /**
     * picture width / height.
     *
     * @note Those fields may not match the values of the last
     * AVFrame output by avcodec_receive_frame() due frame
     * reordering.
     *
     * - encoding: MUST be set by user.
     * - decoding: May be set by the user before opening the decoder if known e.g.
     *             from the container. Some decoders will require the dimensions
     *             to be set by the caller. During decoding, the decoder may
     *             overwrite those values as required while parsing the data.
     */
    int width, height;

    /**
     * Bitstream width / height, may be different from width/height e.g. when
     * the decoded frame is cropped before being output or lowres is enabled.
     *
     * @note Those field may not match the value of the last
     * AVFrame output by avcodec_receive_frame() due frame
     * reordering.
     *
     * - encoding: unused
     * - decoding: May be set by the user before opening the decoder if known
     *             e.g. from the container. During decoding, the decoder may
     *             overwrite those values as required while parsing the data.
     */
    int coded_width, coded_height;

    /**
     * the number of pictures in a group of pictures, or 0 for intra_only
     * - encoding: Set by user.
     * - decoding: unused
     */
    int gop_size;

    /**
     * Pixel format, see AV_PIX_FMT_xxx.
     * May be set by the demuxer if known from headers.
     * May be overridden by the decoder if it knows better.
     *
     * @note This field may not match the value of the last
     * AVFrame output by avcodec_receive_frame() due frame
     * reordering.
     *
     * - encoding: Set by user.
     * - decoding: Set by user if known, overridden by libavcodec while
     *             parsing the data.
     */
    enum AVPixelFormat pix_fmt;

    /**
     * If non NULL, 'draw_horiz_band' is called by the libavcodec
     * decoder to draw a horizontal band. It improves cache usage. Not
     * all codecs can do that. You must check the codec capabilities
     * beforehand.
     * When multithreading is used, it may be called from multiple threads
     * at the same time; threads might draw different parts of the same AVFrame,
     * or multiple AVFrames, and there is no guarantee that slices will be drawn
     * in order.
     * The function is also used by hardware acceleration APIs.
     * It is called at least once during frame decoding to pass
     * the data needed for hardware render.
     * In that mode instead of pixel data, AVFrame points to
     * a structure specific to the acceleration API. The application
     * reads the structure and can change some fields to indicate progress
     * or mark state.
     * - encoding: unused
     * - decoding: Set by user.
     * @param height the height of the slice
     * @param y the y position of the slice
     * @param type 1->top field, 2->bottom field, 3->frame
     * @param offset offset into the AVFrame.data from which the slice should be read
     */
    void (*draw_horiz_band)(struct AVCodecContext *s,
                            const AVFrame *src, int offset[AV_NUM_DATA_POINTERS],
                            int y, int type, int height);

    /**
     * Callback to negotiate the pixel format. Decoding only, may be set by the
     * caller before avcodec_open2().
     *
     * Called by some decoders to select the pixel format that will be used for
     * the output frames. This is mainly used to set up hardware acceleration,
     * then the provided format list contains the corresponding hwaccel pixel
     * formats alongside the "software" one. The software pixel format may also
     * be retrieved from \ref sw_pix_fmt.
     *
     * This callback will be called when the coded frame properties (such as
     * resolution, pixel format, etc.) change and more than one output format is
     * supported for those new properties. If a hardware pixel format is chosen
     * and initialization for it fails, the callback may be called again
     * immediately.
     *
     * This callback may be called from different threads if the decoder is
     * multi-threaded, but not from more than one thread simultaneously.
     *
     * @param fmt list of formats which may be used in the current
     *            configuration, terminated by AV_PIX_FMT_NONE.
     * @warning Behavior is undefined if the callback returns a value other
     *          than one of the formats in fmt or AV_PIX_FMT_NONE.
     * @return the chosen format or AV_PIX_FMT_NONE
     */
    enum AVPixelFormat (*get_format)(struct AVCodecContext *s, const enum AVPixelFormat * fmt);

    /**
     * maximum number of B-frames between non-B-frames
     * Note: The output will be delayed by max_b_frames+1 relative to the input.
     * - encoding: Set by user.
     * - decoding: unused
     */
    int max_b_frames;

    /**
     * qscale factor between IP and B-frames
     * If > 0 then the last P-frame quantizer will be used (q= lastp_q*factor+offset).
     * If < 0 then normal ratecontrol will be done (q= -normal_q*factor+offset).
     * - encoding: Set by user.
     * - decoding: unused
     */
    float b_quant_factor;

    /**
     * qscale offset between IP and B-frames
     * - encoding: Set by user.
     * - decoding: unused
     */
    float b_quant_offset;

    /**
     * Size of the frame reordering buffer in the decoder.
     * For MPEG-2 it is 1 IPB or 0 low delay IP.
     * - encoding: Set by libavcodec.
     * - decoding: Set by libavcodec.
     */
    int has_b_frames;

    /**
     * qscale factor between P- and I-frames
     * If > 0 then the last P-frame quantizer will be used (q = lastp_q * factor + offset).
     * If < 0 then normal ratecontrol will be done (q= -normal_q*factor+offset).
     * - encoding: Set by user.
     * - decoding: unused
     */
    float i_quant_factor;

    /**
     * qscale offset between P and I-frames
     * - encoding: Set by user.
     * - decoding: unused
     */
    float i_quant_offset;

    /**
     * luminance masking (0-> disabled)
     * - encoding: Set by user.
     * - decoding: unused
     */
    float lumi_masking;

    /**
     * temporary complexity masking (0-> disabled)
     * - encoding: Set by user.
     * - decoding: unused
     */
    float temporal_cplx_masking;

    /**
     * spatial complexity masking (0-> disabled)
     * - encoding: Set by user.
     * - decoding: unused
     */
    float spatial_cplx_masking;

    /**
     * p block masking (0-> disabled)
     * - encoding: Set by user.
     * - decoding: unused
     */
    float p_masking;

    /**
     * darkness masking (0-> disabled)
     * - encoding: Set by user.
     * - decoding: unused
     */
    float dark_masking;

    /**
     * slice count
     * - encoding: Set by libavcodec.
     * - decoding: Set by user (or 0).
     */
    int slice_count;

    /**
     * slice offsets in the frame in bytes
     * - encoding: Set/allocated by libavcodec.
     * - decoding: Set/allocated by user (or NULL).
     */
    int *slice_offset;

    /**
     * sample aspect ratio (0 if unknown)
     * That is the width of a pixel divided by the height of the pixel.
     * Numerator and denominator must be relatively prime and smaller than 256 for some video standards.
     * - encoding: Set by user.
     * - decoding: Set by libavcodec.
     */
    AVRational sample_aspect_ratio;

    /**
     * motion estimation comparison function
     * - encoding: Set by user.
     * - decoding: unused
     */
    int me_cmp;
    /**
     * subpixel motion estimation comparison function
     * - encoding: Set by user.
     * - decoding: unused
     */
    int me_sub_cmp;
    /**
     * macroblock comparison function (not supported yet)
     * - encoding: Set by user.
     * - decoding: unused
     */
    int mb_cmp;

函数

函数调用逻辑慢慢补充

int avcodec_send_packet(AVCodecContext *avctx, const AVPacket *avpkt);
int avcodec_receive_frame(AVCodecContext *avctx, AVFrame *frame);
int avcodec_send_frame(AVCodecContext *avctx, const AVFrame *frame);
int avcodec_receive_packet(AVCodecContext *avctx, AVPacket *avpkt);
int avcodec_get_hw_frames_parameters(AVCodecContext *avctx,
                                     AVBufferRef *device_ref,
                                     enum AVPixelFormat hw_pix_fmt,
                                     AVBufferRef **out_frames_ref);
文章来源:https://blog.csdn.net/weixin_43360707/article/details/134948672
本文来自互联网用户投稿,该文观点仅代表作者本人,不代表本站立场。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。