FFmpeg AVCodec

FFmpeg編解碼

FFmpeg支持絕大多數視頻編解碼格式，如何遍歷FFmpeg編解碼器？

編解碼器以鏈表形式存儲，使用av_codec_next() 函數可以獲取編解碼器指針，當參數為NULL時，獲取第一個編解碼器指針，循環遍歷，獲取所有編解碼器信息

void avcodecInfo()
{
     av_register_all();
     AVCodec *c_temp = av_codec_next(NULL);
     while(c_temp!=NULL){
         if (c_temp->encode2!=NULL) {
             switch (c_temp->type){
                 case AVMEDIA_TYPE_VIDEO:
                     printf("[video encode] %10s\n", c_temp->name);
                     break;
                 case AVMEDIA_TYPE_AUDIO:
                     printf("[audio encode] %10s\n", c_temp->name);
                     break;
                 default:
                     printf("[other encode] %10s\n", c_temp->name);
                     break;
             }
         }
         c_temp=c_temp->next;
     }
}

AVCodec登場

遍歷FFmpeg編解碼器的時候，出現了AVCodec，什么是AVCodec？

AVCodec是存儲編解碼器信息的結構體，包含了編解碼器的基本信息，例如編解碼器的名稱，編解碼類型(video or audio)，以及編解碼的參數等。下面列舉了常用字段：

• const char *name; //編解碼器名字
• const char *long_name; //編解碼器全名
• enum AVMediaType type; //編解碼器類型
• enum AVCodecID id; //編解碼器ID
• const AVRational *supported_framerates; //支持幀率（視頻）
• const enum AVPixelFormat *pix_fmts; //支持像素格式(視頻）
• const int *supported_samplerates; //支持音頻采樣率(音頻）
• const enum AVSampleFormat *sample_fmts; //支持采樣格式(音頻)
• const uint64_t *channel_layouts; //支持聲道數（音頻）
• const AVClass *priv_class; //私有數據

AVCodec結構體

mpeg2video(video)編碼器結構體

pcm_bluray(audio)解碼器結構體

注意：在編解碼的時候，要設置為編解碼器支持的格式，例如給mpeg2video編碼器設置pix_fmts為AV_PIX_FMT_NV12，則會報出以下錯誤：

Error：Specified pixel format nv12 is invalid or not supported

AVCodec結構體內容

typedef struct AVCodec {
    /**
     * Name of the codec implementation.
     * The name is globally unique among encoders and among decoders (but an
     * encoder and a decoder can share the same name).
     * This is the primary way to find a codec from the user perspective.
     */
    const char *name;   
    /**
     * Descriptive name for the codec, meant to be more human readable than name.
     * You should use the NULL_IF_CONFIG_SMALL() macro to define it.
     */
    const char *long_name;  
    enum AVMediaType type; 
    enum AVCodecID id;       
    /**
     * Codec capabilities.
     * see AV_CODEC_CAP_*
     */
    int capabilities;
    const AVRational *supported_framerates; ///< array of supported framerates, or NULL if any, array is terminated by {0,0} 
    const enum AVPixelFormat *pix_fmts;     ///< array of supported pixel formats, or NULL if unknown, array is terminated by -1
    const int *supported_samplerates;       ///< array of supported audio samplerates, or NULL if unknown, array is terminated by 0
    const enum AVSampleFormat *sample_fmts; ///< array of supported sample formats, or NULL if unknown, array is terminated by -1
    const uint64_t *channel_layouts;         ///< array of support channel layouts, or NULL if unknown. array is terminated by 0
    uint8_t max_lowres;                     ///< maximum value for lowres supported by the decoder
    const AVClass *priv_class;              ///< AVClass for the private context
    const AVProfile *profiles;              ///< array of recognized profiles, or NULL if unknown, array is terminated by {FF_PROFILE_UNKNOWN}

    /*****************************************************************
     * No fields below this line are part of the public API. They
     * may not be used outside of libavcodec and can be changed and
     * removed at will.
     * New public fields should be added right above.
     *****************************************************************
     */
    int priv_data_size;
    struct AVCodec *next;
    /**
     * @name Frame-level threading support functions
     * @{
     */
    /**
     * If defined, called on thread contexts when they are created.
     * If the codec allocates writable tables in init(), re-allocate them here.
     * priv_data will be set to a copy of the original.
     */
    int (*init_thread_copy)(AVCodecContext *);
    /**
     * Copy necessary context variables from a previous thread context to the current one.
     * If not defined, the next thread will start automatically; otherwise, the codec
     * must call ff_thread_finish_setup().
     *
     * dst and src will (rarely) point to the same context, in which case memcpy should be skipped.
     */
    int (*update_thread_context)(AVCodecContext *dst, const AVCodecContext *src);
    /** @} */

    /**
     * Private codec-specific defaults.
     */
    const AVCodecDefault *defaults;

    /**
     * Initialize codec static data, called from avcodec_register().
     */
    void (*init_static_data)(struct AVCodec *codec);

    int (*init)(AVCodecContext *);
    int (*encode_sub)(AVCodecContext *, uint8_t *buf, int buf_size,
                      const struct AVSubtitle *sub);
    /**
     * Encode data to an AVPacket.
     *
     * @param      avctx          codec context
     * @param      avpkt          output AVPacket (may contain a user-provided buffer)
     * @param[in]  frame          AVFrame containing the raw data to be encoded
     * @param[out] got_packet_ptr encoder sets to 0 or 1 to indicate that a
     *                            non-empty packet was returned in avpkt.
     * @return 0 on success, negative error code on failure
     */
    int (*encode2)(AVCodecContext *avctx, AVPacket *avpkt, const AVFrame *frame,
                   int *got_packet_ptr);
    int (*decode)(AVCodecContext *, void *outdata, int *outdata_size, AVPacket *avpkt);
    int (*close)(AVCodecContext *);
    /**
     * Encode API with decoupled packet/frame dataflow. The API is the
     * same as the avcodec_ prefixed APIs (avcodec_send_frame() etc.), except
     * that:
     * - never called if the codec is closed or the wrong type,
     * - if AV_CODEC_CAP_DELAY is not set, drain frames are never sent,
     * - only one drain frame is ever passed down,
     */
    int (*send_frame)(AVCodecContext *avctx, const AVFrame *frame);
    int (*receive_packet)(AVCodecContext *avctx, AVPacket *avpkt);

    /**
     * Decode API with decoupled packet/frame dataflow. This function is called
     * to get one output frame. It should call ff_decode_get_packet() to obtain
     * input data.
     */
    int (*receive_frame)(AVCodecContext *avctx, AVFrame *frame);
    /**
     * Flush buffers.
     * Will be called when seeking
     */
    void (*flush)(AVCodecContext *);
    /**
     * Internal codec capabilities.
     * See FF_CODEC_CAP_* in internal.h
     */
    int caps_internal;

    /**
     * Decoding only, a comma-separated list of bitstream filters to apply to
     * packets before decoding.
     */
    const char *bsfs;
} AVCodec;

關聯類型

從AVCodec中，字段除了基本數據類型，還涉及到了其它結構體和枚舉，例如AVMediaType，AVCodecID，AVRational，AVPixelFormat，AVSampleFormat，AVClass等。

AVMediaType媒體類型，是視頻，音頻，字幕等。

enum AVMediaType {
    AVMEDIA_TYPE_UNKNOWN = -1,  ///< Usually treated as AVMEDIA_TYPE_DATA
    AVMEDIA_TYPE_VIDEO,
    AVMEDIA_TYPE_AUDIO,
    AVMEDIA_TYPE_DATA,          ///< Opaque data information usually continuous
    AVMEDIA_TYPE_SUBTITLE,
    AVMEDIA_TYPE_ATTACHMENT,    ///< Opaque data information usually sparse
    AVMEDIA_TYPE_NB
};

AVCodecID編解碼器唯一標識符

enum AVCodecID {
    AV_CODEC_ID_NONE,

    /* video codecs */
    AV_CODEC_ID_MPEG1VIDEO,
    AV_CODEC_ID_MPEG2VIDEO, ///< preferred ID for MPEG-1/2 video decoding
#if FF_API_XVMC
    AV_CODEC_ID_MPEG2VIDEO_XVMC,
#endif /* FF_API_XVMC */
    AV_CODEC_ID_H261,
    AV_CODEC_ID_H263,
    AV_CODEC_ID_RV10,
    AV_CODEC_ID_RV20,
    .......
}

AVPixelFormat視頻格式，如RGB，YUV等

enum AVPixelFormat {
    AV_PIX_FMT_NONE = -1,
    AV_PIX_FMT_YUV420P,   ///< planar YUV 4:2:0, 12bpp, (1 Cr & Cb sample per 2x2 Y samples)
    AV_PIX_FMT_YUYV422,   ///< packed YUV 4:2:2, 16bpp, Y0 Cb Y1 Cr
    AV_PIX_FMT_RGB24,     ///< packed RGB 8:8:8, 24bpp, RGBRGB...
    AV_PIX_FMT_BGR24,     ///< packed RGB 8:8:8, 24bpp, BGRBGR...
    AV_PIX_FMT_YUV422P,   ///< planar YUV 4:2:2, 16bpp, (1 Cr & Cb sample per 2x1 Y samples)
    AV_PIX_FMT_YUV444P,   ///< planar YUV 4:4:4, 24bpp, (1 Cr & Cb sample per 1x1 Y samples)
    AV_PIX_FMT_YUV410P,   ///< planar YUV 4:1:0,  9bpp, (1 Cr & Cb sample per 4x4 Y samples)
    AV_PIX_FMT_YUV411P,   ///< planar YUV 4:1:1, 12bpp, (1 Cr & Cb sample per 4x1 Y samples)
    AV_PIX_FMT_GRAY8,     ///<        Y        ,  8bpp
    AV_PIX_FMT_MONOWHITE, ///<        Y        ,  1bpp, 0 is white, 1 is black, in each byte pixels are ordered from the msb to the lsb
    AV_PIX_FMT_MONOBLACK, ///<        Y        ,  1bpp, 0 is black, 1 is white, in each byte pixels are ordered from the msb to the lsb
    AV_PIX_FMT_PAL8,      ///< 8 bits with AV_PIX_FMT_RGB32 palette
    AV_PIX_FMT_YUVJ420P,  ///< planar YUV 4:2:0, 12bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV420P and setting color_range
    AV_PIX_FMT_YUVJ422P,  ///< planar YUV 4:2:2, 16bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV422P and setting color_range
    AV_PIX_FMT_YUVJ444P,  ///< planar YUV 4:4:4, 24bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV444P and setting color_range
#if FF_API_XVMC
    AV_PIX_FMT_XVMC_MPEG2_MC,///< XVideo Motion Acceleration via common packet passing
    AV_PIX_FMT_XVMC_MPEG2_IDCT,
    AV_PIX_FMT_XVMC = AV_PIX_FMT_XVMC_MPEG2_IDCT,
#endif /* FF_API_XVMC */
    AV_PIX_FMT_UYVY422,   
    ......
}

AVSampleFormat采樣格式，其中帶P結尾的為平面格式。例如對於雙通道音頻，設左通道為L，右通道為R，如果是平面格式，在內存中的排列為LLLLLL……RRRRRR……，對於非平面格式，內存中排列為LRLRLRLRLR……

enum AVSampleFormat {
    AV_SAMPLE_FMT_NONE = -1,
    AV_SAMPLE_FMT_U8,          ///< unsigned 8 bits
    AV_SAMPLE_FMT_S16,         ///< signed 16 bits
    AV_SAMPLE_FMT_S32,         ///< signed 32 bits
    AV_SAMPLE_FMT_FLT,         ///< float
    AV_SAMPLE_FMT_DBL,         ///< double

    AV_SAMPLE_FMT_U8P,         ///< unsigned 8 bits, planar
    AV_SAMPLE_FMT_S16P,        ///< signed 16 bits, planar
    AV_SAMPLE_FMT_S32P,        ///< signed 32 bits, planar
    AV_SAMPLE_FMT_FLTP,        ///< float, planar
    AV_SAMPLE_FMT_DBLP,        ///< double, planar
    AV_SAMPLE_FMT_S64,         ///< signed 64 bits
    AV_SAMPLE_FMT_S64P,        ///< signed 64 bits, planar

    AV_SAMPLE_FMT_NB           ///< Number of sample formats. DO NOT USE if linking dynamically
};