FFmpeg常用API与示例（三）—— 音视频解码与编码

编解码层

1.解码

(1) 注册所有容器格式和 CODEC:av_register_all()

(2) 打开文件:av_open_input_file()

(3) 从文件中提取流信息:av_find_stream_info()

(4) 穷举所有的流，查找其中种类为 CODEC_TYPE_VIDEO

(5) 查找对应的解码器:avcodec_find_decoder()

(6) 打开编解码器:avcodec_open()

(7) 为解码帧分配内存:avcodec_alloc_frame()

(8) 不停地从码流中提取出帧数据:av_read_frame()

(9) 判断帧的类型，对于视频帧调用:avcodec_decode_video()

(10) 解码完后，释放解码器:avcodec_close()

(11) 关闭输入文件:av_close_input_file()

/**
 * @file
 * Demuxing and decoding example.
 *
 * Show how to use the libavformat and libavcodec API to demux and
 * decode audio and video data.
 * @example demuxing_decoding.c
 */

#include <libavutil/imgutils.h>
#include <libavutil/samplefmt.h>
#include <libavutil/timestamp.h>
#include <libavformat/avformat.h>

static AVFormatContext *fmt_ctx = NULL;
static AVCodecContext *video_dec_ctx = NULL, *audio_dec_ctx;
static int width, height;
static enum AVPixelFormat pix_fmt;
static AVStream *video_stream = NULL, *audio_stream = NULL;
static const char *src_filename = NULL;
static const char *video_dst_filename = NULL;
static const char *audio_dst_filename = NULL;
static FILE *video_dst_file = NULL;
static FILE *audio_dst_file = NULL;

static uint8_t *video_dst_data[4] = {NULL};
static int      video_dst_linesize[4];
static int video_dst_bufsize;

static int video_stream_idx = -1, audio_stream_idx = -1;
static AVFrame *frame = NULL;
static AVPacket pkt;
static int video_frame_count = 0;
static int audio_frame_count = 0;

static int output_video_frame(AVFrame *frame)
{
    if (frame->width != width || frame->height != height ||
        frame->format != pix_fmt) {
        /* To handle this change, one could call av_image_alloc again and
         * decode the following frames into another rawvideo file. */
        fprintf(stderr, "Error: Width, height and pixel format have to be "
                "constant in a rawvideo file, but the width, height or "
                "pixel format of the input video changed:\n"
                "old: width = %d, height = %d, format = %s\n"
                "new: width = %d, height = %d, format = %s\n",
                width, height, av_get_pix_fmt_name(pix_fmt),
                frame->width, frame->height,
                av_get_pix_fmt_name(frame->format));
        return -1;
    }

    printf("video_frame n:%d coded_n:%d\n",
           video_frame_count++, frame->coded_picture_number);

    /* copy decoded frame to destination buffer:
     * this is required since rawvideo expects non aligned data */
    av_image_copy(video_dst_data, video_dst_linesize,
                  (const uint8_t **)(frame->data), frame->linesize,
                  pix_fmt, width, height);

    /* write to rawvideo file */
    fwrite(video_dst_data[0], 1, video_dst_bufsize, video_dst_file);
    return 0;
}

static int output_audio_frame(AVFrame *frame)
{
    size_t unpadded_linesize = frame->nb_samples * av_get_bytes_per_sample(frame->format);
    printf("audio_frame n:%d nb_samples:%d pts:%s\n",
           audio_frame_count++, frame->nb_samples,
           av_ts2timestr(frame->pts, &audio_dec_ctx->time_base));

    /* Write the raw audio data samples of the first plane. This works
     * fine for packed formats (e.g. AV_SAMPLE_FMT_S16). However,
     * most audio decoders output planar audio, which uses a separate
     * plane of audio samples for each channel (e.g. AV_SAMPLE_FMT_S16P).
     * In other words, this code will write only the first audio channel
     * in these cases.
     * You should use libswresample or libavfilter to convert the frame
     * to packed data. */
    fwrite(frame->extended_data[0], 1, unpadded_linesize, audio_dst_file);

    return 0;
}

static int decode_packet(AVCodecContext *dec, const AVPacket *pkt)
{
    int ret = 0;

    // submit the packet to the decoder
    ret = avcodec_send_packet(dec, pkt);
    if (ret < 0) {
        fprintf(stderr, "Error submitting a packet for decoding (%s)\n", av_err2str(ret));
        return ret;
    }

    // get all the available frames from the decoder
    while (ret >= 0) {
        ret = avcodec_receive_frame(dec, frame);
        if (ret < 0) {
            // those two return values are special and mean there is no output
            // frame available, but there were no errors during decoding
            if (ret == AVERROR_EOF || ret == AVERROR(EAGAIN))
                return 0;

            fprintf(stderr, "Error during decoding (%s)\n", av_err2str(ret));
            return ret;
        }

        // write the frame data to output file
        if (dec->codec->type == AVMEDIA_TYPE_VIDEO)
            ret = output_video_frame(frame);
        else
            ret = output_audio_frame(frame);

        av_frame_unref(frame);
        if (ret < 0)
            return ret;
    }

    return 0;
}

static int open_codec_context(int *stream_idx,
                              AVCodecContext **dec_ctx, AVFormatContext *fmt_ctx, enum AVMediaType type)
{
    int ret, stream_index;
    AVStream *st;
    AVCodec *dec = NULL;
    AVDictionary *opts = NULL;

    ret = av_find_best_stream(fmt_ctx, type, -1, -1, NULL, 0);
    if (ret < 0) {
        fprintf(stderr, "Could not find %s stream in input file '%s'\n",
                av_get_media_type_string(type), src_filename);
        return ret;
    } else {
        stream_index = ret;
        st = fmt_ctx->streams[stream_index];

        /* find decoder for the stream */
        dec = avcodec_find_decoder(st->codecpar->codec_id);
        if (!dec) {
            fprintf(stderr, "Failed to find %s codec\n",
                    av_get_media_type_string(type));
            return AVERROR(EINVAL);
        }

        /* Allocate a codec context for the decoder */
        *dec_ctx = avcodec_alloc_context3(dec);
        if (!*dec_ctx) {
            fprintf(stderr, "Failed to allocate the %s codec context\n",
                    av_get_media_type_string(type));
            return AVERROR(ENOMEM);
        }

        /* Copy codec parameters from input stream to output codec context */
        if ((ret = avcodec_parameters_to_context(*dec_ctx, st->codecpar)) < 0) {
            fprintf(stderr, "Failed to copy %s codec parameters to decoder context\n",
                    av_get_media_type_string(type));
            return ret;
        }

        /* Init the decoders */
        if ((ret = avcodec_open2(*dec_ctx, dec, &opts)) < 0) {
            fprintf(stderr, "Failed to open %s codec\n",
                    av_get_media_type_string(type));
            return ret;
        }
        *stream_idx = stream_index;
    }

    return 0;
}

static int get_format_from_sample_fmt(const char **fmt,
                                      enum AVSampleFormat sample_fmt)
{
    int i;
    struct sample_fmt_entry {
        enum AVSampleFormat sample_fmt; const char *fmt_be, *fmt_le;
    } sample_fmt_entries[] = {
        { AV_SAMPLE_FMT_U8,  "u8",    "u8"    },
        { AV_SAMPLE_FMT_S16, "s16be", "s16le" },
        { AV_SAMPLE_FMT_S32, "s32be", "s32le" },
        { AV_SAMPLE_FMT_FLT, "f32be", "f32le" },
        { AV_SAMPLE_FMT_DBL, "f64be", "f64le" },
    };
    *fmt = NULL;

    for (i = 0; i < FF_ARRAY_ELEMS(sample_fmt_entries); i++) {
        struct sample_fmt_entry *entry = &sample_fmt_entries[i];
        if (sample_fmt == entry->sample_fmt) {
            *fmt = AV_NE(entry->fmt_be, entry->fmt_le);
            return 0;
        }
    }

    fprintf(stderr,
            "sample format %s is not supported as output format\n",
            av_get_sample_fmt_name(sample_fmt));
    return -1;
}

int main (int argc, char **argv)
{
    int ret = 0;

    if (argc != 4) {
        fprintf(stderr, "usage: %s  input_file video_output_file audio_output_file\n"
                "API example program to show how to read frames from an input file.\n"
                "This program reads frames from a file, decodes them, and writes decoded\n"
                "video frames to a rawvideo file named video_output_file, and decoded\n"
                "audio frames to a rawaudio file named audio_output_file.\n",
                argv[0]);
        exit(1);
    }
    src_filename = argv[1];
    video_dst_filename = argv[2];
    audio_dst_filename = argv[3];

    /* open input file, and allocate format context */
    if (avformat_open_input(&fmt_ctx, src_filename, NULL, NULL) < 0) {
        fprintf(stderr, "Could not open source file %s\n", src_filename);
        exit(1);
    }

    /* retrieve stream information */
    if (avformat_find_stream_info(fmt_ctx, NULL) < 0) {
        fprintf(stderr, "Could not find stream information\n");
        exit(1);
    }

    if (open_codec_context(&video_stream_idx, &video_dec_ctx, fmt_ctx, AVMEDIA_TYPE_VIDEO) >= 0) {
        video_stream = fmt_ctx->streams[video_stream_idx];

        video_dst_file = fopen(video_dst_filename, "wb");
        if (!video_dst_file) {
            fprintf(stderr, "Could not open destination file %s\n", video_dst_filename);
            ret = 1;
            goto end;
        }

        /* allocate image where the decoded image will be put */
        width = video_dec_ctx->width;
        height = video_dec_ctx->height;
        pix_fmt = video_dec_ctx->pix_fmt;
        ret = av_image_alloc(video_dst_data, video_dst_linesize,
                             width, height, pix_fmt, 1);
        if (ret < 0) {
            fprintf(stderr, "Could not allocate raw video buffer\n");
            goto end;
        }
        video_dst_bufsize = ret;
    }

    if (open_codec_context(&audio_stream_idx, &audio_dec_ctx, fmt_ctx, AVMEDIA_TYPE_AUDIO) >= 0) {
        audio_stream = fmt_ctx->streams[audio_stream_idx];
        audio_dst_file = fopen(audio_dst_filename, "wb");
        if (!audio_dst_file) {
            fprintf(stderr, "Could not open destination file %s\n", audio_dst_filename);
            ret = 1;
            goto end;
        }
    }

    /* dump input information to stderr */
    av_dump_format(fmt_ctx, 0, src_filename, 0);

    if (!audio_stream && !video_stream) {
        fprintf(stderr, "Could not find audio or video stream in the input, aborting\n");
        ret = 1;
        goto end;
    }

    frame = av_frame_alloc();
    if (!frame) {
        fprintf(stderr, "Could not allocate frame\n");
        ret = AVERROR(ENOMEM);
        goto end;
    }

    /* initialize packet, set data to NULL, let the demuxer fill it */
    av_init_packet(&pkt);
    pkt.data = NULL;
    pkt.size = 0;

    if (video_stream)
        printf("Demuxing video from file '%s' into '%s'\n", src_filename, video_dst_filename);
    if (audio_stream)
        printf("Demuxing audio from file '%s' into '%s'\n", src_filename, audio_dst_filename);

    /* read frames from the file */
    while (av_read_frame(fmt_ctx, &pkt) >= 0) {
        // check if the packet belongs to a stream we are interested in, otherwise
        // skip it
        if (pkt.stream_index == video_stream_idx)
            ret = decode_packet(video_dec_ctx, &pkt);
        else if (pkt.stream_index == audio_stream_idx)
            ret = decode_packet(audio_dec_ctx, &pkt);
        av_packet_unref(&pkt);
        if (ret < 0)
            break;
    }

    /* flush the decoders */
    if (video_dec_ctx)
        decode_packet(video_dec_ctx, NULL);
    if (audio_dec_ctx)
        decode_packet(audio_dec_ctx, NULL);

    printf("Demuxing succeeded.\n");

    if (video_stream) {
        printf("Play the output video file with the command:\n"
               "ffplay -f rawvideo -pix_fmt %s -video_size %dx%d %s\n",
               av_get_pix_fmt_name(pix_fmt), width, height,
               video_dst_filename);
    }

    if (audio_stream) {
        enum AVSampleFormat sfmt = audio_dec_ctx->sample_fmt;
        int n_channels = audio_dec_ctx->channels;
        const char *fmt;

        if (av_sample_fmt_is_planar(sfmt)) {
            const char *packed = av_get_sample_fmt_name(sfmt);
            printf("Warning: the sample format the decoder produced is planar "
                   "(%s). This example will output the first channel only.\n",
                   packed ? packed : "?");
            sfmt = av_get_packed_sample_fmt(sfmt);
            n_channels = 1;
        }

        if ((ret = get_format_from_sample_fmt(&fmt, sfmt)) < 0)
            goto end;

        printf("Play the output audio file with the command:\n"
               "ffplay -f %s -ac %d -ar %d %s\n",
               fmt, n_channels, audio_dec_ctx->sample_rate,
               audio_dst_filename);
    }

end:
    avcodec_free_context(&video_dec_ctx);
    avcodec_free_context(&audio_dec_ctx);
    avformat_close_input(&fmt_ctx);
    if (video_dst_file)
        fclose(video_dst_file);
    if (audio_dst_file)
        fclose(audio_dst_file);
    av_frame_free(&frame);
    av_free(video_dst_data[0]);

    return ret < 0;
}

2.编码

大流程可以划分为输入、输出、转码、播放四大块。

其中转码涉及比较多的处理环节，从图中可以看出，转码功能在整个功能图中占比很大。转码的核心功能在解码和编码两个部分，但在一个可用的示例程序中，编码解码与输入输出是难以分割的。

解复用器为解码器提供输入，解码器会输出原始帧，对原始帧可进行各种复杂的滤镜处理，滤镜处理后的帧经编码器生成编码帧，多路流的编码帧经复用器输出到输出文件。

/**
 * @file
 * video encoding with libavcodec API example
 *
 * @example encode_video.c
 */

#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#include <libavcodec/avcodec.h>

#include <libavutil/opt.h>
#include <libavutil/imgutils.h>

static void encode(AVCodecContext *enc_ctx, AVFrame *frame, AVPacket *pkt,
                   FILE *outfile)
{
    int ret;

    /* send the frame to the encoder */
    if (frame)
        printf("Send frame %3"PRId64"\n", frame->pts);

    ret = avcodec_send_frame(enc_ctx, frame);
    if (ret < 0) {
        fprintf(stderr, "Error sending a frame for encoding\n");
        exit(1);
    }

    while (ret >= 0) {
        ret = avcodec_receive_packet(enc_ctx, pkt);
        if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
            return;
        else if (ret < 0) {
            fprintf(stderr, "Error during encoding\n");
            exit(1);
        }

        printf("Write packet %3"PRId64" (size=%5d)\n", pkt->pts, pkt->size);
        fwrite(pkt->data, 1, pkt->size, outfile);
        av_packet_unref(pkt);
    }
}

int mainsse22(int argc, char **argv)
{
    const char *filename, *codec_name;
    const AVCodec *codec;
    AVCodecContext *c= NULL;
    int i, ret, x, y;
    FILE *f;
    AVFrame *frame;
    AVPacket *pkt;
    uint8_t endcode[] = { 0, 0, 1, 0xb7 };

    if (argc <= 2) {
        fprintf(stderr, "Usage: %s <output file> <codec name>\n", argv[0]);
        exit(0);
    }
    filename = argv[1];
    codec_name = argv[2];

    /* find the mpeg1video encoder */
    codec = avcodec_find_encoder_by_name(codec_name);
    if (!codec) {
        fprintf(stderr, "Codec '%s' not found\n", codec_name);
        exit(1);
    }

    c = avcodec_alloc_context3(codec);
    if (!c) {
        fprintf(stderr, "Could not allocate video codec context\n");
        exit(1);
    }

    pkt = av_packet_alloc();
    if (!pkt)
        exit(1);

    /* put sample parameters */
    c->bit_rate = 400000;
    /* resolution must be a multiple of two */
    c->width = 352;
    c->height = 288;
    /* frames per second */
    c->time_base = (AVRational){1, 25};
    c->framerate = (AVRational){25, 1};

    /* emit one intra frame every ten frames
     * check frame pict_type before passing frame
     * to encoder, if frame->pict_type is AV_PICTURE_TYPE_I
     * then gop_size is ignored and the output of encoder
     * will always be I frame irrespective to gop_size
     */
    c->gop_size = 10;
    c->max_b_frames = 1;
    c->pix_fmt = AV_PIX_FMT_YUV420P;

    if (codec->id == AV_CODEC_ID_H264)
        av_opt_set(c->priv_data, "preset", "slow", 0);

    /* open it */
    ret = avcodec_open2(c, codec, NULL);
    if (ret < 0) {
        fprintf(stderr, "Could not open codec: %s\n", av_err2str(ret));
        exit(1);
    }

    f = fopen(filename, "wb");
    if (!f) {
        fprintf(stderr, "Could not open %s\n", filename);
        exit(1);
    }

    frame = av_frame_alloc();
    if (!frame) {
        fprintf(stderr, "Could not allocate video frame\n");
        exit(1);
    }
    frame->format = c->pix_fmt;
    frame->width  = c->width;
    frame->height = c->height;

    ret = av_frame_get_buffer(frame, 0);
    if (ret < 0) {
        fprintf(stderr, "Could not allocate the video frame data\n");
        exit(1);
    }

    /* encode 1 second of video */
    for (i = 0; i < 25; i++) {
        fflush(stdout);

        /* make sure the frame data is writable */
        ret = av_frame_make_writable(frame);
        if (ret < 0)
            exit(1);

        /* prepare a dummy image */
        /* Y */
        for (y = 0; y < c->height; y++) {
            for (x = 0; x < c->width; x++) {
                frame->data[0][y * frame->linesize[0] + x] = x + y + i * 3;
            }
        }

        /* Cb and Cr */
        for (y = 0; y < c->height/2; y++) {
            for (x = 0; x < c->width/2; x++) {
                frame->data[1][y * frame->linesize[1] + x] = 128 + y + i * 2;
                frame->data[2][y * frame->linesize[2] + x] = 64 + x + i * 5;
            }
        }

        frame->pts = i;

        /* encode the image */
        encode(c, frame, pkt, f);
    }

    /* flush the encoder */
    encode(c, NULL, pkt, f);

    /* add sequence end code to have a real MPEG file */
    if (codec->id == AV_CODEC_ID_MPEG1VIDEO || codec->id == AV_CODEC_ID_MPEG2VIDEO)
        fwrite(endcode, 1, sizeof(endcode), f);
    fclose(f);

    avcodec_free_context(&c);
    av_frame_free(&frame);
    av_packet_free(&pkt);

    return 0;
}