AVFormatContext编解码层:理论与实战(三)

简介: AVFormatContext编解码层:理论与实战(三)

AVFormatContext编解码层:理论与实战(二)https://developer.aliyun.com/article/1473960

五、解码案例实战

下面代码使用实现了一个视频解码,将指定的视频 test.flv 解码为原始视频数据 yuv 和原始音频数据 pcm

1、示例源码

/**
 * @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;
    src_filename = "./debug/test.flv";
    video_dst_filename = "./debug/test.yuv";
    audio_dst_filename = "./debug/test.pcm";
    /* 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、运行结果

Demuxing video from file './debug/test.flv' into './debug/test.yuv'
Demuxing audio from file './debug/test.flv' into './debug/test.pcm'
video_frame n:0 coded_n:0
audio_frame n:0 nb_samples:1024 pts:0
audio_frame n:1 nb_samples:1024 pts:0.0004375
video_frame n:1 coded_n:1
audio_frame n:2 nb_samples:1024 pts:0.000895833
audio_frame n:3 nb_samples:1024 pts:0.00133333
video_frame n:2 coded_n:2
audio_frame n:4 nb_samples:1024 pts:0.00177083
audio_frame n:5 nb_samples:1024 pts:0.00222917
....
video_frame n:2931 coded_n:2931
audio_frame n:5496 nb_samples:1024 pts:2.44267
audio_frame n:5497 nb_samples:1024 pts:2.4431
audio_frame n:5498 nb_samples:1024 pts:2.44356
Demuxing succeeded.
Play the output video file with the command:
ffplay -f rawvideo -pix_fmt yuv420p -video_size 1280x720 ./debug/test.yuv
Warning: the sample format the decoder produced is planar (fltp). This example will output the first channel only.
Play the output audio file with the command:
ffplay -f f32le -ac 1 -ar 48000 ./debug/test.pcm
Input #0, flv, from './debug/test.flv':
  Metadata:
    encoder         : Lavf58.45.100
  Duration: 00:01:57.31, start: 0.000000, bitrate: 1442 kb/s
    Stream #0:0: Video: h264 (Main), yuv420p(progressive), 1280x720 [SAR 1:1 DAR 16:9], 1048 kb/s, 25 fps, 25 tbr, 1k tbn, 50 tbc
    Stream #0:1: Audio: aac (LC), 48000 Hz, 5.1, fltp, 383 kb/s

在 debug 目录下生成了原始视频数据 test.yuv 以及原始音频数据 test.pcm

在 debug 目录下打开终端使用 ffplay 播放 test.yuv:

ffplay -f rawvideo -video_size 1280x720 test.yuv

此时可以看到原视频中的视频(无音频)。

在 debug 目录下打开终端使用 ffplay 播放 test.pcm:

ffplay -f f32le -ac 1 -ar 48000 test.pcm

此时可以听到原视频中的音频(无视频)。

目录
相关文章
|
17天前
|
存储 缓存 编解码
AVFormatContext封装层:理论与实战(一)
AVFormatContext封装层:理论与实战(一)
30 1
|
17天前
|
编解码 算法 容器
AVFormatContext封装层:理论与实战(二)
AVFormatContext封装层:理论与实战(二)
29 0
|
17天前
|
编解码
AVFormatContext编解码层:理论与实战(二)
AVFormatContext编解码层:理论与实战(二)
28 0
|
17天前
|
编解码 缓存 大数据
AVFormatContext编解码层:理论与实战(一)
AVFormatContext编解码层:理论与实战(一)
35 0
|
17天前
|
大数据 测试技术 API
AVFormatContext协议层:理论与实战(一)
AVFormatContext协议层:理论与实战(一)
17 0
|
17天前
|
测试技术
AVFormatContext协议层:理论与实战(二)
AVFormatContext协议层:理论与实战(二)
17 1
|
17天前
|
测试技术
AVFormatContext协议层:理论与实战(三)
AVFormatContext协议层:理论与实战(三)
18 4
|
17天前
|
编解码 内存技术
AVFormatContext封装层:理论与实战(三)
AVFormatContext封装层:理论与实战(三)
12 1
AVFormatContext封装层:理论与实战(三)
|
9月前
|
机器学习/深度学习 存储 人工智能
解码Transformer:自注意力机制与编解码器机制详述与代码实现
解码Transformer:自注意力机制与编解码器机制详述与代码实现
146 0
|
编解码 内存技术 容器
【FFmpeg】使用 FFmpeg 处理音视频格式转换流程 ( 解复用 | 解码 | 帧处理 | 编码 | 复用 )(二)
【FFmpeg】使用 FFmpeg 处理音视频格式转换流程 ( 解复用 | 解码 | 帧处理 | 编码 | 复用 )(二)
220 0
【FFmpeg】使用 FFmpeg 处理音视频格式转换流程 ( 解复用 | 解码 | 帧处理 | 编码 | 复用 )(二)