[Libav-user] Scaled down h264 video has almost same size as normal sized video; why?

Taha Ansari mtaha.ansari at gmail.com
Tue Dec 18 12:07:29 CET 2012


Hi,

I have modified muxer program that saves h264 video to disk of 01 minute
duration, as follows:

******************************
************************************************************
/*
 * Copyright (c) 2001 Fabrice Bellard
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
copy
 * of this software and associated documentation files (the "Software"), to
deal
 * in the Software without restriction, including without limitation the
rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included
in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 */

/**
 * @file
 * libavcodec API use example.
 *
 * Note that libavcodec only handles codecs (mpeg, mpeg4, etc...),
 * not file formats (avi, vob, mp4, mov, mkv, mxf, flv, mpegts, mpegps,
etc...). See library 'libavformat' for the
 * format handling
 */

#include <Windows.h>
#include <math.h>
extern "C"
{
#include "libavcodec/avcodec.h"
#include "libavformat/avformat.h"
#include "libavdevice/avdevice.h"
#include "libswscale/swscale.h"
#include "libavutil/dict.h"
#include "libavutil/error.h"
#include "libavutil/opt.h"
}

#define DECODER_WIDTH    640
#define DECODER_HEIGHT    480

#define ENCODER_WIDTH    640
#define ENCODER_HEIGHT    480

/* 5 seconds stream duration */
#define STREAM_DURATION   60.0
#define STREAM_FRAME_RATE 25 /* 25 images/s */
#define STREAM_NB_FRAMES  ((int)(STREAM_DURATION * STREAM_FRAME_RATE))
#define STREAM_PIX_FMT    AV_PIX_FMT_YUV420P /* default pix_fmt */

static int sws_flags = SWS_BICUBIC;

/**************************************************************/
/* audio output */

static float t, tincr, tincr2;
static int16_t *samples;
static int audio_input_frame_size;

/* Add an output stream. */
static AVStream *add_stream(AVFormatContext *oc, AVCodec **codec,
                            enum AVCodecID codec_id)
{
    AVCodecContext *c;
    AVStream *st;

    /* find the encoder */
    *codec = avcodec_find_encoder(codec_id);
    if (!(*codec)) {
        fprintf(stderr, "Could not find codec\n");
        exit(1);
    }

    st = avformat_new_stream(oc, *codec);
    if (!st) {
        fprintf(stderr, "Could not allocate stream\n");
        exit(1);
    }
    st->id = oc->nb_streams-1;
    c = st->codec;

    switch ((*codec)->type) {
    case AVMEDIA_TYPE_AUDIO:
        st->id = 1;
        c->sample_fmt  = AV_SAMPLE_FMT_S16;
        c->bit_rate    = 64000;
        c->sample_rate = 44100;
        c->channels    = 2;
        break;

    case AVMEDIA_TYPE_VIDEO:
        avcodec_get_context_defaults3(c, *codec);
        c->codec_id = codec_id;

        c->bit_rate = 400000;
        /* Resolution must be a multiple of two. */
        c->width    = ENCODER_WIDTH;
        c->height   = ENCODER_HEIGHT;
        /* timebase: 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
         * identical to 1. */
        c->time_base.den = STREAM_FRAME_RATE;
        c->time_base.num = 1;
        c->gop_size      = 12; /* emit one intra frame every twelve frames
at most */
        c->pix_fmt       = STREAM_PIX_FMT;
        if (c->codec_id == AV_CODEC_ID_MPEG2VIDEO) {
            /* just for testing, we also add B frames */
            c->max_b_frames = 2;
        }
        if (c->codec_id == AV_CODEC_ID_MPEG1VIDEO) {
            /* Needed to avoid using macroblocks in which some coeffs
overflow.
             * This does not happen with normal video, it just happens here
as
             * the motion of the chroma plane does not match the luma
plane. */
            c->mb_decision = 2;
        }
    break;

    default:
        break;
    }

    /* Some formats want stream headers to be separate. */
    if (oc->oformat->flags & AVFMT_GLOBALHEADER)
        c->flags |= CODEC_FLAG_GLOBAL_HEADER;

    return st;
}

/**************************************************************/
/* audio output */


static void open_audio(AVFormatContext *oc, AVCodec *codec, AVStream *st)
{
    AVCodecContext *c;

    c = st->codec;

    /* open it */
    if (avcodec_open2(c, codec, NULL) < 0) {
        fprintf(stderr, "Could not open audio codec\n");
        exit(1);
    }

    /* init signal generator */
    t     = 0;
    tincr = 2 * M_PI * 110.0 / c->sample_rate;
    /* increment frequency by 110 Hz per second */
    tincr2 = 2 * M_PI * 110.0 / c->sample_rate / c->sample_rate;

    if (c->codec->capabilities & CODEC_CAP_VARIABLE_FRAME_SIZE)
        audio_input_frame_size = 10000;
    else
        audio_input_frame_size = c->frame_size;
    samples = (int16_t *) av_malloc(audio_input_frame_size *
                        av_get_bytes_per_sample(c->sample_fmt) *
                        c->channels);
    if (!samples) {
        fprintf(stderr, "Could not allocate audio samples buffer\n");
        exit(1);
    }
}

/* Prepare a 16 bit dummy audio frame of 'frame_size' samples and
 * 'nb_channels' channels. */
static void get_audio_frame(int16_t *samples, int frame_size, int
nb_channels)
{
    int j, i, v;
    int16_t *q;

    q = samples;
    for (j = 0; j < frame_size; j++) {
        v = (int)(sin(t) * 10000);
        for (i = 0; i < nb_channels; i++)
            *q++ = v;
        t     += tincr;
        tincr += tincr2;
    }
}

static void write_audio_frame(AVFormatContext *oc, AVStream *st)
{
    AVCodecContext *c;
    AVPacket pkt = { 0 }; // data and size must be 0;
    AVFrame *frame = avcodec_alloc_frame();
    int got_packet, ret;

    av_init_packet(&pkt);
    c = st->codec;

    get_audio_frame(samples, audio_input_frame_size, c->channels);
    frame->nb_samples = audio_input_frame_size;
    avcodec_fill_audio_frame(frame, c->channels, c->sample_fmt,
                             (uint8_t *)samples,
                             audio_input_frame_size *
                             av_get_bytes_per_sample(c->sample_fmt) *
                             c->channels, 1);

    ret = avcodec_encode_audio2(c, &pkt, frame, &got_packet);
    if (ret < 0) {
        fprintf(stderr, "Error encoding audio frame\n");
        exit(1);
    }

    if (!got_packet)
        return;

    pkt.stream_index = st->index;

    /* Write the compressed frame to the media file. */
    if (av_interleaved_write_frame(oc, &pkt) != 0) {
        fprintf(stderr, "Error while writing audio frame\n");
        exit(1);
    }
    avcodec_free_frame(&frame);
}

static void close_audio(AVFormatContext *oc, AVStream *st)
{
    avcodec_close(st->codec);

    av_free(samples);
}

/**************************************************************/
/* video output */

static AVFrame *frame;
static AVPicture src_picture, dst_picture;
static int frame_count;

static void open_video(AVFormatContext *oc, AVCodec *codec, AVStream *st)
{
    int ret;
    AVCodecContext *c = st->codec;

    /* open the codec */
    if (avcodec_open2(c, codec, NULL) < 0) {
        fprintf(stderr, "Could not open video codec\n");
        exit(1);
    }

    /* allocate and init a re-usable frame */
    frame = avcodec_alloc_frame();
    if (!frame) {
        fprintf(stderr, "Could not allocate video frame\n");
        exit(1);
    }

    /* Allocate the encoded raw picture. */
    ret = avpicture_alloc(&dst_picture, c->pix_fmt, c->width, c->height);
    if (ret < 0) {
        fprintf(stderr, "Could not allocate picture\n");
        exit(1);
    }

    /* If the output format is not YUV420P, then a temporary YUV420P
     * picture is needed too. It is then converted to the required
     * output format. */
    if (1) {
        ret = avpicture_alloc(&src_picture, PIX_FMT_YUV420P, DECODER_WIDTH,
DECODER_HEIGHT);
        if (ret < 0) {
            fprintf(stderr, "Could not allocate temporary picture\n");
            exit(1);
        }
    }
    //if (c->pix_fmt != AV_PIX_FMT_YUV420P) {
    //    ret = avpicture_alloc(&src_picture, AV_PIX_FMT_YUV420P, c->width,
c->height);
    //    if (ret < 0) {
    //        fprintf(stderr, "Could not allocate temporary picture\n");
    //        exit(1);
    //    }
    //}

    /* copy data and linesize picture pointers to frame */
    *((AVPicture *)frame) = dst_picture;
}

/* Prepare a dummy image. */
static void fill_yuv_image(AVPicture *pict, int frame_index,
                           int width, int height)
{
    int x, y, i;

    i = frame_index;

    /* Y */
    for (y = 0; y < height; y++)
        for (x = 0; x < width; x++)
            pict->data[0][y * pict->linesize[0] + x] = x + y + i * 3;

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

static void write_video_frame(AVFormatContext *oc, AVStream *st)
{
    int ret;
    static struct SwsContext *sws_ctx;
    AVCodecContext *c = st->codec;

    if (frame_count >= STREAM_NB_FRAMES) {
        /* No more frames to compress. The codec has a latency of a few
         * frames if using B-frames, so we get the last frames by
         * passing the same picture again. */
    } else {
        if (c->pix_fmt != AV_PIX_FMT_YUV420P) {
            /* as we only generate a YUV420P picture, we must convert it
             * to the codec pixel format if needed */
            if (!sws_ctx) {
                sws_ctx = sws_getContext(c->width, c->height,
AV_PIX_FMT_YUV420P,
                                         c->width, c->height, c->pix_fmt,
                                         sws_flags, NULL, NULL, NULL);
                if (!sws_ctx) {
                    fprintf(stderr,
                            "Could not initialize the conversion
context\n");
                    exit(1);
                }
            }
            fill_yuv_image(&src_picture, frame_count, c->width, c->height);
            sws_scale(sws_ctx,
                      (const uint8_t * const *)src_picture.data,
src_picture.linesize,
                      0, c->height, dst_picture.data, dst_picture.linesize);
        } else
        {
             /* as we only generate a YUV420P picture, we must convert it
            * to the codec pixel format if needed */
            if (!sws_ctx)
            {
                sws_ctx = sws_getContext( DECODER_WIDTH, DECODER_HEIGHT,
PIX_FMT_YUV420P,
                    c->width, c->height, c->pix_fmt,
                    sws_flags, NULL, NULL, NULL);
                if (!sws_ctx)
                {
                    fprintf(stderr,
                        "Could not initialize the conversion context\n");
                    exit(1);
                }
            }
            fill_yuv_image(&src_picture, frame_count, DECODER_WIDTH,
DECODER_HEIGHT);
            sws_scale(sws_ctx,
                (const uint8_t * const *)src_picture.data,
src_picture.linesize,
                0, DECODER_WIDTH, dst_picture.data, dst_picture.linesize);
            //fill_yuv_image(&dst_picture, frame_count, c->width,
c->height);
        }
    }

    if (oc->oformat->flags & AVFMT_RAWPICTURE) {
        /* Raw video case - directly store the picture in the packet */
        AVPacket pkt;
        av_init_packet(&pkt);

        pkt.flags        |= AV_PKT_FLAG_KEY;
        pkt.stream_index  = st->index;
        pkt.data          = dst_picture.data[0];
        pkt.size          = sizeof(AVPicture);

        ret = av_interleaved_write_frame(oc, &pkt);
    } else {
        /* encode the image */
        AVPacket pkt;
        int got_output;

        av_init_packet(&pkt);
        pkt.data = NULL;    // packet data will be allocated by the encoder
        pkt.size = 0;

        ret = avcodec_encode_video2(c, &pkt, frame, &got_output);
        if (ret < 0) {
            fprintf(stderr, "Error encoding video frame\n");
            exit(1);
        }

        /* If size is zero, it means the image was buffered. */
        if (got_output) {
            if (c->coded_frame->key_frame)
                pkt.flags |= AV_PKT_FLAG_KEY;

            pkt.stream_index = st->index;

            /* Write the compressed frame to the media file. */
            ret = av_interleaved_write_frame(oc, &pkt);
        } else {
            ret = 0;
        }
    }
    if (ret != 0) {
        fprintf(stderr, "Error while writing video frame\n");
        exit(1);
    }
    frame_count++;
}

static void close_video(AVFormatContext *oc, AVStream *st)
{
    avcodec_close(st->codec);
    av_free(src_picture.data[0]);
    av_free(dst_picture.data[0]);
    av_free(frame);
}

/**************************************************************/
/* media file output */

int main(int argc, char **argv)
{
    char filename[99]="";
    AVOutputFormat *fmt;
    AVFormatContext *oc;
    AVStream *audio_st, *video_st;
    AVCodec *audio_codec, *video_codec;
    double audio_pts, video_pts;
    int i;

    /* Initialize libavcodec, and register all codecs and formats. */
    av_register_all();

    if (argc != 2) {
        printf("usage: %s output_file\n"
               "API example program to output a media file with
libavformat.\n"
               "This program generates a synthetic audio and video stream,
encodes and\n"
               "muxes them into a file named output_file.\n"
               "The output format is automatically guessed according to the
file extension.\n"
               "Raw images can also be output by using '%%d' in the
filename.\n"
               "\n", argv[0]);
        return 1;
    }

    strcpy(filename,"a.h264");
    /* allocate the output media context */
    avformat_alloc_output_context2(&oc, NULL, NULL, filename);
    if (!oc) {
        printf("Could not deduce output format from file extension: using
MPEG.\n");
        avformat_alloc_output_context2(&oc, NULL, "mpeg", filename);
    }
    if (!oc) {
        return 1;
    }
    fmt = oc->oformat;

    /* Add the audio and video streams using the default format codecs
     * and initialize the codecs. */
    video_st = NULL;
    audio_st = NULL;

    if (fmt->video_codec != AV_CODEC_ID_NONE) {
        video_st = add_stream(oc, &video_codec, fmt->video_codec);
    }
    if (fmt->audio_codec != AV_CODEC_ID_NONE) {
        audio_st = add_stream(oc, &audio_codec, fmt->audio_codec);
    }

    /* Now that all the parameters are set, we can open the audio and
     * video codecs and allocate the necessary encode buffers. */
    if (video_st)
        open_video(oc, video_codec, video_st);
    if (audio_st)
        open_audio(oc, audio_codec, audio_st);

    av_dump_format(oc, 0, filename, 1);

    /* open the output file, if needed */
    if (!(fmt->flags & AVFMT_NOFILE)) {
        if (avio_open(&oc->pb, filename, AVIO_FLAG_WRITE) < 0) {
            fprintf(stderr, "Could not open '%s'\n", filename);
            return 1;
        }
    }

    /* Write the stream header, if any. */
    if (avformat_write_header(oc, NULL) < 0) {
        fprintf(stderr, "Error occurred when opening output file\n");
        return 1;
    }

    if (frame)
        frame->pts = 0;
    for (;;) {
        /* Compute current audio and video time. */
        if (audio_st)
            audio_pts = (double)audio_st->pts.val * audio_st->time_base.num
/ audio_st->time_base.den;
        else
            audio_pts = 0.0;

        if (video_st)
            video_pts = (double)video_st->pts.val * video_st->time_base.num
/
                        video_st->time_base.den;
        else
            video_pts = 0.0;

        if ((!audio_st || audio_pts >= STREAM_DURATION) &&
            (!video_st || video_pts >= STREAM_DURATION))
            break;

        /* write interleaved audio and video frames */
        if (!video_st || (video_st && audio_st && audio_pts < video_pts)) {
            write_audio_frame(oc, audio_st);
        } else {
            write_video_frame(oc, video_st);
            frame->pts += av_rescale_q(1, video_st->codec->time_base,
video_st->time_base);
        }
        Sleep(40);
    }

    /* Write the trailer, if any. The trailer must be written before you
     * close the CodecContexts open when you wrote the header; otherwise
     * av_write_trailer() may try to use memory that was freed on
     * av_codec_close(). */
    av_write_trailer(oc);

    /* Close each codec. */
    if (video_st)
        close_video(oc, video_st);
    if (audio_st)
        close_audio(oc, audio_st);

    /* Free the streams. */
    for (i = 0; i < oc->nb_streams; i++) {
        av_freep(&oc->streams[i]->codec);
        av_freep(&oc->streams[i]);
    }

    if (!(fmt->flags & AVFMT_NOFILE))
        /* Close the output file. */
        avio_close(oc->pb);

    /* free the stream */
    av_free(oc);

    return 0;
}
*******************************************************************************

After first run, if we change

#define ENCODER_WIDTH 640
#define ENCODER_HEIGHT 480

to

#define ENCODER_WIDTH 160
#define ENCODER_HEIGHT 120

and run again, file size is almost the same. Question now is why? shouldn't
smaller sized video be taking up much lesser space than the original sized
video?

Same thing happens if instead of saving to hard-disk I transmit over udp;
it is taking up similar bandwidth consumption.

Can anyone provide guidance for above?

Thanks for your time!
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://ffmpeg.org/pipermail/libav-user/attachments/20121218/cab0a8c3/attachment.html>


More information about the Libav-user mailing list