[FFmpeg-devel] [PATCH v5 1/2] lavf/isom: support for demuxing MPEG-H 3D Audio in MP4

[James Almer]

On 11/21/2019 4:25 AM, Yuki Tsuchiya wrote:
> Implemented according to the specification at https://www.iso.org/standard/69561.html
> The 'mhm1' sample entry is registered with MP4RA, which is defined as MHAS encapsulated single stream MPEG-H 3D Audio.
> 'MHAS' stands for MPEG-H audio stream, which contains encoded audio data and corresponds metadata for decoding.
> This patch enables extracting the MHAS bitstream from MP4.

This is changing the muxer, but the commit subject and description talks
about demuxing.

> 
> Signed-off-by: Yuki Tsuchiya <Yuki.Tsuchiya at sony.com>
> ---
>  libavcodec/avcodec.h    | 1 +
>  libavcodec/codec_desc.c | 7 +++++++
>  libavcodec/version.h    | 2 +-
>  libavformat/isom.c      | 1 +
>  libavformat/movenc.c    | 6 ++++--
>  libavformat/utils.c     | 3 ++-
>  6 files changed, 16 insertions(+), 4 deletions(-)
> 
> diff --git a/libavcodec/avcodec.h b/libavcodec/avcodec.h
> index 813a43b72e..85c9401b8f 100644
> --- a/libavcodec/avcodec.h
> +++ b/libavcodec/avcodec.h
> @@ -654,6 +654,7 @@ enum AVCodecID {
>      AV_CODEC_ID_ATRAC9,
>      AV_CODEC_ID_HCOM,
>      AV_CODEC_ID_ACELP_KELVIN,
> +    AV_CODEC_ID_MPEGH_3D_AUDIO,
>  
>      /* subtitle codecs */
>      AV_CODEC_ID_FIRST_SUBTITLE = 0x17000,          ///< A dummy ID pointing at the start of subtitle codecs.
> diff --git a/libavcodec/codec_desc.c b/libavcodec/codec_desc.c
> index 5961af3c85..ba8ec32e4e 100644
> --- a/libavcodec/codec_desc.c
> +++ b/libavcodec/codec_desc.c
> @@ -2999,6 +2999,13 @@ static const AVCodecDescriptor codec_descriptors[] = {
>          .long_name = NULL_IF_CONFIG_SMALL("Sipro ACELP.KELVIN"),
>          .props     = AV_CODEC_PROP_LOSSY,
>      },
> +    {
> +        .id        = AV_CODEC_ID_MPEGH_3D_AUDIO,
> +        .type      = AVMEDIA_TYPE_AUDIO,
> +        .name      = "mpegh_3d_audio",
> +        .long_name = NULL_IF_CONFIG_SMALL("MPEG-H 3D Audio"),
> +        .props     = AV_CODEC_PROP_LOSSY,
> +    },
>  
>      /* subtitle codecs */
>      {
> diff --git a/libavcodec/version.h b/libavcodec/version.h
> index 58ea00a520..5c8e376ea1 100644
> --- a/libavcodec/version.h
> +++ b/libavcodec/version.h
> @@ -28,7 +28,7 @@
>  #include "libavutil/version.h"
>  
>  #define LIBAVCODEC_VERSION_MAJOR  58
> -#define LIBAVCODEC_VERSION_MINOR  62
> +#define LIBAVCODEC_VERSION_MINOR  63
>  #define LIBAVCODEC_VERSION_MICRO 100
>  
>  #define LIBAVCODEC_VERSION_INT  AV_VERSION_INT(LIBAVCODEC_VERSION_MAJOR, \
> diff --git a/libavformat/isom.c b/libavformat/isom.c
> index edd0d81063..824e811177 100644
> --- a/libavformat/isom.c
> +++ b/libavformat/isom.c
> @@ -371,6 +371,7 @@ const AVCodecTag ff_codec_movaudio_tags[] = {
>      { AV_CODEC_ID_FLAC,            MKTAG('f', 'L', 'a', 'C') }, /* nonstandard */
>      { AV_CODEC_ID_TRUEHD,          MKTAG('m', 'l', 'p', 'a') }, /* mp4ra.org */
>      { AV_CODEC_ID_OPUS,            MKTAG('O', 'p', 'u', 's') }, /* mp4ra.org */
> +    { AV_CODEC_ID_MPEGH_3D_AUDIO,  MKTAG('m', 'h', 'm', '1') }, /* MPEG-H 3D Audio bitstream */
>      { AV_CODEC_ID_NONE, 0 },
>  };
>  
> diff --git a/libavformat/movenc.c b/libavformat/movenc.c
> index 715bec1c2f..ff234d9f2b 100644
> --- a/libavformat/movenc.c
> +++ b/libavformat/movenc.c
> @@ -2411,7 +2411,7 @@ static int mov_preroll_write_stbl_atoms(AVIOContext *pb, MOVTrack *track)
>      if (!sgpd_entries)
>          return AVERROR(ENOMEM);
>  
> -    av_assert0(track->par->codec_id == AV_CODEC_ID_OPUS || track->par->codec_id == AV_CODEC_ID_AAC);
> +    av_assert0(track->par->codec_id == AV_CODEC_ID_OPUS || track->par->codec_id == AV_CODEC_ID_AAC || track->par->codec_id == AV_CODEC_ID_MPEGH_3D_AUDIO);

You're calling this function for MPEGH 3D Audio, but not writing an
implementation for it. The sgpd_entries array will be empty.

>  
>      if (track->par->codec_id == AV_CODEC_ID_OPUS) {
>          for (i = 0; i < track->entry; i++) {
> @@ -2493,6 +2493,7 @@ static int mov_write_stbl_tag(AVFormatContext *s, AVIOContext *pb, MOVMuxContext
>      mov_write_stts_tag(pb, track);
>      if ((track->par->codec_type == AVMEDIA_TYPE_VIDEO ||
>           track->par->codec_id == AV_CODEC_ID_TRUEHD ||
> +         track->par->codec_id == AV_CODEC_ID_MPEGH_3D_AUDIO ||
>           track->par->codec_tag == MKTAG('r','t','p',' ')) &&
>          track->has_keyframes && track->has_keyframes < track->entry)
>          mov_write_stss_tag(pb, track, MOV_SYNC_SAMPLE);

Is every sample meant to be a Sync Sample?

> @@ -2512,7 +2513,7 @@ static int mov_write_stbl_tag(AVFormatContext *s, AVIOContext *pb, MOVMuxContext
>      if (track->cenc.aes_ctr) {
>          ff_mov_cenc_write_stbl_atoms(&track->cenc, pb);
>      }
> -    if (track->par->codec_id == AV_CODEC_ID_OPUS || track->par->codec_id == AV_CODEC_ID_AAC) {
> +    if (track->par->codec_id == AV_CODEC_ID_OPUS || track->par->codec_id == AV_CODEC_ID_AAC || track->par->codec_id == AV_CODEC_ID_MPEGH_3D_AUDIO) {
>          mov_preroll_write_stbl_atoms(pb, track);
>      }
>      return update_size(pb, pos);
> @@ -6877,6 +6878,7 @@ const AVCodecTag codec_mp4_tags[] = {
>      { AV_CODEC_ID_DVD_SUBTITLE, MKTAG('m', 'p', '4', 's') },
>      { AV_CODEC_ID_MOV_TEXT    , MKTAG('t', 'x', '3', 'g') },
>      { AV_CODEC_ID_BIN_DATA    , MKTAG('g', 'p', 'm', 'd') },
> +    { AV_CODEC_ID_MPEGH_3D_AUDIO, MKTAG('m', 'h', 'm', '1') },
>      { AV_CODEC_ID_NONE        ,    0 },
>  };
>  
> diff --git a/libavformat/utils.c b/libavformat/utils.c
> index 8196442dd1..70f9e23d8c 100644
> --- a/libavformat/utils.c
> +++ b/libavformat/utils.c
> @@ -1021,7 +1021,8 @@ static int is_intra_only(enum AVCodecID id)
>      const AVCodecDescriptor *d = avcodec_descriptor_get(id);
>      if (!d)
>          return 0;
> -    if (d->type == AVMEDIA_TYPE_VIDEO && !(d->props & AV_CODEC_PROP_INTRA_ONLY))
> +    if ((d->type == AVMEDIA_TYPE_VIDEO && !(d->props & AV_CODEC_PROP_INTRA_ONLY)) ||
> +        id == AV_CODEC_ID_MPEGH_3D_AUDIO)
>          return 0;
>      return 1;
>  }
>