From e90137c045721a1635cc241eb1e1be1126389c38 Mon Sep 17 00:00:00 2001 From: Vittorio Giovara Date: Wed, 2 Nov 2016 11:29:15 -0400 Subject: [PATCH] mov: Export spherical information This implements Spherical Video V1 and V2, as described in the spatial-media collection by Google. Signed-off-by: Vittorio Giovara --- Changelog | 1 + libavformat/isom.h | 6 ++ libavformat/mov.c | 262 ++++++++++++++++++++++++++++++++++++++++++++++++++ libavformat/version.h | 2 +- 4 files changed, 270 insertions(+), 1 deletion(-) diff --git a/Changelog b/Changelog index cd0ffb5213..feb151cf3c 100644 --- a/Changelog +++ b/Changelog @@ -2,6 +2,7 @@ Entries are sorted chronologically from oldest to youngest within each release, releases are sorted from youngest to oldest. version : +- Support for spherical videos version 12: diff --git a/libavformat/isom.h b/libavformat/isom.h index 1aa2091043..fa73ad91bb 100644 --- a/libavformat/isom.h +++ b/libavformat/isom.h @@ -24,6 +24,9 @@ #ifndef AVFORMAT_ISOM_H #define AVFORMAT_ISOM_H +#include "libavutil/spherical.h" +#include "libavutil/stereo3d.h" + #include "avio.h" #include "internal.h" #include "dv.h" @@ -145,6 +148,9 @@ typedef struct MOVStreamContext { int stsd_count; int32_t *display_matrix; + AVStereo3D *stereo3d; + AVSphericalMapping *spherical; + size_t spherical_size; } MOVStreamContext; typedef struct MOVContext { diff --git a/libavformat/mov.c b/libavformat/mov.c index 28adce76c3..7fe639dd5e 100644 --- a/libavformat/mov.c +++ b/libavformat/mov.c @@ -37,6 +37,8 @@ #include "libavutil/dict.h" #include "libavutil/opt.h" #include "libavutil/pixdesc.h" +#include "libavutil/spherical.h" +#include "libavutil/stereo3d.h" #include "libavcodec/ac3tab.h" #include "avformat.h" #include "internal.h" @@ -3174,6 +3176,242 @@ static int mov_read_elst(MOVContext *c, AVIOContext *pb, MOVAtom atom) return 0; } +static int mov_read_st3d(MOVContext *c, AVIOContext *pb, MOVAtom atom) +{ + AVStream *st; + MOVStreamContext *sc; + enum AVStereo3DType type; + int mode; + + if (c->fc->nb_streams < 1) + return 0; + + st = c->fc->streams[c->fc->nb_streams - 1]; + sc = st->priv_data; + + if (atom.size < 5) { + av_log(c->fc, AV_LOG_ERROR, "Empty stereoscopic video box\n"); + return AVERROR_INVALIDDATA; + } + avio_skip(pb, 4); /* version + flags */ + + mode = avio_r8(pb); + switch (mode) { + case 0: + type = AV_STEREO3D_2D; + break; + case 1: + type = AV_STEREO3D_TOPBOTTOM; + break; + case 2: + type = AV_STEREO3D_SIDEBYSIDE; + break; + default: + av_log(c->fc, AV_LOG_WARNING, "Unknown st3d mode value %d\n", mode); + return 0; + } + + sc->stereo3d = av_stereo3d_alloc(); + if (!sc->stereo3d) + return AVERROR(ENOMEM); + + sc->stereo3d->type = type; + return 0; +} + +static int mov_read_sv3d(MOVContext *c, AVIOContext *pb, MOVAtom atom) +{ + AVStream *st; + MOVStreamContext *sc; + int size; + int32_t yaw, pitch, roll; + uint32_t tag; + enum AVSphericalProjection projection; + + if (c->fc->nb_streams < 1) + return 0; + + st = c->fc->streams[c->fc->nb_streams - 1]; + sc = st->priv_data; + + if (atom.size < 8) { + av_log(c->fc, AV_LOG_ERROR, "Empty spherical video box\n"); + return AVERROR_INVALIDDATA; + } + + size = avio_rb32(pb); + if (size > atom.size) + return AVERROR_INVALIDDATA; + + tag = avio_rl32(pb); + if (tag != MKTAG('s','v','h','d')) { + av_log(c->fc, AV_LOG_ERROR, "Missing spherical video header\n"); + return 0; + } + avio_skip(pb, 4); /* version + flags */ + avio_skip(pb, avio_r8(pb)); /* metadata_source */ + + size = avio_rb32(pb); + if (size > atom.size) + return AVERROR_INVALIDDATA; + + tag = avio_rl32(pb); + if (tag != MKTAG('p','r','o','j')) { + av_log(c->fc, AV_LOG_ERROR, "Missing projection box\n"); + return 0; + } + + size = avio_rb32(pb); + if (size > atom.size) + return AVERROR_INVALIDDATA; + + tag = avio_rl32(pb); + if (tag != MKTAG('p','r','h','d')) { + av_log(c->fc, AV_LOG_ERROR, "Missing projection header box\n"); + return 0; + } + avio_skip(pb, 4); /* version + flags */ + + /* 16.16 fixed point */ + yaw = avio_rb32(pb); + pitch = avio_rb32(pb); + roll = avio_rb32(pb); + + size = avio_rb32(pb); + if (size > atom.size) + return AVERROR_INVALIDDATA; + + tag = avio_rl32(pb); + avio_skip(pb, 4); /* version + flags */ + switch (tag) { + case MKTAG('c','b','m','p'): + projection = AV_SPHERICAL_CUBEMAP; + break; + case MKTAG('e','q','u','i'): + projection = AV_SPHERICAL_EQUIRECTANGULAR; + break; + default: + av_log(c->fc, AV_LOG_ERROR, "Unknown projection type\n"); + return 0; + } + + sc->spherical = av_spherical_alloc(&sc->spherical_size); + if (!sc->spherical) + return AVERROR(ENOMEM); + + sc->spherical->projection = projection; + + sc->spherical->yaw = yaw; + sc->spherical->pitch = pitch; + sc->spherical->roll = roll; + + return 0; +} + +static int mov_parse_uuid_spherical(MOVStreamContext *sc, AVIOContext *pb, size_t len) +{ + int ret = 0; + uint8_t *buffer = av_malloc(len + 1); + const char *val; + + if (!buffer) + return AVERROR(ENOMEM); + buffer[len] = '\0'; + + ret = ffio_read_size(pb, buffer, len); + if (ret < 0) + goto out; + + /* Check for mandatory keys and values, try to support XML as best-effort */ + if (av_stristr(buffer, "") && + (val = av_stristr(buffer, "")) && + av_stristr(val, "true") && + (val = av_stristr(buffer, "")) && + av_stristr(val, "true") && + (val = av_stristr(buffer, "")) && + av_stristr(val, "equirectangular")) { + sc->spherical = av_spherical_alloc(&sc->spherical_size); + if (!sc->spherical) + goto out; + + sc->spherical->projection = AV_SPHERICAL_EQUIRECTANGULAR; + + if (av_stristr(buffer, "")) { + enum AVStereo3DType mode; + + if (av_stristr(buffer, "left-right")) + mode = AV_STEREO3D_SIDEBYSIDE; + else if (av_stristr(buffer, "top-bottom")) + mode = AV_STEREO3D_TOPBOTTOM; + else + mode = AV_STEREO3D_2D; + + sc->stereo3d = av_stereo3d_alloc(); + if (!sc->stereo3d) + goto out; + + sc->stereo3d->type = mode; + } + + /* orientation */ + val = av_stristr(buffer, ""); + if (val) + sc->spherical->yaw = strtol(val, NULL, 10) * (1 << 16); + val = av_stristr(buffer, ""); + if (val) + sc->spherical->pitch = strtol(val, NULL, 10) * (1 << 16); + val = av_stristr(buffer, ""); + if (val) + sc->spherical->roll = strtol(val, NULL, 10) * (1 << 16); + } + +out: + av_free(buffer); + return ret; +} + +static int mov_read_uuid(MOVContext *c, AVIOContext *pb, MOVAtom atom) +{ + AVStream *st; + MOVStreamContext *sc; + int ret; + + uint8_t uuid[16]; + static const uint8_t uuid_spherical[] = { + 0xff, 0xcc, 0x82, 0x63, 0xf8, 0x55, 0x4a, 0x93, + 0x88, 0x14, 0x58, 0x7a, 0x02, 0x52, 0x1f, 0xdd, + }; + + if (atom.size < sizeof(uuid) || atom.size == INT64_MAX) + return AVERROR_INVALIDDATA; + + if (c->fc->nb_streams < 1) + return 0; + st = c->fc->streams[c->fc->nb_streams - 1]; + sc = st->priv_data; + + ret = ffio_read_size(pb, uuid, sizeof(uuid)); + if (ret < 0) + return ret; + + if (!memcmp(uuid, uuid_spherical, sizeof(uuid)) && !sc->spherical) { + size_t len = atom.size - sizeof(uuid); + ret = mov_parse_uuid_spherical(sc, pb, len); + if (ret < 0) + return ret; + if (!sc->spherical) + av_log(c->fc, AV_LOG_WARNING, "Invalid spherical metadata found\n"); + } else { + int i; + av_log(c->fc, AV_LOG_VERBOSE, "Unknown UUID found: 0x"); + for (i = 0; i < sizeof(uuid); i++) + av_log(c->fc, AV_LOG_WARNING, "%02x", uuid[i]); + av_log(c->fc, AV_LOG_WARNING, "\n"); + } + + return 0; +} + static const MOVParseTableEntry mov_default_parse_table[] = { { MKTAG('a','v','s','s'), mov_read_extradata }, { MKTAG('c','h','p','l'), mov_read_chpl }, @@ -3235,6 +3473,9 @@ static const MOVParseTableEntry mov_default_parse_table[] = { { MKTAG('d','v','c','1'), mov_read_dvc1 }, { MKTAG('s','b','g','p'), mov_read_sbgp }, { MKTAG('h','v','c','C'), mov_read_glbl }, +{ MKTAG('s','t','3','d'), mov_read_st3d }, /* stereoscopic 3D video box */ +{ MKTAG('s','v','3','d'), mov_read_sv3d }, /* spherical video box */ +{ MKTAG('u','u','i','d'), mov_read_uuid }, /* universal unique identifier */ { MKTAG('-','-','-','-'), mov_read_custom }, { 0, NULL } }; @@ -3463,6 +3704,9 @@ static int mov_read_close(AVFormatContext *s) av_free(sc->extradata[j]); av_freep(&sc->extradata); av_freep(&sc->extradata_size); + + av_freep(&sc->stereo3d); + av_freep(&sc->spherical); } if (mov->dv_demux) { @@ -3553,6 +3797,24 @@ static int mov_read_header(AVFormatContext *s) sc->display_matrix = NULL; } + if (sc->stereo3d) { + err = av_stream_add_side_data(st, AV_PKT_DATA_STEREO3D, + (uint8_t *)sc->stereo3d, + sizeof(*sc->stereo3d)); + if (err < 0) + return err; + + sc->stereo3d = NULL; + } + if (sc->spherical) { + err = av_stream_add_side_data(st, AV_PKT_DATA_SPHERICAL, + (uint8_t *)sc->spherical, + sc->spherical_size); + if (err < 0) + return err; + + sc->spherical = NULL; + } break; } } diff --git a/libavformat/version.h b/libavformat/version.h index c6085f8591..ad7997ec4f 100644 --- a/libavformat/version.h +++ b/libavformat/version.h @@ -31,7 +31,7 @@ #define LIBAVFORMAT_VERSION_MAJOR 57 #define LIBAVFORMAT_VERSION_MINOR 10 -#define LIBAVFORMAT_VERSION_MICRO 0 +#define LIBAVFORMAT_VERSION_MICRO 1 #define LIBAVFORMAT_VERSION_INT AV_VERSION_INT(LIBAVFORMAT_VERSION_MAJOR, \ LIBAVFORMAT_VERSION_MINOR, \ -- 2.11.0