Recherche avancée
Médias (91)
-
Spitfire Parade - Crisis
15 mai 2011, par
Mis à jour : Septembre 2011
Langue : English
Type : Audio
-
Wired NextMusic
14 mai 2011, par
Mis à jour : Février 2012
Langue : English
Type : Video
-
Video d’abeille en portrait
14 mai 2011, par
Mis à jour : Février 2012
Langue : français
Type : Video
-
Sintel MP4 Surround 5.1 Full
13 mai 2011, par
Mis à jour : Février 2012
Langue : English
Type : Video
-
Carte de Schillerkiez
13 mai 2011, par
Mis à jour : Septembre 2011
Langue : English
Type : Texte
-
Publier une image simplement
13 avril 2011, par ,
Mis à jour : Février 2012
Langue : français
Type : Video
Autres articles (31)
-
Personnaliser en ajoutant son logo, sa bannière ou son image de fond
5 septembre 2013, parCertains thèmes prennent en compte trois éléments de personnalisation : l’ajout d’un logo ; l’ajout d’une bannière l’ajout d’une image de fond ;
-
Ecrire une actualité
21 juin 2013, parPrésentez les changements dans votre MédiaSPIP ou les actualités de vos projets sur votre MédiaSPIP grâce à la rubrique actualités.
Dans le thème par défaut spipeo de MédiaSPIP, les actualités sont affichées en bas de la page principale sous les éditoriaux.
Vous pouvez personnaliser le formulaire de création d’une actualité.
Formulaire de création d’une actualité Dans le cas d’un document de type actualité, les champs proposés par défaut sont : Date de publication ( personnaliser la date de publication ) (...) -
Publier sur MédiaSpip
13 juin 2013Puis-je poster des contenus à partir d’une tablette Ipad ?
Oui, si votre Médiaspip installé est à la version 0.2 ou supérieure. Contacter au besoin l’administrateur de votre MédiaSpip pour le savoir
Sur d’autres sites (8551)
-
How to decode mp4 file and encode it to mp4 container using h264 codec in cpp ?
17 juillet 2017, par Herdesh VermaI am developing a cpp program which will take mp4 video file as input, decode it and encode it again using H264 codec.
Below is the program i have developed so far.extern "C"
{
#include <libavutil></libavutil>imgutils.h>
#include <libavutil></libavutil>opt.h>
#include <libavcodec></libavcodec>avcodec.h>
#include <libavutil></libavutil>mathematics.h>
#include <libavutil></libavutil>samplefmt.h>
#include <libavutil></libavutil>timestamp.h>
#include <libavformat></libavformat>avformat.h>
#include <libavfilter></libavfilter>avfiltergraph.h>
#include <libswscale></libswscale>swscale.h>
}
#include
static AVFormatContext *fmt_ctx = NULL;
static int frame_index = 0;
static AVDictionary *pMetaData = NULL;
static int j = 0, nbytes=0;
uint8_t *video_outbuf = NULL;
static AVPacket *pAVPacket=NULL;
static int value=0;
static AVFrame *pAVFrame=NULL;
static AVFrame *outFrame=NULL;
static AVStream *video_st=NULL;
static AVFormatContext *outAVFormatContext=NULL;
static AVCodec *outAVCodec=NULL;
static AVOutputFormat *output_format=NULL;
static AVCodecContext *video_dec_ctx = NULL, *audio_dec_ctx;
static AVCodecContext *outAVCodecContext=NULL;
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 AVPacket *pkt=NULL;
static AVPacket *pkt1=NULL;
static AVFrame *frame = NULL;
//static AVPacket pkt;
static int video_frame_count = 0;
static int audio_frame_count = 0;
static int refcount = 0;
AVCodec *codec;
static struct SwsContext *sws_ctx;
AVCodecContext *c= NULL;
int i, out_size, size, x, y, outbuf_size;
AVFrame *picture;
uint8_t *outbuf, *picture_buf;
int video_outbuf_size;
int w, h;
AVPixelFormat pixFmt;
uint8_t *data[4];
int linesize[4];
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) {
printf("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) {
printf("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) {
printf("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) {
printf("Failed to copy %s codec parameters to decoder context\n",
av_get_media_type_string(type));
return ret;
}
/* Init the decoders, with or without reference counting */
av_dict_set(&opts, "refcounted_frames", refcount ? "1" : "0", 0);
if ((ret = avcodec_open2(*dec_ctx, dec, &opts)) < 0) {
printf("Failed to open %s codec\n",
av_get_media_type_string(type));
return ret;
}
*stream_idx = stream_index;
}
return 0;
}
int main (int argc, char **argv)
{
int ret = 0, got_frame;
src_filename = argv[1];
video_dst_filename = argv[2];
audio_dst_filename = argv[3];
av_register_all();
avcodec_register_all();
printf("Registered all\n");
/* open input file, and allocate format context */
if (avformat_open_input(&fmt_ctx, src_filename, NULL, NULL) < 0) {
printf("Could not open source file %s\n", src_filename);
exit(1);
}
/* retrieve stream information */
if (avformat_find_stream_info(fmt_ctx, NULL) < 0) {
printf("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];
avformat_alloc_output_context2(&outAVFormatContext, NULL, NULL,
video_dst_filename);
if (!outAVFormatContext)
{
printf("\n\nError : avformat_alloc_output_context2()");
return -1;
}
}
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) {
printf("Could not open destination file %s\n", audio_dst_filename);
ret = 1;
goto end;
}
}
/* dump input information to stderr */
printf("Source file dump starts-----------------------\n");
av_dump_format(fmt_ctx, 0, src_filename, 0);
printf("Source file dump ends-----------------------\n");
if (!audio_stream && !video_stream) {
printf("Could not find audio or video stream in the input, aborting\n");
ret = 1;
goto end;
}
output_format = av_guess_format(NULL, video_dst_filename, NULL);
if( !output_format )
{
printf("\n\nError : av_guess_format()");
return -1;
}
video_st = avformat_new_stream(outAVFormatContext ,NULL);
if( !video_st )
{
printf("\n\nError : avformat_new_stream()");
return -1;
}
outAVCodec = avcodec_find_encoder(AV_CODEC_ID_H264);
if( !outAVCodec )
{
printf("\n\nError : avcodec_find_encoder()");
return -1;
}
outAVCodecContext = avcodec_alloc_context3(outAVCodec);
if( !outAVCodecContext )
{
printf("\n\nError : avcodec_alloc_context3()");
return -1;
}
printf("Width=%d Height=%d\n",video_dec_ctx->width, video_dec_ctx-
>height);
outAVCodecContext = video_st->codec;
outAVCodecContext->codec_id = AV_CODEC_ID_H264;// AV_CODEC_ID_MPEG4; //
AV_CODEC_ID_H264 // AV_CODEC_ID_MPEG1VIDEO
outAVCodecContext->codec_type = AVMEDIA_TYPE_VIDEO;
outAVCodecContext->pix_fmt = AV_PIX_FMT_YUV420P;
outAVCodecContext->bit_rate = 350000; // 2500000
outAVCodecContext->width = video_dec_ctx->width;
outAVCodecContext->height = video_dec_ctx->height;
//outAVCodecContext->width = 720;
//outAVCodecContext->height = 480;
outAVCodecContext->gop_size = 100;
outAVCodecContext->max_b_frames = 0;
outAVCodecContext->time_base.num = 1;
outAVCodecContext->time_base.den = 25; // 15fps
if (outAVCodecContext->codec_id == AV_CODEC_ID_H264)
{
printf("HERE");
//outAVCodecContext->me_range = 16;
//outAVCodecContext->max_qdiff = 4;
outAVCodecContext->qmin = 10;
outAVCodecContext->qmax = 51;
outAVCodecContext->qcompress = 0.1;
av_opt_set(outAVCodecContext->priv_data, "preset", "slow", 0);
av_opt_set(outAVCodecContext->priv_data, "profile", "baseline",
AV_OPT_SEARCH_CHILDREN);
}
if ( outAVFormatContext->oformat->flags & AVFMT_GLOBALHEADER)
{
outAVCodecContext->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;
}
value = avcodec_open2(outAVCodecContext, outAVCodec, NULL);
if( value < 0)
{
printf("\n\nError : avcodec_open2()=%d", value);
return -1;
}
outAVFormatContext->metadata = fmt_ctx->metadata;
//outAVFormatContext->streams[video_stream_idx]->metadata=fmt_ctx-
>streams[video_stream_idx]->metadata;
av_dict_set(&(outAVFormatContext->streams[video_stream_idx]->metadata),
"rotate", "90", 0);
/* create empty video file */
if ( !(outAVFormatContext->flags & AVFMT_NOFILE) )
{
if( avio_open2(&outAVFormatContext->pb , video_dst_filename,
AVIO_FLAG_WRITE ,NULL, NULL) < 0 )
{
printf("\n\nError : avio_open2()");
}
}
if(!outAVFormatContext->nb_streams)
{
printf("\n\nError : Output file dose not contain any stream");
return -1;
}
value = avformat_write_header(outAVFormatContext , NULL);
if(value < 0)
{
printf("\n\nError : avformat_write_header()");
return -1;
}
printf("\n\nOutput file information :\n\n");
av_dump_format(outAVFormatContext , 0 ,video_dst_filename ,1);
int flag;
int frameFinished;
value = 0;
pAVPacket = (AVPacket *)av_malloc(sizeof(AVPacket));
av_init_packet(pAVPacket);
pAVFrame = av_frame_alloc();
if( !pAVFrame )
{
printf("\n\nError : av_frame_alloc()");
return -1;
}
outFrame = av_frame_alloc();//Allocate an AVFrame and set its fields to
default values.
if( !outFrame )
{
printf("\n\nError : av_frame_alloc()");
return -1;
}
outFrame->format = outAVCodecContext->pix_fmt;
outFrame->width = outAVCodecContext->width;
outFrame->height = outAVCodecContext->height;
nbytes = av_image_get_buffer_size(outAVCodecContext-
>pix_fmt,outAVCodecContext->width,outAVCodecContext->height,32);
video_outbuf = (uint8_t*)av_malloc(nbytes);
if( video_outbuf == NULL )
{
printf("\n\nError : av_malloc()");
}
// Setup the data pointers and linesizes based on the specified image
parameters and the provided array.
value = av_image_fill_arrays( outFrame->data, outFrame->linesize,
video_outbuf , AV_PIX_FMT_YUV420P, outAVCodecContext-
>width,outAVCodecContext->height,1 ); // returns : the size in bytes
required for src
if(value < 0)
{
printf("\n\nError : av_image_fill_arrays()");
}
SwsContext* swsCtx_ ;
// Allocate and return swsContext.
// a pointer to an allocated context, or NULL in case of error
// Deprecated : Use sws_getCachedContext() instead.
swsCtx_ = sws_getContext(video_dec_ctx->width,
video_dec_ctx->height,
video_dec_ctx->pix_fmt,
video_dec_ctx->width,
video_dec_ctx->height,
video_dec_ctx->pix_fmt,
SWS_BICUBIC, NULL, NULL, NULL);
AVPacket outPacket;
int got_picture;
while( av_read_frame( fmt_ctx , pAVPacket ) >= 0 )
{
printf("Starting of while\n");
if(pAVPacket->stream_index == video_stream_idx)
{
value = avcodec_decode_video2(video_dec_ctx , pAVFrame ,
&frameFinished , pAVPacket );
if( value < 0)
{
printf("Error : avcodec_decode_video2()");
}
if(frameFinished)// Frame successfully decoded :)
{
sws_scale(swsCtx_, pAVFrame->data, pAVFrame-
>linesize,0, video_dec_ctx->height, outFrame->data,outFrame->linesize);
// sws_scale(swsCtx_, pAVFrame->data, pAVFrame-
>linesize,0, video_dec_ctx->height, outFrame->data,outFrame->linesize);
av_init_packet(&outPacket);
outPacket.data = NULL; // packet data will be
allocated by the encoder
outPacket.size = 0;
avcodec_encode_video2(outAVCodecContext ,
&outPacket ,outFrame , &got_picture);
if(got_picture)
{
if(outPacket.pts != AV_NOPTS_VALUE)
outPacket.pts =
av_rescale_q(outPacket.pts, video_st->codec->time_base, video_st-
>time_base);
if(outPacket.dts != AV_NOPTS_VALUE)
outPacket.dts =
av_rescale_q(outPacket.dts, video_st->codec->time_base, video_st-
>time_base);
printf("Write frame %3d (size= %2d)\n",
j++, outPacket.size/1000);
if(av_write_frame(outAVFormatContext ,
&outPacket) != 0)
{
printf("\n\nError :
av_write_frame()");
}
av_packet_unref(&outPacket);
} // got_picture
av_packet_unref(&outPacket);
} // got_picture
}
printf("Ending of while\n");
}// End of while-loop
/* get the delayed frames */
for (got_picture = 1; got_picture; i++) {
//fflush(stdout);
ret = avcodec_encode_video2(outAVCodecContext, &outPacket, NULL,
&got_picture);
if (ret < 0) {
printf("Error encoding frame\n");
exit(1);
}
if (got_picture) {
printf("Write frame %3d (size=%5d)\n", i, outPacket.size);
av_write_frame(outAVFormatContext , &outPacket);
av_free_packet(&outPacket);
}
}
value = av_write_trailer(outAVFormatContext);
if( value < 0)
{
printf("\n\nError : av_write_trailer()");
}
//THIS WAS ADDED LATER
av_free(video_outbuf);
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;
}Above code is generating a mp4 file but it is not playing.
Can someone please tell me what i am doing wrong ? -
KLV data in RTP stream
18 septembre 2013, par ArdoramorI have implemented RFC6597 to stream KLV is RTP SMPTE336M packets. Currently, my SDP looks like this :
v=2
o=- 0 0 IN IP4 127.0.0.1
s=Unnamed
i=N/A
c=IN IP4 192.168.1.6
t=0 0
a=recvonly
m=video 8202 RTP/AVP 96
a=rtpmap:96 H264/90000
a=fmtp:96 packetization-mode=1;profile-level-id=428028;sprop-parameter-sets=Z0KAKJWgKA9E,aM48gA==;
a=control:trackID=0
m=application 8206 RTP/AVP 97
a=rtpmap:97 smpte336m/1000
a=control:trackID=1I try to remux the RTP stream with FFmpeg like so :
ffmpeg.exe -i test.sdp -map 0:0 -map 0:1 -c:v copy -c:d copy test.m2tsI get the following output with FFmpeg :
ffmpeg version 1.2 Copyright (c) 2000-2013 the FFmpeg developers
built on Mar 28 2013 00:34:08 with gcc 4.8.0 (GCC)
configuration: --enable-gpl --enable-version3 --disable-w32threads --enable-avisynth --enable-bzlib --enable-fontconfig --enable-frei0r --enable-gnutls --enable-libass --enable-libbluray --enable-libcaca --enable-libfreetype --enable-libgsm --enable-libilbc --enable-libmp3lame --enable-libopencore-amrnb --enable-libopencore-amrwb --enable-libopenjpeg --enable-libopus --enable-librtmp --enable-libschroedinger --enable-libsoxr --enable-libspeex --enable-libtheora --enable-libtwolame --enable-libvo-aacenc --enable-libvo-amrwbenc --enable-libvorbis --enable-libvpx --enable-libx264 --enable-libxavs --enable-libxvid --enable-zlib
libavutil 52. 18.100 / 52. 18.100
libavcodec 54. 92.100 / 54. 92.100
libavformat 54. 63.104 / 54. 63.104
libavdevice 54. 3.103 / 54. 3.103
libavfilter 3. 42.103 / 3. 42.103
libswscale 2. 2.100 / 2. 2.100
libswresample 0. 17.102 / 0. 17.102
libpostproc 52. 2.100 / 52. 2.100
[aac @ 0000000002137900] Sample rate index in program config element does not match the sample rate index configured by the container.
Last message repeated 1 times
[aac @ 0000000002137900] decode_pce: Input buffer exhausted before END element found
[h264 @ 00000000002ce540] Missing reference picture, default is 0
[h264 @ 00000000002ce540] decode_slice_header error
[sdp @ 00000000002cfa80] Estimating duration from bitrate, this may be inaccurate
Input #0, sdp, from 'C:\Users\dragan\Documents\Workspace\Android\uvlens\tests\test.sdp':
Metadata:
title : Unnamed
comment : N/A
Duration: N/A, start: 0.000000, bitrate: N/A
Stream #0:0: Audio: aac, 32000 Hz, 58 channels, fltp
Stream #0:1: Video: h264 (Baseline), yuv420p, 640x480, 14.83 tbr, 90k tbn, 180k tbc
Stream #0:2: Data: none
File 'C:\Users\dragan\Documents\Workspace\Android\uvlens\tests\test.m2ts' already exists. Overwrite ? [y/N] y
Output #0, mpegts, to 'C:\Users\dragan\Documents\Workspace\Android\uvlens\tests\test.m2ts':
Metadata:
title : Unnamed
comment : N/A
encoder : Lavf54.63.104
Stream #0:0: Video: h264, yuv420p, 640x480, q=2-31, 90k tbn, 90k tbc
Stream #0:1: Data: none
Stream mapping:
Stream #0:1 -> #0:0 (copy)
Stream #0:2 -> #0:1 (copy)
Press [q] to stop, [?] for help
[mpegts @ 0000000002159940] Application provided invalid, non monotonically increasing dts to muxer in stream 1: 8583659665 >= 8583656110
av_interleaved_write_frame(): Invalid argumentThe problem is that KLV stream packets do not contain have a DTS field. According to the RFC6597 STMPE336M, RTP packet structure is the same as a standard structure :
4.1. RTP Header Usage
This payload format uses the RTP packet header fields as described in
the table below:
+-----------+-------------------------------------------------------+
| Field | Usage |
+-----------+-------------------------------------------------------+
| Timestamp | The RTP Timestamp encodes the instant along a |
| | presentation timeline that the entire KLVunit encoded |
| | in the packet payload is to be presented. When one |
| | KLVunit is placed in multiple RTP packets, the RTP |
| | timestamp of all packets comprising that KLVunit MUST |
| | be the same. The timestamp clock frequency is |
| | defined as a parameter to the payload format |
| | (Section 6). |
| | |
| M-bit | The RTP header marker bit (M) is used to demarcate |
| | KLVunits. Senders MUST set the marker bit to '1' for |
| | any RTP packet that contains the final byte of a |
| | KLVunit. For all other packets, senders MUST set the |
| | RTP header marker bit to '0'. This allows receivers |
| | to pass a KLVunit for parsing/decoding immediately |
| | upon receipt of the last RTP packet comprising the |
| | KLVunit. Without this, a receiver would need to wait |
| | for the next RTP packet with a different timestamp to |
| | arrive, thus signaling the end of one KLVunit and the |
| | start of another. |
+-----------+-------------------------------------------------------+
The remaining RTP header fields are used as specified in [RFC3550].Header from RFC3550 :
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
|V=2|P|X| CC |M| PT | sequence number |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| timestamp |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| synchronization source (SSRC) identifier |
+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+
| contributing source (CSRC) identifiers |
| .... |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+RFC's note about placement of KLV data into RTP packet :
KLVunits small enough to fit into a single RTP
packet (RTP packet size is up to the implementation but should
consider underlying transport/network factors such as MTU
limitations) are placed directly into the payload of the RTP packet,
with the first byte of the KLVunit (which is the first byte of a KLV
Universal Label Key) being the first byte of the RTP packet payload.My question is where does FFmpeg keep looking for the DTS ?
Does it interpret the Timestamp field of the RTP packet header as DTS ? If so, I've verified that the timestamps increase (although at different rates) but are not equal to what FFmpeg prints out :
8583659665 >= 8583656110
-
Video rotating to left by 90 degree when converted using ffmpeg
15 juillet 2017, par Herdesh VermaI developed a below code :
extern "C"
{
#include <libavutil></libavutil>imgutils.h>
#include <libavutil></libavutil>opt.h>
#include <libavcodec></libavcodec>avcodec.h>
#include <libavutil></libavutil>mathematics.h>
#include <libavutil></libavutil>samplefmt.h>
#include <libavutil></libavutil>timestamp.h>
#include <libavformat></libavformat>avformat.h>
#include <libavfilter></libavfilter>avfiltergraph.h>
#include <libswscale></libswscale>swscale.h>
}
#include
static AVFormatContext *fmt_ctx = NULL;
static int frame_index = 0;
static int j = 0, nbytes=0;
uint8_t *video_outbuf = NULL;
static AVPacket *pAVPacket=NULL;
static int value=0;
static AVFrame *pAVFrame=NULL;
static AVFrame *outFrame=NULL;
static AVStream *video_st=NULL;
static AVFormatContext *outAVFormatContext=NULL;
static AVCodec *outAVCodec=NULL;
static AVOutputFormat *output_format=NULL;
static AVCodecContext *video_dec_ctx = NULL, *audio_dec_ctx;
static AVCodecContext *outAVCodecContext=NULL;
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 AVPacket *pkt=NULL;
static AVPacket *pkt1=NULL;
static AVFrame *frame = NULL;
//static AVPacket pkt;
static int video_frame_count = 0;
static int audio_frame_count = 0;
static int refcount = 0;
AVCodec *codec;
static struct SwsContext *sws_ctx;
AVCodecContext *c= NULL;
int i, out_size, size, x, y, outbuf_size;
AVFrame *picture;
uint8_t *outbuf, *picture_buf;
int video_outbuf_size;
int w, h;
AVPixelFormat pixFmt;
uint8_t *data[4];
int linesize[4];
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) {
printf("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) {
printf("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) {
printf("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) {
printf("Failed to copy %s codec parameters to decoder context\n",
av_get_media_type_string(type));
return ret;
}
/* Init the decoders, with or without reference counting */
av_dict_set(&opts, "refcounted_frames", refcount ? "1" : "0", 0);
if ((ret = avcodec_open2(*dec_ctx, dec, &opts)) < 0) {
printf("Failed to open %s codec\n",
av_get_media_type_string(type));
return ret;
}
*stream_idx = stream_index;
}
return 0;
}
int main (int argc, char **argv)
{
int ret = 0, got_frame;
src_filename = argv[1];
video_dst_filename = argv[2];
audio_dst_filename = argv[3];
av_register_all();
avcodec_register_all();
printf("Registered all\n");
/* open input file, and allocate format context */
if (avformat_open_input(&fmt_ctx, src_filename, NULL, NULL) < 0) {
printf("Could not open source file %s\n", src_filename);
exit(1);
}
/* retrieve stream information */
if (avformat_find_stream_info(fmt_ctx, NULL) < 0) {
printf("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];
avformat_alloc_output_context2(&outAVFormatContext, NULL, NULL,
video_dst_filename);
if (!outAVFormatContext)
{
printf("\n\nError : avformat_alloc_output_context2()");
return -1;
}
}
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) {
printf("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) {
printf("Could not find audio or video stream in the input, aborting\n");
ret = 1;
goto end;
}
output_format = av_guess_format(NULL, video_dst_filename, NULL);
if( !output_format )
{
printf("\n\nError : av_guess_format()");
return -1;
}
video_st = avformat_new_stream(outAVFormatContext ,NULL);
if( !video_st )
{
printf("\n\nError : avformat_new_stream()");
return -1;
}
outAVCodecContext = avcodec_alloc_context3(outAVCodec);
if( !outAVCodecContext )
{
printf("\n\nError : avcodec_alloc_context3()");
return -1;
}
outAVCodecContext = video_st->codec;
outAVCodecContext->codec_id = AV_CODEC_ID_MPEG4;// AV_CODEC_ID_MPEG4; //
AV_CODEC_ID_H264 // AV_CODEC_ID_MPEG1VIDEO
outAVCodecContext->codec_type = AVMEDIA_TYPE_VIDEO;
outAVCodecContext->pix_fmt = AV_PIX_FMT_YUV420P;
outAVCodecContext->bit_rate = 400000; // 2500000
outAVCodecContext->width = 1920;
//outAVCodecContext->width = 500;
outAVCodecContext->height = 1080;
//outAVCodecContext->height = 500;
outAVCodecContext->gop_size = 3;
outAVCodecContext->max_b_frames = 2;
outAVCodecContext->time_base.num = 1;
outAVCodecContext->time_base.den = 30; // 15fps
if (outAVCodecContext->codec_id == AV_CODEC_ID_H264)
{
av_opt_set(outAVCodecContext->priv_data, "preset", "slow", 0);
}
outAVCodec = avcodec_find_encoder(AV_CODEC_ID_MPEG4);
if( !outAVCodec )
{
printf("\n\nError : avcodec_find_encoder()");
return -1;
}
/* Some container formats (like MP4) require global headers to be
present
Mark the encoder so that it behaves accordingly. */
if ( outAVFormatContext->oformat->flags & AVFMT_GLOBALHEADER)
{
outAVCodecContext->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;
}
value = avcodec_open2(outAVCodecContext, outAVCodec, NULL);
if( value < 0)
{
printf("\n\nError : avcodec_open2()");
return -1;
}
/* create empty video file */
if ( !(outAVFormatContext->flags & AVFMT_NOFILE) )
{
if( avio_open2(&outAVFormatContext->pb , video_dst_filename,
AVIO_FLAG_WRITE ,NULL, NULL) < 0 )
{
printf("\n\nError : avio_open2()");
}
}
if(!outAVFormatContext->nb_streams)
{
printf("\n\nError : Output file dose not contain any stream");
return -1;
}
/* imp: mp4 container or some advanced container file required header
information*/
value = avformat_write_header(outAVFormatContext , NULL);
if(value < 0)
{
printf("\n\nError : avformat_write_header()");
return -1;
}
printf("\n\nOutput file information :\n\n");
av_dump_format(outAVFormatContext , 0 ,video_dst_filename ,1);
int flag;
int frameFinished;
value = 0;
pAVPacket = (AVPacket *)av_malloc(sizeof(AVPacket));
av_init_packet(pAVPacket);
pAVFrame = av_frame_alloc();
if( !pAVFrame )
{
printf("\n\nError : av_frame_alloc()");
return -1;
}
outFrame = av_frame_alloc();//Allocate an AVFrame and set its fields to
default values.
if( !outFrame )
{
printf("\n\nError : av_frame_alloc()");
return -1;
}
nbytes = av_image_get_buffer_size(outAVCodecContext-
>pix_fmt,outAVCodecContext->width,outAVCodecContext->height,32);
video_outbuf = (uint8_t*)av_malloc(nbytes);
if( video_outbuf == NULL )
{
printf("\n\nError : av_malloc()");
}
value = av_image_fill_arrays( outFrame->data, outFrame->linesize,
video_outbuf , AV_PIX_FMT_YUV420P, outAVCodecContext-
>width,outAVCodecContext->height,1 ); // returns : the size in bytes
required for src
if(value < 0)
{
printf("\n\nError : av_image_fill_arrays()");
}
SwsContext* swsCtx_ ;
// Allocate and return swsContext.
// a pointer to an allocated context, or NULL in case of error
// Deprecated : Use sws_getCachedContext() instead.
swsCtx_ = sws_getContext(video_dec_ctx->width,
video_dec_ctx->height,
video_dec_ctx->pix_fmt,
video_dec_ctx->width,
video_dec_ctx->height,
video_dec_ctx->pix_fmt,
SWS_BICUBIC, NULL, NULL, NULL);
AVPacket outPacket;
int got_picture;
while( av_read_frame( fmt_ctx , pAVPacket ) >= 0 )
{
if(pAVPacket->stream_index == video_stream_idx)
{
value = avcodec_decode_video2(video_dec_ctx , pAVFrame ,
&frameFinished , pAVPacket );
if( value < 0)
{
printf("Error : avcodec_decode_video2()");
}
if(frameFinished)// Frame successfully decoded :)
{
sws_scale(swsCtx_, pAVFrame->data, pAVFrame-
>linesize,0, video_dec_ctx->height, outFrame->data,outFrame->linesize);
// sws_scale(swsCtx_, pAVFrame->data, pAVFrame-
>linesize,0, video_dec_ctx->height, outFrame->data,outFrame->linesize);
av_init_packet(&outPacket);
outPacket.data = NULL; // packet data will be
allocated by the encoder
outPacket.size = 0;
avcodec_encode_video2(outAVCodecContext ,
&outPacket ,outFrame , &got_picture);
if(got_picture)
{
if(outPacket.pts != AV_NOPTS_VALUE)
outPacket.pts =
av_rescale_q(outPacket.pts, video_st->codec->time_base, video_st-
>time_base);
if(outPacket.dts != AV_NOPTS_VALUE)
outPacket.dts =
av_rescale_q(outPacket.dts, video_st->codec->time_base, video_st-
>time_base);
printf("Write frame %3d (size= %2d)\n",
j++, outPacket.size/1000);
if(av_write_frame(outAVFormatContext ,
&outPacket) != 0)
{
printf("\n\nError :
av_write_frame()");
}
av_packet_unref(&outPacket);
} // got_picture
av_packet_unref(&outPacket);
} // frameFinished
}
}// End of while-loop
value = av_write_trailer(outAVFormatContext);
if( value < 0)
{
printf("\n\nError : av_write_trailer()");
}
//THIS WAS ADDED LATER
av_free(video_outbuf);
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;
}Problem with above code is that it rotates a video to left by 90 degree.
Snapshot of video given as input to above program
Snapshot of output video. It is rotated by 90 degree to left.
I compiled program using below command :
g++ -D__STDC_CONSTANT_MACROS -Wall -g ScreenRecorder.cpp -I/home/harry/Documents/compressor/ffmpeg-3.3/ -I/root/android-ndk-r14b/platforms/android-21/arch-x86_64/usr/include/ -c -o ScreenRecorder.o -wAnd linked it using below command :
g++ -Wall -g ScreenRecorder.o -I/home/harry/Documents/compressor/ffmpeg-3.3/ -I/root/android-ndk-r14b/platforms/android-21/arch-x86_64/usr/include/ -L/usr/lib64 -L/lib64 -L/usr/lib/gcc/x86_64-redhat-linux/4.4.7/ -L/home/harry/Documents/compressor/ffmpeg-3.3/ffmpeg-build -L/root/android-ndk-r14b/platforms/android-21/arch-x86_64/usr/lib64 -o ScreenRecorder.exe -lavformat -lavcodec -lavutil -lavdevice -lavfilter -lswscale -lx264 -lswresample -lm -lpthread -ldl -lstdc++ -lc -lrtProgram is being run using below command :
./ScreenRecorder.exe vertical.MOV videoH.mp4 audioH.mp3Note :
- Source video is taken from iphone and is of .mov format.
- Output video is being stored in .mp4 file.Can anyone please tell me why it is rotating video by 90 degree ?
One thing i noticed in dump is shown below :
Duration: 00:00:06.04, start: 0.000000, bitrate: 17087 kb/s
Stream #0:0(und): Video: h264 (High) (avc1 / 0x31637661), yuv420p(tv, bt709), 1920x1080, 17014 kb/s, 29.98 fps, 29.97 tbr, 600 tbn, 1200 tbc (default)
Metadata:
rotate : 90
creation_time : 2017-07-09T10:56:42.000000Z
handler_name : Core Media Data Handler
encoder : H.264
Side data:
displaymatrix: rotation of -90.00 degreesit says
displaymatrix: rotation of -90.00 degrees. Is it responsible for rotating video by 90 degree ?
Syndiquer tout le site
