Related
So I have a program that reads an opengl window and encodes the read data as a video. Now through a series of experimentation I have learned that the bit format of my glfw window is 8:8:8 as returned by glfwGetVideoMode(monitor). So I use this function to read the window:
glReadPixels(0, 0,gl_width, gl_height,GL_RGBA, GL_UNSIGNED_BYTE, (GLvoid*) Buffer);
and I simply encode it in the AV_PIX_FMT_YUV420P format.
Under normal circumstances this method works just fine. However, when I actually run the program, the output I get, as opposed to what I can see in the glfw window, is really low resolution and a bit pixelated.
Here is what my GLFW window looks like:
Now this is what I want it to look like. It looks just fine on the opengl window, and I encode it directly without altering Buffer.
And here is what the encoded result, test.mp4 looks like when I run it using mplayer or similar software:
It's a lot more blurry and pixelated compare to the GLFW window. With some experimentation and following an answer to another question I asked, I us avcodec_find_best_pix_fmt_of_list((*codec)->pix_fmts, AV_PIX_FMT_RGBA, 1, &ret) and it returned 13. Which led me to believe using AV_PIX_FMT_YUVJ422P is the best option for this convertion to not have a blurry/pixelated result. However, no matter which function I pass, every single format gives off an error except AV_PIX_FMT_YUV420P. The error is:
[mpeg4 # 0x558e74f47900] Specified pixel format yuvj422p is invalid or not supported
I have no idea why this is happening, as the format is bound to a define and it is changed throughout the entire program when I change the define.
Here is my encoder so far (I have trimmed some parts):
video_encoder.cpp:
int video_encoder::write_frame(AVFormatContext *fmt_ctx, AVCodecContext *c,
AVStream *st, AVFrame *frame, AVPacket *pkt)
{
int ret;
// Conditional jump or move depends on uninitialised value
// Use of uninitialised value of size 8
// send the frame to the encoder
// Error is about c.
ret = avcodec_send_frame(c, frame);
if (ret < 0) {
std::cout << "Error sending a frame to the encoder: " << ret << std::endl;
exit(1);
}
while (ret >= 0) {
ret = avcodec_receive_packet(c, pkt);
if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
break;
else if (ret < 0) {
std::cout << "Error encoding a frame: " << ret << std::endl;
exit(1);
}
/* rescale output packet timestamp values from codec to stream timebase */
av_packet_rescale_ts(pkt, c->time_base, st->time_base);
pkt->stream_index = st->index;
/* Write the compressed frame to the media file. */
//log_packet(fmt_ctx, pkt);
//std::cout << "Packet: " << pkt << std::endl;
ret = av_interleaved_write_frame(fmt_ctx, pkt);
/* pkt is now blank (av_interleaved_write_frame() takes ownership of
* its contents and resets pkt), so that no unreferencing is necessary.
* This would be different if one used av_write_frame(). */
if (ret < 0) {
std::cout << "Error while writing output packet: " << ret << std::endl;
exit(1);
}
}
return ret == AVERROR_EOF ? 1 : 0;
}
/* Add an output stream. */
void video_encoder::add_stream(OutputStream *ost, AVFormatContext *oc,
const AVCodec **codec,
enum AVCodecID codec_id)
{
AVCodecContext *c;
int i;
/* find the encoder */
*codec = avcodec_find_encoder(codec_id);
if (!(*codec)) {
fprintf(stderr, "Could not find encoder for '%s'\n",
avcodec_get_name(codec_id));
exit(1);
}
ost->tmp_pkt = av_packet_alloc();
if (!ost->tmp_pkt) {
fprintf(stderr, "Could not allocate AVPacket\n");
exit(1);
}
ost->st = avformat_new_stream(oc, NULL);
if (!ost->st) {
fprintf(stderr, "Could not allocate stream\n");
exit(1);
}
ost->st->id = oc->nb_streams-1;
c = avcodec_alloc_context3(*codec);
if (!c) {
fprintf(stderr, "Could not alloc an encoding context\n");
exit(1);
}
ost->enc = c;
switch ((*codec)->type) {
case AVMEDIA_TYPE_AUDIO:
...
case AVMEDIA_TYPE_VIDEO:
c->codec_id = codec_id;
c->bit_rate = 10000;
/* Resolution must be a multiple of two. */
c->width = width;
c->height = 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. */
ost->st->time_base = (AVRational){ 1, STREAM_FRAME_RATE }; // *frame_rate
c->time_base = ost->st->time_base;
c->gop_size = 7; /* emit one intra frame every twelve frames at most */
c->pix_fmt = STREAM_PIX_FMT;
//if (c->codec_id == AV_CODEC_ID_MPEG2VIDEO)
// 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;
}
if ((*codec)->pix_fmts){
//c->pix_fmt = (*codec)->pix_fmts[0];
std::cout << "NEW FORMAT : " << c->pix_fmt << std::endl;
}
int ret;
avcodec_find_best_pix_fmt_of_list((*codec)->pix_fmts, AV_PIX_FMT_RGBA, 1, &ret);
std::cout << "Desired format is: " << ret << std::endl;
break;
}
/* Some formats want stream headers to be separate. */
if (oc->oformat->flags & AVFMT_GLOBALHEADER)
c->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;
}
/**************************************************************/
/* video output */
AVFrame* video_encoder::alloc_picture(enum AVPixelFormat pix_fmt, int width, int height)
{
AVFrame *picture;
int ret;
picture = av_frame_alloc();
if (!picture)
return NULL;
picture->format = pix_fmt;
picture->width = width;
picture->height = height;
/* allocate the buffers for the frame data */
ret = av_frame_get_buffer(picture, 0);
if (ret < 0) {
fprintf(stderr, "Could not allocate frame data.\n");
exit(1);
}
return picture;
}
void video_encoder::open_video(AVFormatContext *oc, const AVCodec *codec,
OutputStream *ost, AVDictionary *opt_arg)
{
int ret;
AVCodecContext *c = ost->enc;
AVDictionary *opt = NULL;
av_dict_copy(&opt, opt_arg, 0);
/* open the codec */
ret = avcodec_open2(c, codec, &opt);
av_dict_free(&opt);
if (ret < 0) {
fprintf(stderr, "Could not open video codec: %s\n", ret);
exit(1);
}
/* allocate and init a re-usable frame */
ost->frame = alloc_picture(c->pix_fmt, c->width, c->height);
if (!ost->frame) {
fprintf(stderr, "Could not allocate video frame\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. */
ost->tmp_frame = NULL;
/* copy the stream parameters to the muxer */
ret = avcodec_parameters_from_context(ost->st->codecpar, c);
if (ret < 0) {
fprintf(stderr, "Could not copy the stream parameters\n");
exit(1);
}
}
void video_encoder::set_frame_yuv_from_rgb(AVFrame *frame, struct SwsContext *sws_context) {
const int in_linesize[1] = { 4 * width };
//uint8_t* dest[4] = { rgb_data, NULL, NULL, NULL };
sws_context = sws_getContext(
width, height, AV_PIX_FMT_RGBA,
width, height, STREAM_PIX_FMT,
SCALE_FLAGS, 0, 0, 0);
sws_scale(sws_context, (const uint8_t * const *)&rgb_data, in_linesize, 0,
height, frame->data, frame->linesize);
}
AVFrame* video_encoder::get_video_frame(OutputStream *ost)
{
AVCodecContext *c = ost->enc;
/* check if we want to generate more frames */
if (av_compare_ts(ost->next_pts, c->time_base,
(float) STREAM_DURATION / 1000, (AVRational){ 1, 1 }) > 0)
return NULL;
/* when we pass a frame to the encoder, it may keep a reference to it
* internally; make sure we do not overwrite it here */
if (av_frame_make_writable(ost->frame) < 0)
exit(1);
set_frame_yuv_from_rgb(ost->frame, ost->sws_ctx);
ost->frame->pts = ost->next_pts++;
return ost->frame;
}
/*
* encode one video frame and send it to the muxer
* return 1 when encoding is finished, 0 otherwise
*/
int video_encoder::write_video_frame(AVFormatContext *oc, OutputStream *ost)
{
return write_frame(oc, ost->enc, ost->st, get_video_frame(ost), ost->tmp_pkt);
}
void video_encoder::close_stream(AVFormatContext *oc, OutputStream *ost)
{
avcodec_free_context(&ost->enc);
av_frame_free(&ost->frame);
av_frame_free(&ost->tmp_frame);
av_packet_free(&ost->tmp_pkt);
//sws_freeContext(ost->sws_ctx);
//swr_free(&ost->swr_ctx);
}
/**************************************************************/
/* media file output */
void video_encoder::set_encode_framebuffer(uint8_t* data, bool audio_only)
{
rgb_data = data;
}
video_encoder::~video_encoder()
{
av_write_trailer(enc_inf.oc);
/* Close each codec. */
if (enc_inf.have_video)
close_stream(enc_inf.oc, &enc_inf.video_st);
if (!(enc_inf.fmt->flags & AVFMT_NOFILE))
/* Close the output file. */
avio_closep(&enc_inf.oc->pb);
/* free the stream */
avformat_free_context(enc_inf.oc);
std::cout << "Done, closing." << std::endl;
}
bool video_encoder::encode_one_frame()
{
if (enc_inf.encode_video || enc_inf.encode_audio) {
/* select the stream to encode */
if (enc_inf.encode_video &&
(!enc_inf.encode_audio || av_compare_ts(enc_inf.video_st.next_pts, enc_inf.video_st.enc->time_base,
enc_inf.audio_st.next_pts, enc_inf.audio_st.enc->time_base) <= 0)) {
enc_inf.encode_video = !write_video_frame(enc_inf.oc, &enc_inf.video_st);
return true;
}
}
return false;
}
video_encoder::video_encoder(int w, int h, float fps, unsigned int duration)
:width(w), height(h), STREAM_FRAME_RATE(fps), STREAM_DURATION(duration)
{
//std::filesystem::create_directory("media");
//std::string as_str = "./output/" + std::string(getenv ("OUTPUT_UUID")) + ".mp4";
std::string as_str = "./output/video.mp4";
char* filename = const_cast<char*>(as_str.c_str());
enc_inf.video_st, enc_inf.audio_st = (struct OutputStream) { 0 };
enc_inf.video_st.next_pts = 1;
enc_inf.audio_st.next_pts = 1;
enc_inf.encode_audio, enc_inf.encode_video = 0;
int ret;
int i;
//rgb_data = (uint8_t*)malloc( 48 * sizeof(uint8_t) );
/* allocate the output media context */
avformat_alloc_output_context2(&enc_inf.oc, NULL, NULL, filename);
if (!enc_inf.oc) {
//VI_ERROR("Could not deduce output format from file extension: using MPEG.\n");
avformat_alloc_output_context2(&enc_inf.oc, NULL, "mpeg", filename);
}
if (!enc_inf.oc)
std::cout << "FAILED" << std::endl;
//return 1;
enc_inf.fmt = enc_inf.oc->oformat;
/* Add the audio and video streams using the default format codecs
* and initialize the codecs. */
if (enc_inf.fmt->video_codec != AV_CODEC_ID_NONE) {
add_stream(&enc_inf.video_st, enc_inf.oc, &video_codec, enc_inf.fmt->video_codec);
enc_inf.have_video = 1;
enc_inf.encode_video = 1;
}
/* Now that all the parameters are set, we can open the audio and
* video codecs and allocate the necessary encode buffers. */
if (enc_inf.have_video)
open_video(enc_inf.oc, video_codec, &enc_inf.video_st, opt);
/* open the output file, if needed */
if (!(enc_inf.fmt->flags & AVFMT_NOFILE)) {
ret = avio_open(&enc_inf.oc->pb, filename, AVIO_FLAG_WRITE);
if (ret < 0) {
//VI_ERROR("Could not open '%s': %s\n", filename, ret);
//return 1;
}
}
/* Write the stream header, if any. */
ret = avformat_write_header(enc_inf.oc, &opt);
if (ret < 0) {
VI_ERROR("Error occurred when opening output file:");
//return 1;
}
//return 0;
}
video_encoder.h:
#define STREAM_PIX_FMT AV_PIX_FMT_YUV420P /* default pix_fmt */
#define SCALE_FLAGS SWS_SPLINE
/* The output bit rate in bit/s */
#define OUTPUT_BIT_RATE 96000
/* The number of output channels */
#define OUTPUT_CHANNELS 2
typedef struct OutputStream {
AVStream *st;
AVCodecContext *enc;
/* pts of the next frame that will be generated */
int64_t next_pts;
int samples_count;
AVFrame *frame;
AVFrame *tmp_frame;
AVPacket *tmp_pkt;
float t, tincr, tincr2;
struct SwsContext *sws_ctx;
struct SwrContext *swr_ctx;
} OutputStream;
typedef struct {
OutputStream video_st, audio_st;
const AVOutputFormat *fmt;
AVFormatContext *oc;
int have_video, have_audio, encode_video, encode_audio;
std::string name;
} encode_info;
Again, changing STREAM_PIX_FMT anything other than AV_PIX_FMT_YUV420P causes the program to give the error.
What is the cause of this and how can I fix this? Also am I on the right track for fixing the pixelation problem? I'm using ubuntu.
I am actually trying to send real time images via the network efficiently. For this, I thought that the RTP protocole in video streaming can be a good way to achieve this.
I actually tried this :
extern "C"
{
#include <libavcodec/avcodec.h>
#include <libavformat/avformat.h>
#include <libswscale/swscale.h>
#include <libavutil/opt.h>
#include <libavutil/channel_layout.h>
#include <libavutil/common.h>
#include <libavutil/imgutils.h>
#include <libavutil/mathematics.h>
#include <libavutil/samplefmt.h>
}
#include <iostream>
#include <unistd.h>
#include <stdio.h>
//Mainly based on https://stackoverflow.com/questions/40825300/ffmpeg-create-rtp-stream
int main()
{
//Init ffmpeg
avcodec_register_all();
av_register_all();
avformat_network_init();
//Init the codec used to encode our given image
AVCodecID codecID = AV_CODEC_ID_MPEG4;
AVCodec* codec;
AVCodecContext* codecCtx;
codec = avcodec_find_encoder(codecID);
codecCtx = avcodec_alloc_context3(codec);
//codecCtx->bit_rate = 400000;
codecCtx->width = 352;
codecCtx->height = 288;
codecCtx->time_base.num = 1;
codecCtx->time_base.den = 25;
codecCtx->gop_size = 25;
codecCtx->max_b_frames = 1;
codecCtx->pix_fmt = AV_PIX_FMT_YUV420P;
codecCtx->codec_type = AVMEDIA_TYPE_VIDEO;
if (codecID == AV_CODEC_ID_H264)
{
av_opt_set(codecCtx->priv_data, "preset", "ultrafast", 0);
av_opt_set(codecCtx->priv_data, "tune", "zerolatency", 0);
}
avcodec_open2(codecCtx, codec, NULL);
//Init the Frame containing our raw data
AVFrame* frame;
frame = av_frame_alloc();
frame->format = codecCtx->pix_fmt;
frame->width = codecCtx->width;
frame->height = codecCtx->height;
av_image_alloc(frame->data, frame->linesize, frame->width, frame->height, codecCtx->pix_fmt, 32);
//Init the format context
AVFormatContext* fmtCtx = avformat_alloc_context();
AVOutputFormat* format = av_guess_format("rtp", NULL, NULL);
avformat_alloc_output_context2(&fmtCtx, format, format->name, "rtp://127.0.0.1:49990");
avio_open(&fmtCtx->pb, fmtCtx->filename, AVIO_FLAG_WRITE);
//Configure the AVStream for the output format context
struct AVStream* stream = avformat_new_stream(fmtCtx, codec);
avcodec_parameters_from_context(stream->codecpar, codecCtx);
stream->time_base.num = 1;
stream->time_base.den = 25;
/* Rewrite the header */
avformat_write_header(fmtCtx, NULL);
/* Write a file for VLC */
char buf[200000];
AVFormatContext *ac[] = { fmtCtx };
av_sdp_create(ac, 1, buf, 20000);
printf("sdp:\n%s\n", buf);
FILE* fsdp = fopen("test.sdp", "w");
fprintf(fsdp, "%s", buf);
fclose(fsdp);
AVPacket pkt;
int j = 0;
for(int i = 0; i < 10000; i++)
{
fflush(stdout);
av_init_packet(&pkt);
pkt.data = NULL; // packet data will be allocated by the encoder
pkt.size = 0;
int R, G, B;
R = G = B = i % 255;
int Y = 0.257 * R + 0.504 * G + 0.098 * B + 16;
int U = -0.148 * R - 0.291 * G + 0.439 * B + 128;
int V = 0.439 * R - 0.368 * G - 0.071 * B + 128;
/* prepare a dummy image */
/* Y */
for (int y = 0; y < codecCtx->height; y++)
for (int x = 0; x < codecCtx->width; x++)
frame->data[0][y * codecCtx->width + x] = Y;
for (int y = 0; y < codecCtx->height/2; y++)
for (int x=0; x < codecCtx->width / 2; x++)
{
frame->data[1][y * frame->linesize[1] + x] = U;
frame->data[2][y * frame->linesize[2] + x] = V;
}
/* Which frame is it ? */
frame->pts = i;
/* Send the frame to the codec */
avcodec_send_frame(codecCtx, frame);
/* Use the data in the codec to the AVPacket */
switch(avcodec_receive_packet(codecCtx, &pkt))
{
case AVERROR_EOF:
printf("Stream EOF\n");
break;
case AVERROR(EAGAIN):
printf("Stream EAGAIN\n");
break;
default:
printf("Write frame %3d (size=%5d)\n", j++, pkt.size);
/* Write the data on the packet to the output format */
av_interleaved_write_frame(fmtCtx, &pkt);
/* Reset the packet */
av_packet_unref(&pkt);
break;
}
usleep(1e6/25);
}
// end
avcodec_send_frame(codecCtx, NULL);
//Free everything
av_free(codecCtx);
av_free(fmtCtx);
return 0;
}
And I can with VLC to see one image, but not a video (I have to reaload it to see another image in grayscale).
Does someone know why vlc don't play my video well ? Thank you !
After a lot of research, I found the error : I needed to call
av_packet_rescale_ts(&pkt, codecCtx->time_base, stream->time_base);
before the interleaved to correctly place the packet. What a shame...
I am trying to write c++ code on how to extract audio from mp4 format file. I have compiled the examples in ffmpeg library and tried to run the demuxing_decoding.c file. The problem is that on running the code, it starts to decode way more than the actual file size and decodes wrong codec format (the decoded files cant be run).
here is the demuxing_decoding.c that I am trying to run:
#include <math.h>
#include <libavutil/opt.h>
#include <libavcodec/avcodec.h>
#include <libavutil/channel_layout.h>
#include <libavutil/common.h>
#include <libavutil/imgutils.h>
#include <libavutil/mathematics.h>
#include <libavutil/samplefmt.h>
#define INBUF_SIZE 4096
#define AUDIO_INBUF_SIZE 20480
#define AUDIO_REFILL_THRESH 4096
/* check that a given sample format is supported by the encoder */
static int check_sample_fmt(AVCodec *codec, enum AVSampleFormat sample_fmt)
{
const enum AVSampleFormat *p = codec->sample_fmts;
while (*p != AV_SAMPLE_FMT_NONE) {
if (*p == sample_fmt)
return 1;
p++;
}
return 0;
}
/* just pick the highest supported samplerate */
static int select_sample_rate(AVCodec *codec)
{
const int *p;
int best_samplerate = 0;
if (!codec->supported_samplerates)
return 44100;
p = codec->supported_samplerates;
while (*p) {
best_samplerate = FFMAX(*p, best_samplerate);
p++;
}
return best_samplerate;
}
/* select layout with the highest channel count */
static int select_channel_layout(AVCodec *codec)
{
const uint64_t *p;
uint64_t best_ch_layout = 0;
int best_nb_channels = 0;
if (!codec->channel_layouts)
return AV_CH_LAYOUT_STEREO;
p = codec->channel_layouts;
while (*p) {
int nb_channels = av_get_channel_layout_nb_channels(*p);
if (nb_channels > best_nb_channels) {
best_ch_layout = *p;
best_nb_channels = nb_channels;
}
p++;
}
return best_ch_layout;
}
/*
* Audio encoding example
*/
static void audio_encode_example(const char *filename)
{
AVCodec *codec;
AVCodecContext *c= NULL;
AVFrame *frame;
AVPacket pkt;
int i, j, k, ret, got_output;
int buffer_size;
FILE *f;
uint16_t *samples;
float t, tincr;
printf("Encode audio file %s\n", filename);
/* find the MP2 encoder */
codec = avcodec_find_encoder(AV_CODEC_ID_MP2);
if (!codec) {
fprintf(stderr, "Codec not found\n");
exit(1);
}
c = avcodec_alloc_context3(codec);
if (!c) {
fprintf(stderr, "Could not allocate audio codec context\n");
exit(1);
}
/* put sample parameters */
c->bit_rate = 64000;
/* check that the encoder supports s16 pcm input */
c->sample_fmt = AV_SAMPLE_FMT_S16;
if (!check_sample_fmt(codec, c->sample_fmt)) {
fprintf(stderr, "Encoder does not support sample format %s",
av_get_sample_fmt_name(c->sample_fmt));
exit(1);
}
/* select other audio parameters supported by the encoder */
c->sample_rate = select_sample_rate(codec);
c->channel_layout = select_channel_layout(codec);
c->channels = av_get_channel_layout_nb_channels(c->channel_layout);
/* open it */
if (avcodec_open2(c, codec, NULL) < 0) {
fprintf(stderr, "Could not open codec\n");
exit(1);
}
f = fopen(filename, "wb");
if (!f) {
fprintf(stderr, "Could not open %s\n", filename);
exit(1);
}
/* frame containing input raw audio */
frame = av_frame_alloc();
if (!frame) {
fprintf(stderr, "Could not allocate audio frame\n");
exit(1);
}
frame->nb_samples = c->frame_size;
frame->format = c->sample_fmt;
frame->channel_layout = c->channel_layout;
/* the codec gives us the frame size, in samples,
* we calculate the size of the samples buffer in bytes */
buffer_size = av_samples_get_buffer_size(NULL, c->channels, c->frame_size,
c->sample_fmt, 0);
if (buffer_size < 0) {
fprintf(stderr, "Could not get sample buffer size\n");
exit(1);
}
samples = av_malloc(buffer_size);
if (!samples) {
fprintf(stderr, "Could not allocate %d bytes for samples buffer\n",
buffer_size);
exit(1);
}
/* setup the data pointers in the AVFrame */
ret = avcodec_fill_audio_frame(frame, c->channels, c->sample_fmt,
(const uint8_t*)samples, buffer_size, 0);
if (ret < 0) {
fprintf(stderr, "Could not setup audio frame\n");
exit(1);
}
/* encode a single tone sound */
t = 0;
tincr = 2 * M_PI * 440.0 / c->sample_rate;
for (i = 0; i < 200; i++) {
av_init_packet(&pkt);
pkt.data = NULL; // packet data will be allocated by the encoder
pkt.size = 0;
for (j = 0; j < c->frame_size; j++) {
samples[2*j] = (int)(sin(t) * 10000);
for (k = 1; k < c->channels; k++)
samples[2*j + k] = samples[2*j];
t += tincr;
}
/* encode the samples */
ret = avcodec_encode_audio2(c, &pkt, frame, &got_output);
if (ret < 0) {
fprintf(stderr, "Error encoding audio frame\n");
exit(1);
}
if (got_output) {
fwrite(pkt.data, 1, pkt.size, f);
av_free_packet(&pkt);
}
}
/* get the delayed frames */
for (got_output = 1; got_output; i++) {
ret = avcodec_encode_audio2(c, &pkt, NULL, &got_output);
if (ret < 0) {
fprintf(stderr, "Error encoding frame\n");
exit(1);
}
if (got_output) {
fwrite(pkt.data, 1, pkt.size, f);
av_free_packet(&pkt);
}
}
fclose(f);
av_freep(&samples);
av_frame_free(&frame);
avcodec_close(c);
av_free(c);
}
/*
* Audio decoding.
*/
static void audio_decode_example(const char *outfilename, const char *filename)
{
AVCodec *codec;
AVCodecContext *c= NULL;
int len;
FILE *f, *outfile;
uint8_t inbuf[AUDIO_INBUF_SIZE + AV_INPUT_BUFFER_PADDING_SIZE];
AVPacket avpkt;
AVFrame *decoded_frame = NULL;
av_init_packet(&avpkt);
printf("Decode audio file %s to %s\n", filename, outfilename);
/* find the mpeg audio decoder */
codec = avcodec_find_decoder(AV_CODEC_ID_MP2);
if (!codec) {
fprintf(stderr, "Codec not found\n");
exit(1);
}
c = avcodec_alloc_context3(codec);
if (!c) {
fprintf(stderr, "Could not allocate audio codec context\n");
exit(1);
}
/* open it */
if (avcodec_open2(c, codec, NULL) < 0) {
fprintf(stderr, "Could not open codec\n");
exit(1);
}
f = fopen(filename, "rb");
if (!f) {
fprintf(stderr, "Could not open %s\n", filename);
exit(1);
}
outfile = fopen(outfilename, "wb");
if (!outfile) {
av_free(c);
exit(1);
}
/* decode until eof */
avpkt.data = inbuf;
avpkt.size = fread(inbuf, 1, AUDIO_INBUF_SIZE, f);
while (avpkt.size > 0) {
int i, ch;
int got_frame = 0;
if (!decoded_frame) {
if (!(decoded_frame = av_frame_alloc())) {
fprintf(stderr, "Could not allocate audio frame\n");
exit(1);
}
}
len = avcodec_decode_audio4(c, decoded_frame, &got_frame, &avpkt);
if (len < 0) {
fprintf(stderr, "Error while decoding\n");
exit(1);
}
if (got_frame) {
/* if a frame has been decoded, output it */
int data_size = av_get_bytes_per_sample(c->sample_fmt);
if (data_size < 0) {
/* This should not occur, checking just for paranoia */
fprintf(stderr, "Failed to calculate data size\n");
exit(1);
}
for (i=0; i<decoded_frame->nb_samples; i++)
for (ch=0; ch<c->channels; ch++)
fwrite(decoded_frame->data[ch] + data_size*i, 1, data_size, outfile);
}
avpkt.size -= len;
avpkt.data += len;
avpkt.dts =
avpkt.pts = AV_NOPTS_VALUE;
if (avpkt.size < AUDIO_REFILL_THRESH) {
/* Refill the input buffer, to avoid trying to decode
* incomplete frames. Instead of this, one could also use
* a parser, or use a proper container format through
* libavformat. */
memmove(inbuf, avpkt.data, avpkt.size);
avpkt.data = inbuf;
len = fread(avpkt.data + avpkt.size, 1,
AUDIO_INBUF_SIZE - avpkt.size, f);
if (len > 0)
avpkt.size += len;
}
}
fclose(outfile);
fclose(f);
avcodec_close(c);
av_free(c);
av_frame_free(&decoded_frame);
}
/*
* Video encoding example
*/
static void video_encode_example(const char *filename, int codec_id)
{
AVCodec *codec;
AVCodecContext *c= NULL;
int i, ret, x, y, got_output;
FILE *f;
AVFrame *frame;
AVPacket pkt;
uint8_t endcode[] = { 0, 0, 1, 0xb7 };
printf("Encode video file %s\n", filename);
/* find the mpeg1 video encoder */
codec = avcodec_find_encoder(codec_id);
if (!codec) {
fprintf(stderr, "Codec not found\n");
exit(1);
}
c = avcodec_alloc_context3(codec);
if (!c) {
fprintf(stderr, "Could not allocate video codec context\n");
exit(1);
}
/* put sample parameters */
c->bit_rate = 400000;
/* resolution must be a multiple of two */
c->width = 352;
c->height = 288;
/* frames per second */
c->time_base = (AVRational){1,25};
/* emit one intra frame every ten frames
* check frame pict_type before passing frame
* to encoder, if frame->pict_type is AV_PICTURE_TYPE_I
* then gop_size is ignored and the output of encoder
* will always be I frame irrespective to gop_size
*/
c->gop_size = 10;
c->max_b_frames = 1;
c->pix_fmt = AV_PIX_FMT_YUV420P;
if (codec_id == AV_CODEC_ID_H264)
av_opt_set(c->priv_data, "preset", "slow", 0);
/* open it */
if (avcodec_open2(c, codec, NULL) < 0) {
fprintf(stderr, "Could not open codec\n");
exit(1);
}
f = fopen(filename, "wb");
if (!f) {
fprintf(stderr, "Could not open %s\n", filename);
exit(1);
}
frame = av_frame_alloc();
if (!frame) {
fprintf(stderr, "Could not allocate video frame\n");
exit(1);
}
frame->format = c->pix_fmt;
frame->width = c->width;
frame->height = c->height;
/* the image can be allocated by any means and av_image_alloc() is
* just the most convenient way if av_malloc() is to be used */
ret = av_image_alloc(frame->data, frame->linesize, c->width, c->height,
c->pix_fmt, 32);
if (ret < 0) {
fprintf(stderr, "Could not allocate raw picture buffer\n");
exit(1);
}
/* encode 1 second of video */
for (i = 0; i < 25; i++) {
av_init_packet(&pkt);
pkt.data = NULL; // packet data will be allocated by the encoder
pkt.size = 0;
fflush(stdout);
/* prepare a dummy image */
/* Y */
for (y = 0; y < c->height; y++) {
for (x = 0; x < c->width; x++) {
frame->data[0][y * frame->linesize[0] + x] = x + y + i * 3;
}
}
/* Cb and Cr */
for (y = 0; y < c->height/2; y++) {
for (x = 0; x < c->width/2; x++) {
frame->data[1][y * frame->linesize[1] + x] = 128 + y + i * 2;
frame->data[2][y * frame->linesize[2] + x] = 64 + x + i * 5;
}
}
frame->pts = i;
/* encode the image */
ret = avcodec_encode_video2(c, &pkt, frame, &got_output);
if (ret < 0) {
fprintf(stderr, "Error encoding frame\n");
exit(1);
}
if (got_output) {
printf("Write frame %3d (size=%5d)\n", i, pkt.size);
fwrite(pkt.data, 1, pkt.size, f);
av_free_packet(&pkt);
}
}
/* get the delayed frames */
for (got_output = 1; got_output; i++) {
fflush(stdout);
ret = avcodec_encode_video2(c, &pkt, NULL, &got_output);
if (ret < 0) {
fprintf(stderr, "Error encoding frame\n");
exit(1);
}
if (got_output) {
printf("Write frame %3d (size=%5d)\n", i, pkt.size);
fwrite(pkt.data, 1, pkt.size, f);
av_free_packet(&pkt);
}
}
/* add sequence end code to have a real mpeg file */
fwrite(endcode, 1, sizeof(endcode), f);
fclose(f);
avcodec_close(c);
av_free(c);
av_freep(&frame->data[0]);
av_frame_free(&frame);
printf("\n");
}
/*
* Video decoding example
*/
static void pgm_save(unsigned char *buf, int wrap, int xsize, int ysize,
char *filename)
{
FILE *f;
int i;
f = fopen(filename,"w");
fprintf(f, "P5\n%d %d\n%d\n", xsize, ysize, 255);
for (i = 0; i < ysize; i++)
fwrite(buf + i * wrap, 1, xsize, f);
fclose(f);
}
static int decode_write_frame(const char *outfilename, AVCodecContext *avctx,
AVFrame *frame, int *frame_count, AVPacket *pkt, int last)
{
int len, got_frame;
char buf[1024];
len = avcodec_decode_video2(avctx, frame, &got_frame, pkt);
if (len < 0) {
fprintf(stderr, "Error while decoding frame %d\n", *frame_count);
return len;
}
if (got_frame) {
printf("Saving %sframe %3d\n", last ? "last " : "", *frame_count);
fflush(stdout);
/* the picture is allocated by the decoder, no need to free it */
snprintf(buf, sizeof(buf), outfilename, *frame_count);
pgm_save(frame->data[0], frame->linesize[0],
frame->width, frame->height, buf);
(*frame_count)++;
}
if (pkt->data) {
pkt->size -= len;
pkt->data += len;
}
return 0;
}
static void video_decode_example(const char *outfilename, const char *filename)
{
AVCodec *codec;
AVCodecContext *c= NULL;
int frame_count;
FILE *f;
AVFrame *frame;
uint8_t inbuf[INBUF_SIZE + AV_INPUT_BUFFER_PADDING_SIZE];
AVPacket avpkt;
av_init_packet(&avpkt);
/* set end of buffer to 0 (this ensures that no overreading happens for damaged mpeg streams) */
memset(inbuf + INBUF_SIZE, 0, AV_INPUT_BUFFER_PADDING_SIZE);
printf("Decode video file %s to %s\n", filename, outfilename);
/* find the mpeg1 video decoder */
codec = avcodec_find_decoder(AV_CODEC_ID_MPEG1VIDEO);
if (!codec) {
fprintf(stderr, "Codec not found\n");
exit(1);
}
c = avcodec_alloc_context3(codec);
if (!c) {
fprintf(stderr, "Could not allocate video codec context\n");
exit(1);
}
if (codec->capabilities & AV_CODEC_CAP_TRUNCATED)
c->flags |= AV_CODEC_FLAG_TRUNCATED; // we do not send complete frames
/* For some codecs, such as msmpeg4 and mpeg4, width and height
MUST be initialized there because this information is not
available in the bitstream. */
/* open it */
if (avcodec_open2(c, codec, NULL) < 0) {
fprintf(stderr, "Could not open codec\n");
exit(1);
}
f = fopen(filename, "rb");
if (!f) {
fprintf(stderr, "Could not open %s\n", filename);
exit(1);
}
frame = av_frame_alloc();
if (!frame) {
fprintf(stderr, "Could not allocate video frame\n");
exit(1);
}
frame_count = 0;
for (;;) {
avpkt.size = fread(inbuf, 1, INBUF_SIZE, f);
if (avpkt.size == 0)
break;
/* NOTE1: some codecs are stream based (mpegvideo, mpegaudio)
and this is the only method to use them because you cannot
know the compressed data size before analysing it.
BUT some other codecs (msmpeg4, mpeg4) are inherently frame
based, so you must call them with all the data for one
frame exactly. You must also initialize 'width' and
'height' before initializing them. */
/* NOTE2: some codecs allow the raw parameters (frame size,
sample rate) to be changed at any frame. We handle this, so
you should also take care of it */
/* here, we use a stream based decoder (mpeg1video), so we
feed decoder and see if it could decode a frame */
avpkt.data = inbuf;
while (avpkt.size > 0)
if (decode_write_frame(outfilename, c, frame, &frame_count, &avpkt, 0) < 0)
exit(1);
}
/* some codecs, such as MPEG, transmit the I and P frame with a
latency of one frame. You must do the following to have a
chance to get the last frame of the video */
avpkt.data = NULL;
avpkt.size = 0;
decode_write_frame(outfilename, c, frame, &frame_count, &avpkt, 1);
fclose(f);
avcodec_close(c);
av_free(c);
av_frame_free(&frame);
printf("\n");
}
int main(int argc, char **argv)
{
const char *output_type;
/* register all the codecs */
avcodec_register_all();
if (argc < 2) {
printf("usage: %s output_type\n"
"API example program to decode/encode a media stream with libavcodec.\n"
"This program generates a synthetic stream and encodes it to a file\n"
"named test.h264, test.mp2 or test.mpg depending on output_type.\n"
"The encoded stream is then decoded and written to a raw data output.\n"
"output_type must be chosen between 'h264', 'mp2', 'mpg'.\n",
argv[0]);
return 1;
}
output_type = argv[1];
if (!strcmp(output_type, "h264")) {
video_encode_example("test.h264", AV_CODEC_ID_H264);
} else if (!strcmp(output_type, "mp2")) {
audio_encode_example("test.mp2");
audio_decode_example("test.pcm", "test.mp2");
} else if (!strcmp(output_type, "mpg")) {
video_encode_example("test.mpg", AV_CODEC_ID_MPEG1VIDEO);
video_decode_example("test%02d.pgm", "test.mpg");
} else {
fprintf(stderr, "Invalid output type '%s', choose between 'h264', 'mp2', or 'mpg'\n",
output_type);
return 1;
}
return 0;
}
What could be wrong?
The command I used is:
./demuxing_decoding /home/cortana/Burn.mp4 /home/cortana/Desktop/Burn.mp4 /home/cortana/Desktop/Burn.aac
I have a program which capture video from webcam, encode with ffmpeg, encoded packet then write to buffer. At the receiver side, read from buffer decode with ffmpeg and play.
Now I merge sender and receiver in one program for testing. It works fine with AV_CODEC_ID_MPEG1VIDEO, but when I change the ffmpeg codec to AV_CODEC_ID_H264, at the decoding progress, it shows error:
The whole program is here FYI, I made a loop to let the whole progress run twice.
What is the cause of the error, is there anything special for H264? Thanks in advance!
#include <math.h>
extern "C" {
#include <libavutil/opt.h>
#include <libavcodec/avcodec.h>
#include <libavutil/channel_layout.h>
#include <libavutil/common.h>
#include <libavutil/imgutils.h>
#include <libavutil/mathematics.h>
#include <libavutil/samplefmt.h>
#include <libswscale/swscale.h>
#include "v4l2.h"
}
#include "opencv2/highgui/highgui.hpp"
#include <iostream>
using namespace cv;
using namespace std;
#define INBUF_SIZE 4096
static uint8_t inbuf[INBUF_SIZE + FF_INPUT_BUFFER_PADDING_SIZE];
static AVCodec *codec;
static AVCodecContext *c= NULL;
static int ret, got_output;
static int frame_count;
static FILE *f;
static AVPacket pkt;
static AVFrame *frame;
static AVFrame *frameDecode;
static AVFrame *framergb;
static uint8_t endcode[] = { 0, 0, 1, 0xb7 };
static AVPacket avpkt;
int totalSize=0;
#define SUBSITY 3
static int decode_write_frame(AVCodecContext *avctx,
AVFrame *frame, int *frame_count, AVPacket *pkt, int last)
{
int len, got_frame;
char buf[1024];
struct SwsContext *convert_ctx;
Mat m;
AVFrame dst;
len = avcodec_decode_video2(avctx, frame, &got_frame, pkt);
if (len < 0) {
fprintf(stderr, "Error while decoding frame %d\n", *frame_count);
return len;
}
if (got_frame) {
printf("Saving %s frame %3d\n", last ? "last " : "", *frame_count);
fflush(stdout);
int w = avctx->width;
int h = avctx->height;
/*convert AVFrame to opencv Mat frame*/
m = cv::Mat(h, w, CV_8UC3);
dst.data[0] = (uint8_t *)m.data;
avpicture_fill( (AVPicture *)&dst, dst.data[0], PIX_FMT_BGR24, w, h);
enum PixelFormat src_pixfmt = (enum PixelFormat)frame->format;
enum PixelFormat dst_pixfmt = PIX_FMT_BGR24;
convert_ctx = sws_getContext(w, h, src_pixfmt, w, h, dst_pixfmt,
SWS_FAST_BILINEAR, NULL, NULL, NULL);
if(convert_ctx == NULL) {
fprintf(stderr, "Cannot initialize the conversion context!\n");
exit(1);
}
sws_scale(convert_ctx, frame->data, frame->linesize, 0, h,
dst.data, dst.linesize);
imshow("MyVideo", m);
//video.write(m);
waitKey(10); //wait next frame time
(*frame_count)++;
}
if (pkt->data) {
pkt->size -= len;
pkt->data += len;
}
return 0;
}
static void video_decode_example(char *inbufout)
{
int bytes;
uint8_t *buffer;
av_init_packet(&avpkt);
memset(inbuf + INBUF_SIZE, 0, FF_INPUT_BUFFER_PADDING_SIZE);
codec = avcodec_find_decoder(AV_CODEC_ID_H264);
if (!codec) {
fprintf(stderr, "Codec not found\n");
exit(1);
}
c = avcodec_alloc_context3(codec);
if (!c) {
fprintf(stderr, "Could not allocate video codec context\n");
exit(1);
}
if(codec->capabilities&CODEC_CAP_TRUNCATED)
c->flags|= CODEC_FLAG_TRUNCATED; /* we do not send complete frames */
/* open it */
if (avcodec_open2(c, codec, NULL) < 0) {
fprintf(stderr, "Could not open codec\n");
exit(1);
}
frameDecode = avcodec_alloc_frame();
if (!frameDecode) {
fprintf(stderr, "Could not allocate video frame\n");
exit(1);
}
bytes=avpicture_get_size(PIX_FMT_RGB24, CAMER_WIDTH, CAMER_HEIGHT);
buffer=(uint8_t *)av_malloc(bytes*sizeof(uint8_t));
avpicture_fill((AVPicture *)framergb, buffer, PIX_FMT_RGB24,
CAMER_WIDTH, CAMER_HEIGHT);*/
frame_count = 0;
namedWindow("MyVideo",CV_WINDOW_AUTOSIZE); //create a window called "MyVideo"
int size1=0;
for(;;) {
memcpy(inbuf,inbufout+size1,INBUF_SIZE);
size1+=INBUF_SIZE;
if (size1>(totalSize-INBUF_SIZE))
break;
avpkt.size=INBUF_SIZE;
avpkt.data = inbuf;
/*frame by frame process*/
while (avpkt.size > 0)
if (decode_write_frame(c, frameDecode, &frame_count, &avpkt, 0) < 0)
exit(1);
}
avpkt.data = NULL;
avpkt.size = 0;
decode_write_frame(c, frameDecode, &frame_count, &avpkt, 1);
}
static void init_video_encode(const char *filename, AVCodecID codec_id, int max_f)
{
printf("Encode video file %s\n", filename);
/* find the mpeg1 video encoder */
codec = avcodec_find_encoder(codec_id);
if (!codec) {
fprintf(stderr, "Codec not found\n");
exit(1);
}
c = avcodec_alloc_context3(codec);
if (!c) {
fprintf(stderr, "Could not allocate video codec context\n");
exit(1);
}
/* put sample parameters */
c->bit_rate = 400000;
/* resolution must be a multiple of two */
c->width = 640;
c->height = 480;
/* frames per second */
c->time_base= (AVRational){1,25};
c->gop_size = 10; /* emit one intra frame every ten frames */
c->max_b_frames=max_f;
c->pix_fmt = AV_PIX_FMT_YUV420P;
if(codec_id == AV_CODEC_ID_H264)
av_opt_set(c->priv_data, "preset", "slow", 0);
/* open it */
if (avcodec_open2(c, codec, NULL) < 0) {
fprintf(stderr, "Could not open codec\n");
exit(1);
}
frame = avcodec_alloc_frame();
if (!frame) {
fprintf(stderr, "Could not allocate video frame\n");
exit(1);
}
frame->format = c->pix_fmt;
frame->width = c->width;
frame->height = c->height;
ret = av_image_alloc(frame->data, frame->linesize, c->width, c->height,
c->pix_fmt, 32);
/* get the delayed frames */
if (ret < 0) {
fprintf(stderr, "Could not allocate raw picture buffer\n");
exit(1);
}
printf("\n");
}
int video_encode(int frameNo,char *inbufout)
{
static int count = 0;
static int i = 0;
/* encode 1 frame of video */
av_init_packet(&pkt);
pkt.data = NULL; // packet data will be allocated by the encoder
pkt.size = 0;
//cout<<"\nBefore YUV\n";
if(count == 0)
read_yuv420(frame->data[0]);
count ++;
if(count == SUBSITY) {
count = 0;
}
frame->pts = i++;
/* encode the image */
ret = avcodec_encode_video2(c, &pkt, frame, &got_output);
if (ret < 0) {
fprintf(stderr, "Error encoding frame\n");
return -1;
}
if (got_output) {
printf("Write frame %3d (size=%5d)\n", i, pkt.size);
memcpy(inbufout+totalSize,pkt.data,pkt.size);
totalSize+=pkt.size;
fwrite(pkt.data, 1, pkt.size, f);
av_free_packet(&pkt);
}
return 0;
}
void cancle_encode(void)
{
fclose(f);
avcodec_close(c);
av_free(c);
av_freep(&frame->data[0]);
avcodec_free_frame(&frame);
}
int main(int argc, char **argv)
{
int i;
char inbufout[25*50*(INBUF_SIZE + FF_INPUT_BUFFER_PADDING_SIZE)];
if(init_v4l2() < 0) {
printf("can't open camera\n");
return 0;
}
/* register all the codecs */
avcodec_register_all();
for(int j=0;j<2;j++){
//init_video_encode("test.mpg", AV_CODEC_ID_MPEG1VIDEO, 15);
init_video_encode("test.mpg", AV_CODEC_ID_H264, 15);
//for(i = 0;i< 10*15;i++ ) {
for(i = 0;i< 25*10;i++ ) {
if(video_encode(i,inbufout) < 0)
return 0;
}
cout<<"\n"<<totalSize<<"\n"<<endl;
video_decode_example(inbufout);
cancle_encode();
totalSize=0;
}
exit_v4l2();
return 0;
}
You need to include a parser. The ffmpeg mpeg1/2 decoders happen to work fine without a parser, but h264/mpeg4/vp9 need a parser, or you'll get errors like the above.
Note that if you use libavformat for demuxing and call avformat_read_frame(), it will automatically parse for you, but since you're doing buffer management yourself, you need to include the parser yourself also.
I am having issues encoding screen captures, into a h.264 file for viewing. The program below is cobbled together from examples here and here. The first example, uses an older version of the ffmpeg api. So I tried to update that example for use in my program. The file is created and has something written to it, but when I view the file. The encoded images are all distorted. I am able to run the video encoding example from the ffmpeg api successfully. This is my first time posting, so if I missed anything please let me know.
I appreciate any assistance that is given.
My program:
#include <Windows.h>
#include <string>
#include <sstream>
#include <time.h>
#include <iostream>
#include <dwmapi.h>
extern "C"{
#include <stdint.h>
#include <libavcodec/avcodec.h>
#include <libavutil/imgutils.h>
#include <libswscale/swscale.h>
#include <libavutil/opt.h>
}
using namespace std;
void ScreenShot(const char* BmpName, uint8_t *frame)
{
HWND DesktopHwnd = GetDesktopWindow();
RECT DesktopParams;
HDC DevC = GetDC(DesktopHwnd);
GetWindowRect(DesktopHwnd,&DesktopParams);
DWORD Width = DesktopParams.right - DesktopParams.left;
DWORD Height = DesktopParams.bottom - DesktopParams.top;
DWORD FileSize = sizeof(BITMAPFILEHEADER)+sizeof(BITMAPINFOHEADER)+(sizeof(RGBTRIPLE)+1*(Width*Height*4));
char *BmpFileData = (char*)GlobalAlloc(0x0040,FileSize);
PBITMAPFILEHEADER BFileHeader = (PBITMAPFILEHEADER)BmpFileData;
PBITMAPINFOHEADER BInfoHeader = (PBITMAPINFOHEADER)&BmpFileData[sizeof(BITMAPFILEHEADER)];
BFileHeader->bfType = 0x4D42; // BM
BFileHeader->bfSize = sizeof(BITMAPFILEHEADER);
BFileHeader->bfOffBits = sizeof(BITMAPFILEHEADER)+sizeof(BITMAPINFOHEADER);
BInfoHeader->biSize = sizeof(BITMAPINFOHEADER);
BInfoHeader->biPlanes = 1;
BInfoHeader->biBitCount = 32;
BInfoHeader->biCompression = BI_RGB;
BInfoHeader->biHeight = Height;
BInfoHeader->biWidth = Width;
RGBTRIPLE *Image = (RGBTRIPLE*)&BmpFileData[sizeof(BITMAPFILEHEADER)+sizeof(BITMAPINFOHEADER)];
RGBTRIPLE color;
//pPixels = (RGBQUAD **)new RGBQUAD[sizeof(BITMAPFILEHEADER) + sizeof(BITMAPINFOHEADER)];
int start = clock();
HDC CaptureDC = CreateCompatibleDC(DevC);
HBITMAP CaptureBitmap = CreateCompatibleBitmap(DevC,Width,Height);
SelectObject(CaptureDC,CaptureBitmap);
BitBlt(CaptureDC,0,0,Width,Height,DevC,0,0,SRCCOPY|CAPTUREBLT);
GetDIBits(CaptureDC,CaptureBitmap,0,Height,frame,(LPBITMAPINFO)BInfoHeader, DIB_RGB_COLORS);
int end = clock();
cout << "it took " << end - start << " to capture a frame" << endl;
DWORD Junk;
HANDLE FH = CreateFileA(BmpName,GENERIC_WRITE,FILE_SHARE_WRITE,0,CREATE_ALWAYS,0,0);
WriteFile(FH,BmpFileData,FileSize,&Junk,0);
CloseHandle(FH);
GlobalFree(BmpFileData);
}
void video_encode_example(const char *filename, int codec_id)
{
AVCodec *codec;
AVCodecContext *c= NULL;
int i, ret, x, y, got_output;
FILE *f;
AVFrame *frame;
AVPacket pkt;
uint8_t endcode[] = { 0, 0, 1, 0xb7 };
printf("Encode video file %s\n", filename);
/* find the mpeg1 video encoder */
codec = avcodec_find_encoder(AV_CODEC_ID_H264);
if (!codec) {
fprintf(stderr, "Codec not found\n");
cin.get();
exit(1);
}
c = avcodec_alloc_context3(codec);
if (!c) {
fprintf(stderr, "Could not allocate video codec context\n");
cin.get();
exit(1);
}
/* put sample parameters */
c->bit_rate = 400000;
/* resolution must be a multiple of two */
c->width = 352;
c->height = 288;
/* frames per second */
c->time_base.num=1;
c->time_base.den = 25;
c->gop_size = 10; /* emit one intra frame every ten frames */
c->max_b_frames=1;
c->pix_fmt = AV_PIX_FMT_YUV420P;
if(codec_id == AV_CODEC_ID_H264)
av_opt_set(c->priv_data, "preset", "slow", 0);
/* open it */
if (avcodec_open2(c, codec, NULL) < 0) {
fprintf(stderr, "Could not open codec\n");
exit(1);
}
f = fopen(filename, "wb");
if (!f) {
fprintf(stderr, "Could not open %s\n", filename);
exit(1);
}
frame = av_frame_alloc();
if (!frame) {
fprintf(stderr, "Could not allocate video frame\n");
exit(1);
}
frame->format = c->pix_fmt;
frame->width = c->width;
frame->height = c->height;
/* the image can be allocated by any means and av_image_alloc() is
just the most convenient way if av_malloc() is to be used */
ret = av_image_alloc(frame->data, frame->linesize, c->width, c->height, c->pix_fmt, 32);
if (ret < 0) {
fprintf(stderr, "Could not allocate raw picture buffer\n");
exit(1);
}
/* encode 1 second of video */
for(i=0;i<250;i++) {
av_init_packet(&pkt);
pkt.data = NULL; // packet data will be allocated by the encoder
pkt.size = 0;
fflush(stdout);
/* prepare a dummy image */
/* Y */
for(y=0;y<c->height;y++) {
for(x=0;x<c->width;x++) {
frame->data[0][y * frame->linesize[0] + x] = x + y + i * 3;
}
}
/* Cb and Cr */
for(y=0;y<c->height/2;y++) {
for(x=0;x<c->width/2;x++) {
frame->data[1][y * frame->linesize[1] + x] = 128 + y + i * 2;
frame->data[2][y * frame->linesize[2] + x] = 64 + x + i * 5;
}
}
frame->pts = i;
/* encode the image */
ret = avcodec_encode_video2(c, &pkt, frame, &got_output);
if (ret < 0) {
fprintf(stderr, "Error encoding frame\n");
exit(1);
}
if (got_output) {
printf("Write frame %3d (size=%5d)\n", i, pkt.size);
fwrite(pkt.data, 1, pkt.size, f);
av_free_packet(&pkt);
}
}
/* get the delayed frames */
for (got_output = 1; got_output; i++) {
fflush(stdout);
ret = avcodec_encode_video2(c, &pkt, NULL, &got_output);
if (ret < 0) {
fprintf(stderr, "Error encoding frame\n");
exit(1);
}
if (got_output) {
printf("Write frame %3d (size=%5d)\n", i, pkt.size);
fwrite(pkt.data, 1, pkt.size, f);
av_free_packet(&pkt);
}
}
/* add sequence end code to have a real mpeg file */
fwrite(endcode, 1, sizeof(endcode), f);
fclose(f);
avcodec_close(c);
av_free(c);
av_freep(&frame->data[0]);
av_frame_free(&frame);
printf("\n");
}
void write_video_frame()
{
}
int lineSizeOfFrame(int width)
{
return (width*24 + 31)/32 * 4;//((width*24 / 8) + 3) & ~3;//(width*24 + 31)/32 * 4;
}
int getScreenshotWithCursor(uint8_t* frame)
{
int successful = 0;
HDC screen, bitmapDC;
HBITMAP screen_bitmap;
screen = GetDC(NULL);
RECT DesktopParams;
HWND desktop = GetDesktopWindow();
GetWindowRect(desktop, &DesktopParams);
int width = DesktopParams.right;
int height = DesktopParams.bottom;
bitmapDC = CreateCompatibleDC(screen);
screen_bitmap = CreateCompatibleBitmap(screen, width, height);
SelectObject(bitmapDC, screen_bitmap);
if (BitBlt(bitmapDC, 0, 0, width, height, screen, 0, 0, SRCCOPY))
{
int pos_x, pos_y;
HICON hcur;
ICONINFO icon_info;
CURSORINFO cursor_info;
cursor_info.cbSize = sizeof(CURSORINFO);
if (GetCursorInfo(&cursor_info))
{
if (cursor_info.flags == CURSOR_SHOWING)
{
hcur = CopyIcon(cursor_info.hCursor);
if (GetIconInfo(hcur, &icon_info))
{
pos_x = cursor_info.ptScreenPos.x - icon_info.xHotspot;
pos_y = cursor_info.ptScreenPos.y - icon_info.yHotspot;
DrawIcon(bitmapDC, pos_x, pos_y, hcur);
if (icon_info.hbmColor) DeleteObject(icon_info.hbmColor);
if (icon_info.hbmMask) DeleteObject(icon_info.hbmMask);
}
}
}
int header_size = sizeof(BITMAPINFOHEADER) + 256*sizeof(RGBQUAD);
size_t line_size = lineSizeOfFrame(width);
PBITMAPINFO lpbi = (PBITMAPINFO) malloc(header_size);
lpbi->bmiHeader.biSize = header_size;
lpbi->bmiHeader.biWidth = width;
lpbi->bmiHeader.biHeight = height;
lpbi->bmiHeader.biPlanes = 1;
lpbi->bmiHeader.biBitCount = 24;
lpbi->bmiHeader.biCompression = BI_RGB;
lpbi->bmiHeader.biSizeImage = height*line_size;
lpbi->bmiHeader.biXPelsPerMeter = 0;
lpbi->bmiHeader.biYPelsPerMeter = 0;
lpbi->bmiHeader.biClrUsed = 0;
lpbi->bmiHeader.biClrImportant = 0;
if (GetDIBits(bitmapDC, screen_bitmap, 0, height, (LPVOID)frame, lpbi, DIB_RGB_COLORS))
{
int i;
uint8_t *buf_begin = frame;
uint8_t *buf_end = frame + line_size*(lpbi->bmiHeader.biHeight - 1);
void *temp = malloc(line_size);
for (i = 0; i < lpbi->bmiHeader.biHeight / 2; ++i)
{
memcpy(temp, buf_begin, line_size);
memcpy(buf_begin, buf_end, line_size);
memcpy(buf_end, temp, line_size);
buf_begin += line_size;
buf_end -= line_size;
}
cout << *buf_begin << endl;
free(temp);
successful = 1;
}
free(lpbi);
}
DeleteObject(screen_bitmap);
DeleteDC(bitmapDC);
ReleaseDC(NULL, screen);
return successful;
}
int main()
{
RECT DesktopParams;
HWND desktop = GetDesktopWindow();
GetWindowRect(desktop, &DesktopParams);
int width = DesktopParams.right;
int height = DesktopParams.bottom;
uint8_t *frame = (uint8_t *)malloc(width * height);
AVCodec *codec;
AVCodecContext *codecContext = NULL;
AVPacket packet;
FILE *f;
AVFrame *pictureYUV = NULL;
AVFrame *pictureRGB;
avcodec_register_all();
codec = avcodec_find_encoder(AV_CODEC_ID_H264);
if(!codec)
{
cout << "codec not found!" << endl;
cin.get();
return 1;
}
else
{
cout << "codec h265 found!" << endl;
}
codecContext = avcodec_alloc_context3(codec);
codecContext->bit_rate = width * height * 4;
codecContext->width = width;
codecContext->height = height;
codecContext->time_base.num = 1;
codecContext->time_base.den = 250;
codecContext->gop_size = 10;
codecContext->max_b_frames = 1;
codecContext->keyint_min = 1;
codecContext->i_quant_factor = (float)0.71; // qscale factor between P and I frames
codecContext->b_frame_strategy = 20; ///// find out exactly what this does
codecContext->qcompress = (float)0.6; ///// find out exactly what this does
codecContext->qmin = 20; // minimum quantizer
codecContext->qmax = 51; // maximum quantizer
codecContext->max_qdiff = 4; // maximum quantizer difference between frames
codecContext->refs = 4; // number of reference frames
codecContext->trellis = 1;
codecContext->pix_fmt = AV_PIX_FMT_YUV420P;
codecContext->codec_id = AV_CODEC_ID_H264;
codecContext->codec_type = AVMEDIA_TYPE_VIDEO;
if(avcodec_open2(codecContext, codec, NULL) < 0)
{
cout << "couldn't open codec" << endl;
cout << stderr << endl;
cin.get();
return 1;
}
else
{
cout << "opened h265 codec!" << endl;
cin.get();
}
f = fopen("test.h264", "wb");
if(!f)
{
cout << "Unable to open file" << endl;
return 1;
}
struct SwsContext *img_convert_ctx = sws_getContext(codecContext->width, codecContext->height, PIX_FMT_RGB32, codecContext->width,
codecContext->height, codecContext->pix_fmt, SWS_BILINEAR, NULL, NULL, NULL);
int got_output = 0, i = 0;
uint8_t encode[] = { 0, 0, 1, 0xb7 };
try
{
for(i = 0; i < codecContext->time_base.den; i++)
{
av_init_packet(&packet);
packet.data = NULL;
packet.size = 0;
pictureRGB = av_frame_alloc();
pictureYUV = av_frame_alloc();
getScreenshotWithCursor(frame);
//ScreenShot("example.bmp", frame);
int nbytes = avpicture_get_size(AV_PIX_FMT_YUV420P, codecContext->width, codecContext->height); // allocating outbuffer
uint8_t* outbuffer = (uint8_t*)av_malloc(nbytes*sizeof(uint8_t));
pictureRGB = av_frame_alloc();
pictureYUV = av_frame_alloc();
avpicture_fill((AVPicture*)pictureRGB, frame, PIX_FMT_RGB32, codecContext->width, codecContext->height); // fill image with input screenshot
avpicture_fill((AVPicture*)pictureYUV, outbuffer, PIX_FMT_YUV420P, codecContext->width, codecContext->height);
av_image_alloc(pictureYUV->data, pictureYUV->linesize, codecContext->width, codecContext->height, codecContext->pix_fmt, 32);
sws_scale(img_convert_ctx, pictureRGB->data, pictureRGB->linesize, 0, codecContext->height, pictureYUV->data, pictureYUV->linesize);
pictureYUV->pts = i;
avcodec_encode_video2(codecContext, &packet, pictureYUV, &got_output);
if(got_output)
{
printf("Write frame %3d (size=%5d)\n", i, packet.size);
fwrite(packet.data, 1, packet.size, f);
av_free_packet(&packet);
}
//av_frame_free(&pictureRGB);
//av_frame_free(&pictureYUV);
}
for(got_output = 1; got_output; i++)
{
fflush(stdout);
avcodec_encode_video2(codecContext, &packet, NULL, &got_output);
if (got_output) {
printf("Write frame %3d (size=%5d)\n", i, packet.size);
fwrite(packet.data, 1, packet.size, f);
av_free_packet(&packet);
}
}
}
catch(std::exception ex)
{
cout << ex.what() << endl;
}
avcodec_close(codecContext);
av_free(codecContext);
av_freep(&pictureYUV->data[0]);
//av_frame_free(&picture);
fwrite(encode, 1, sizeof(encode), f);
fclose(f);
cin.get();
return 0;
}