Related
After decoding some videos from iphone, I find the image has a strange border on the right.
It is not black but some random pix (width:4).
why i get the border?
how to cut this border or to turn it to black?
Most of videos dont have this problem.
here is the sample code:
the code will load a video from memory, and decode it
int VideoParseFFmpeg::read_packet(void *opaque, uint8_t *buf, int buf_size) {
struct buffer_data *bd = (struct buffer_data *) opaque;
buf_size = FFMIN(buf_size, bd->size_);
if (!buf_size)
return AVERROR_EOF;
memcpy(buf, bd->ptr_, buf_size);
bd->ptr_ += buf_size;
bd->size_ -= buf_size;
return buf_size;
}
int VideoParseFFmpeg::LoadContent(const std::string &video_content) {
int ret = 0;
...
video_size_ = video_content.size();
avio_ctx_buffer_size_ = video_size_ + AV_INPUT_BUFFER_PADDING_SIZE;
avio_ctx_buffer_ = static_cast<uint8_t *>(av_malloc(avio_ctx_buffer_size_));
bd_.ptr_ = (uint8_t *)(video_content.c_str());
bd_.size_ = video_content.size();
av_register_all();
input_ctx_ = avformat_alloc_context();
avio_ctx_ = avio_alloc_context(avio_ctx_buffer_,
avio_ctx_buffer_size_,
0,
&bd_,
&read_packet,
NULL,
NULL);
if ((ret = av_probe_input_buffer(avio_ctx_, &in_fmt_, "", NULL, 0, 0)) < 0) {
LOGGER_WARN(Log::GetLog(), "fail to prob input, err [{}]", AVERROR(ret));
return -1;
}
input_ctx_->pb = avio_ctx_;
/* open the input file */
if ((ret = avformat_open_input(&input_ctx_, "", in_fmt_, NULL)) != 0) {
LOGGER_WARN(Log::GetLog(), "fail to open input, err [{}]", AVERROR(ret));
return -1;
}
if ((ret = avformat_find_stream_info(input_ctx_, NULL)) < 0) {
LOGGER_WARN(Log::GetLog(),
"fail to find input stream information, err[{}]",
AVERROR(ret));
return -1;
}
/* find the video stream information */
if ((ret = av_find_best_stream(input_ctx_, AVMEDIA_TYPE_VIDEO, -1, -1, &decoder_, 0)) < 0) {
LOGGER_WARN(Log::GetLog(), "fail to find a video stream from input, err[{}]", ret);
return -1;
}
video_stream_idx_ = ret;
if (!(decoder_ctx_ = avcodec_alloc_context3(decoder_))) {
LOGGER_WARN(Log::GetLog(), "fail to alloc avcodec context");
return -1;
}
video_stream_ = input_ctx_->streams[video_stream_idx_];
if ((ret = avcodec_parameters_to_context(decoder_ctx_, video_stream_->codecpar)) < 0) {
LOGGER_WARN(Log::GetLog(), "fail to convert parameters to context, err [{}]", ret);
return -1;
}
if ((ret = avcodec_open2(decoder_ctx_, decoder_, NULL)) < 0) {
LOGGER_WARN(Log::GetLog(), "fail to open decodec, err[{}]", ret);
return -1;
}
return 0;
}
void VideoParseFFmpeg::GetFrames(std::vector<cv::Mat> &frames) {
while (1) {
...
decode_write(decoder_ctx_, &packet_, &buffer, frames);
...
}
//flush
...
}
cv::Mat VideoParseFFmpeg::avFrame2Mat(AVFrame *pAvFrame,
AVCodecContext *pCodecCtx,
AVPixelFormat src_fmt) {
AVFrame *pFrameBGR = av_frame_alloc(); // 存储解码后转换的BGR数据
int w = pAvFrame->width;
int h = pAvFrame->height;
auto size = av_image_get_buffer_size(AV_PIX_FMT_BGR24, w, h, 1);
cv::Mat out(h, w, CV_8UC3);
int ret = av_image_fill_arrays(pFrameBGR->data,
pFrameBGR->linesize,
out.data,
AV_PIX_FMT_BGR24,
w,
h,
1);
img_convert_ctx_ = sws_getCachedContext(img_convert_ctx_,
w,
h,
ConvertDeprecatedFormat(src_fmt),
w,
h,
AV_PIX_FMT_BGR24,
SWS_BICUBIC,
NULL, NULL, NULL);
sws_scale(img_convert_ctx_,
(const uint8_t *const *) pAvFrame->data,
pAvFrame->linesize,
0,
pCodecCtx->height,
pFrameBGR->data,
pFrameBGR->linesize);
av_free(pFrameBGR);
return out;
}
int VideoParseFFmpeg::decode_write(AVCodecContext *avctx,
AVPacket *packet,
uint8_t **buffer,
std::vector<cv::Mat> &p_mat_out) {
AVFrame *frame = NULL, *sw_frame = NULL;
AVFrame *tmp_frame = NULL;
int ret = 0;
ret = avcodec_send_packet(avctx, packet);
...
while (1) {
auto clear = [&frame, &sw_frame, this] {
if (frame != NULL)
av_frame_free(&frame);
if (sw_frame != NULL)
av_frame_free(&sw_frame);
av_packet_unref(&packet_);
};
...
ret = avcodec_receive_frame(avctx, frame);
if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF) {
clear();
return 0;
} else if (ret < 0) {
LOGGER_WARN(Log::GetLog(), "error while decoding, err[{}]", AVERROR(ret));
clear();
return ret;
}
tmp_frame = frame;
p_mat_out.push_back(avFrame2Mat(tmp_frame,
avctx,
(AVPixelFormat) tmp_frame->format));
clear();
}
}
After replacing lib tcmalloc with a newer version, the border turns to be a black line (used to be a random line), like this.
there is image content in the area of the border in the original image, how to fix it?
i encode currently a QImage from RGB888 to H264, but i want to encode each image (even if this is not the perfect way) by itself.
Im able to encode the image, but its needed to send the same image 46 times. And i dont know what i do wrong (probably wrong config of the encode, but i cannot find the issue there).
Afterwards i decode this image and then convert it back to a QImage. I do this only for testing some other code.
avcodec_register_all();
AVCodec *nVidiaCodec = avcodec_find_encoder_by_name("h264_nvenc");
if (!nVidiaCodec)
{
return false;
}
AVCodecContext* av_codec_context_ = NULL;
av_codec_context_ = avcodec_alloc_context3(nVidiaCodec);
if (!av_codec_context_)
{
return false;
}
av_codec_context_->width = dst->width;
av_codec_context_->height = dst->height;
av_codec_context_->pix_fmt = AV_PIX_FMT_YUV420P;
av_codec_context_->gop_size = 1;
av_codec_context_->keyint_min = 0;
av_codec_context_->scenechange_threshold = 0;
av_codec_context_->bit_rate = 8000000;
av_codec_context_->time_base.den = 1;
av_codec_context_->time_base.num = 1;
av_codec_context_->refs = 0;
av_codec_context_->qmin = 1;
av_codec_context_->qmax = 1;
av_codec_context_->b_frame_strategy = 0;
av_codec_context_->max_b_frames = 0;
av_codec_context_->thread_count = 1;
av_opt_set(av_codec_context_, "preset", "slow", 0);
av_opt_set(av_codec_context_, "tune", "zerolatency", 0);
int ret = avcodec_open2(av_codec_context_, nVidiaCodec, NULL);
if (0 > ret)
{
return false;
}
AVFrame *picture = av_frame_alloc();
picture->format = AV_PIX_FMT_RGB24;
picture->width = dst->width;
picture->height = dst->height;
ret = avpicture_fill((AVPicture *)picture, imgSrc.bits(), AV_PIX_FMT_RGB24, dst->width, dst->height);
if (0 > ret)
{
return false;
}
AVFrame *tmp_picture = av_frame_alloc();
tmp_picture->format = AV_PIX_FMT_YUV420P;
tmp_picture->width = dst->width;
tmp_picture->height = dst->height;
ret = av_frame_get_buffer(tmp_picture, 32);
SwsContext *img_convert_ctx = sws_getContext(av_codec_context_->width, av_codec_context_->height, AV_PIX_FMT_RGB24, av_codec_context_->width, av_codec_context_->height, av_codec_context_->pix_fmt, SWS_BICUBIC, NULL, NULL, NULL);
if (!img_convert_ctx)
{
return false;
}
ret = sws_scale(img_convert_ctx, picture->data, picture->linesize, 0, av_codec_context_->height, tmp_picture->data, tmp_picture->linesize);
if (0 > ret)
{
return false;
}
ret = avcodec_send_frame(av_codec_context_, tmp_picture);
if (0 > ret)
{
return false;
}
AVPacket pkt;
av_init_packet(&pkt);
pkt.data = NULL;
pkt.size = 0;
do
{
ret = avcodec_receive_packet(av_codec_context_, &pkt);
if (ret == 0)
{
break;
}
else if ((ret < 0) && (ret != AVERROR(EAGAIN)))
{
return false;
}
else if (ret == AVERROR(EAGAIN))
{
ret = avcodec_send_frame(av_codec_context_, tmp_picture);
if (0 > ret)
{
return false;
}
}
} while (ret == 0);
// the do while is called 46 times, then i get the packet, but i want to get the packet at the first call
It would be very nice if you can help me.
Thanks guys.
I assume you just want to encode a single frame. You need to flush the encoder after you have sent your single uncompressed frame by sending NULL instead of a valid buffer.
int result = 0;
// encoder init
// send one uncompressed frame
result = avcodec_send_frame(av_codec_context_, tmp_picture);
if (result < 0) return false;
// send NULL to indicate flushing
result = avcodec_send_frame(av_codec_context_, NULL);
if (result < 0) return false;
while (result != AVERROR_EOF)
{
result = avcodec_receive_packet(av_codec_context_, &pkt);
if (!result)
{
// you should have your encoded frame; do something with it
}
}
I want to apply processing to a video clip with sound track, extract and process frame by frame and write result to output file. Number of frames, size of frame and speed remains unchanged in output clip. Also I want to keep the same audio track as I have in source.
I can read clip, decode frames and process then using opencv. Audio packets are also writes fine. I'm stuck on forming output video stream.
The minimal runnable code I have for now (sorry it not so short, but cant do it shorter):
extern "C" {
#include <libavutil/timestamp.h>
#include <libavformat/avformat.h>
#include "libavcodec/avcodec.h"
#include <libavutil/opt.h>
#include <libavdevice/avdevice.h>
#include <libswscale/swscale.h>
}
#include "opencv2/opencv.hpp"
#if LIBAVCODEC_VERSION_INT < AV_VERSION_INT(55,28,1)
#define av_frame_alloc avcodec_alloc_frame
#endif
using namespace std;
using namespace cv;
static void log_packet(const AVFormatContext *fmt_ctx, const AVPacket *pkt, const char *tag)
{
AVRational *time_base = &fmt_ctx->streams[pkt->stream_index]->time_base;
char buf1[AV_TS_MAX_STRING_SIZE] = { 0 };
av_ts_make_string(buf1, pkt->pts);
char buf2[AV_TS_MAX_STRING_SIZE] = { 0 };
av_ts_make_string(buf1, pkt->dts);
char buf3[AV_TS_MAX_STRING_SIZE] = { 0 };
av_ts_make_string(buf1, pkt->duration);
char buf4[AV_TS_MAX_STRING_SIZE] = { 0 };
av_ts_make_time_string(buf1, pkt->pts, time_base);
char buf5[AV_TS_MAX_STRING_SIZE] = { 0 };
av_ts_make_time_string(buf1, pkt->dts, time_base);
char buf6[AV_TS_MAX_STRING_SIZE] = { 0 };
av_ts_make_time_string(buf1, pkt->duration, time_base);
printf("pts:%s pts_time:%s dts:%s dts_time:%s duration:%s duration_time:%s stream_index:%d\n",
buf1, buf4,
buf2, buf5,
buf3, buf6,
pkt->stream_index);
}
int main(int argc, char **argv)
{
AVOutputFormat *ofmt = NULL;
AVFormatContext *ifmt_ctx = NULL, *ofmt_ctx = NULL;
AVPacket pkt;
AVFrame *pFrame = NULL;
AVFrame *pFrameRGB = NULL;
int frameFinished = 0;
pFrame = av_frame_alloc();
pFrameRGB = av_frame_alloc();
const char *in_filename, *out_filename;
int ret, i;
in_filename = "../../TestClips/Audio Video Sync Test.mp4";
out_filename = "out.mp4";
// Initialize FFMPEG
av_register_all();
// Get input file format context
if ((ret = avformat_open_input(&ifmt_ctx, in_filename, 0, 0)) < 0)
{
fprintf(stderr, "Could not open input file '%s'", in_filename);
goto end;
}
// Extract streams description
if ((ret = avformat_find_stream_info(ifmt_ctx, 0)) < 0)
{
fprintf(stderr, "Failed to retrieve input stream information");
goto end;
}
// Print detailed information about the input or output format,
// such as duration, bitrate, streams, container, programs, metadata, side data, codec and time base.
av_dump_format(ifmt_ctx, 0, in_filename, 0);
// Allocate an AVFormatContext for an output format.
avformat_alloc_output_context2(&ofmt_ctx, NULL, NULL, out_filename);
if (!ofmt_ctx)
{
fprintf(stderr, "Could not create output context\n");
ret = AVERROR_UNKNOWN;
goto end;
}
// The output container format.
ofmt = ofmt_ctx->oformat;
// Allocating output streams
for (i = 0; i < ifmt_ctx->nb_streams; i++)
{
AVStream *in_stream = ifmt_ctx->streams[i];
AVStream *out_stream = avformat_new_stream(ofmt_ctx, in_stream->codec->codec);
if (!out_stream)
{
fprintf(stderr, "Failed allocating output stream\n");
ret = AVERROR_UNKNOWN;
goto end;
}
ret = avcodec_copy_context(out_stream->codec, in_stream->codec);
if (ret < 0)
{
fprintf(stderr, "Failed to copy context from input to output stream codec context\n");
goto end;
}
out_stream->codec->codec_tag = 0;
if (ofmt_ctx->oformat->flags & AVFMT_GLOBALHEADER)
{
out_stream->codec->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;
}
}
// Show output format info
av_dump_format(ofmt_ctx, 0, out_filename, 1);
// Open output file
if (!(ofmt->flags & AVFMT_NOFILE))
{
ret = avio_open(&ofmt_ctx->pb, out_filename, AVIO_FLAG_WRITE);
if (ret < 0)
{
fprintf(stderr, "Could not open output file '%s'", out_filename);
goto end;
}
}
// Write output file header
ret = avformat_write_header(ofmt_ctx, NULL);
if (ret < 0)
{
fprintf(stderr, "Error occurred when opening output file\n");
goto end;
}
// Search for input video codec info
AVCodec *in_codec = nullptr;
AVCodecContext* avctx = nullptr;
int video_stream_index = -1;
for (int i = 0; i < ifmt_ctx->nb_streams; i++)
{
if (ifmt_ctx->streams[i]->codec->coder_type == AVMEDIA_TYPE_VIDEO)
{
video_stream_index = i;
avctx = ifmt_ctx->streams[i]->codec;
in_codec = avcodec_find_decoder(avctx->codec_id);
if (!in_codec)
{
fprintf(stderr, "in codec not found\n");
exit(1);
}
break;
}
}
// Search for output video codec info
AVCodec *out_codec = nullptr;
AVCodecContext* o_avctx = nullptr;
int o_video_stream_index = -1;
for (int i = 0; i < ofmt_ctx->nb_streams; i++)
{
if (ofmt_ctx->streams[i]->codec->coder_type == AVMEDIA_TYPE_VIDEO)
{
o_video_stream_index = i;
o_avctx = ofmt_ctx->streams[i]->codec;
out_codec = avcodec_find_encoder(o_avctx->codec_id);
if (!out_codec)
{
fprintf(stderr, "out codec not found\n");
exit(1);
}
break;
}
}
// openCV pixel format
AVPixelFormat pFormat = AV_PIX_FMT_RGB24;
// Data size
int numBytes = avpicture_get_size(pFormat, avctx->width, avctx->height);
// allocate buffer
uint8_t *buffer = (uint8_t *)av_malloc(numBytes * sizeof(uint8_t));
// fill frame structure
avpicture_fill((AVPicture *)pFrameRGB, buffer, pFormat, avctx->width, avctx->height);
// frame area
int y_size = avctx->width * avctx->height;
// Open input codec
avcodec_open2(avctx, in_codec, NULL);
// Main loop
while (1)
{
AVStream *in_stream, *out_stream;
ret = av_read_frame(ifmt_ctx, &pkt);
if (ret < 0)
{
break;
}
in_stream = ifmt_ctx->streams[pkt.stream_index];
out_stream = ofmt_ctx->streams[pkt.stream_index];
log_packet(ifmt_ctx, &pkt, "in");
// copy packet
pkt.pts = av_rescale_q_rnd(pkt.pts, in_stream->time_base, out_stream->time_base, AVRounding(AV_ROUND_NEAR_INF | AV_ROUND_PASS_MINMAX));
pkt.dts = av_rescale_q_rnd(pkt.dts, in_stream->time_base, out_stream->time_base, AVRounding(AV_ROUND_NEAR_INF | AV_ROUND_PASS_MINMAX));
pkt.duration = av_rescale_q(pkt.duration, in_stream->time_base, out_stream->time_base);
pkt.pos = -1;
log_packet(ofmt_ctx, &pkt, "out");
if (pkt.stream_index == video_stream_index)
{
avcodec_decode_video2(avctx, pFrame, &frameFinished, &pkt);
if (frameFinished)
{
struct SwsContext *img_convert_ctx;
img_convert_ctx = sws_getCachedContext(NULL,
avctx->width,
avctx->height,
avctx->pix_fmt,
avctx->width,
avctx->height,
AV_PIX_FMT_BGR24,
SWS_BICUBIC,
NULL,
NULL,
NULL);
sws_scale(img_convert_ctx,
((AVPicture*)pFrame)->data,
((AVPicture*)pFrame)->linesize,
0,
avctx->height,
((AVPicture *)pFrameRGB)->data,
((AVPicture *)pFrameRGB)->linesize);
sws_freeContext(img_convert_ctx);
// Do some image processing
cv::Mat img(pFrame->height, pFrame->width, CV_8UC3, pFrameRGB->data[0],false);
cv::GaussianBlur(img,img,Size(5,5),3);
cv::imshow("Display", img);
cv::waitKey(5);
// --------------------------------
// Transform back to initial format
// --------------------------------
img_convert_ctx = sws_getCachedContext(NULL,
avctx->width,
avctx->height,
AV_PIX_FMT_BGR24,
avctx->width,
avctx->height,
avctx->pix_fmt,
SWS_BICUBIC,
NULL,
NULL,
NULL);
sws_scale(img_convert_ctx,
((AVPicture*)pFrameRGB)->data,
((AVPicture*)pFrameRGB)->linesize,
0,
avctx->height,
((AVPicture *)pFrame)->data,
((AVPicture *)pFrame)->linesize);
// --------------------------------------------
// Something must be here
// --------------------------------------------
//
// Write fideo frame (How to write frame to output stream ?)
//
// --------------------------------------------
sws_freeContext(img_convert_ctx);
}
}
else // write sound frame
{
ret = av_interleaved_write_frame(ofmt_ctx, &pkt);
}
if (ret < 0)
{
fprintf(stderr, "Error muxing packet\n");
break;
}
// Decrease packet ref counter
av_packet_unref(&pkt);
}
av_write_trailer(ofmt_ctx);
end:
avformat_close_input(&ifmt_ctx);
// close output
if (ofmt_ctx && !(ofmt->flags & AVFMT_NOFILE))
{
avio_closep(&ofmt_ctx->pb);
}
avformat_free_context(ofmt_ctx);
if (ret < 0 && ret != AVERROR_EOF)
{
char buf_err[AV_ERROR_MAX_STRING_SIZE] = { 0 };
av_make_error_string(buf_err, AV_ERROR_MAX_STRING_SIZE, ret);
fprintf(stderr, "Error occurred: %s\n", buf_err);
return 1;
}
avcodec_close(avctx);
av_free(pFrame);
av_free(pFrameRGB);
return 0;
}
Your original code segfaults in my case. Initializing the output codec context seems to fix it. The code below works for me but I didn't test the OpenCV stuff as I don't have the lib installed.
Get the codec context:
// Search for output video codec info
AVCodec *out_codec = NULL;
AVCodecContext* o_avctx = NULL;
int o_video_stream_index = -1;
for (int i = 0; i < ofmt_ctx->nb_streams; i++)
{
if (ofmt_ctx->streams[i]->codec->coder_type == AVMEDIA_TYPE_VIDEO)
{
o_video_stream_index = i;
out_codec = avcodec_find_encoder(ofmt_ctx->streams[i]->codec->codec_id);
o_avctx = avcodec_alloc_context3(out_codec);
o_avctx->height = avctx->height;
o_avctx->width = avctx->width;
o_avctx->sample_aspect_ratio = avctx->sample_aspect_ratio;
if (out_codec->pix_fmts)
o_avctx->pix_fmt = out_codec->pix_fmts[0];
else
o_avctx->pix_fmt = avctx->pix_fmt;
o_avctx->time_base = avctx->time_base;
avcodec_open2(o_avctx, out_codec, NULL);
}
}
Encode and write:
// Main loop
while (1)
{
...
if (pkt.stream_index == video_stream_index)
{
avcodec_decode_video2(avctx, pFrame, &frameFinished, &pkt);
if (frameFinished)
{
...
// --------------------------------------------
// Something must be here
// --------------------------------------------
int got_packet = 0;
AVPacket enc_pkt = { 0 };
av_init_packet(&enc_pkt);
avcodec_encode_video2(o_avctx, &enc_pkt, pFrame, &got_packet);
av_interleaved_write_frame(ofmt_ctx, &enc_pkt);
....
}
}
you should assign processed frame's packets information to your Original packets then pass it to av_interleaved_write_frame
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;
}
I got distorted image when try to convert YUV420p to RGB24 using
sws_scale.
Code:
ret = avcodec_decode_video2(video_dec_ctx, frame, got_frame, &pkt);
if (ret < 0) {
fprintf(stderr, "Error decoding video frame\n");
return ret;
}
if (*got_frame)
{
printf("video_frame%s n:%d coded_n:%d pts:%s\n",
cached ? "(cached)" : "",
video_frame_count++, frame->coded_picture_number,
"#"/*av_ts2timestr(frame->pts, &video_dec_ctx->time_base)*/);
/* copy decoded frame to destination buffer:
* this is required since rawvideo expects non aligned data */
av_image_copy(video_dst_data, video_dst_linesize,
(const uint8_t **)(frame->data), frame->linesize,
video_dec_ctx->pix_fmt, video_dec_ctx->width, video_dec_ctx->height);
/* write to rawvideo file */
fwrite(video_dst_data[0], 1, video_dst_bufsize, video_dst_file);
AVPicture pic;
avpicture_alloc( &pic, AV_PIX_FMT_RGB24, frame->width, frame->height);
SwsContext *ctxt = sws_getContext(frame->width, frame->height, static_cast<AVPixelFormat>(frame->format),
frame->width, frame->height, AV_PIX_FMT_RGB24, SWS_BILINEAR, NULL, NULL, NULL);
if ( NULL == ctxt )
{
//Log("failed to get sws context");
}
if ( 0 < sws_scale(ctxt, frame->data, frame->linesize, 0, frame->height, pic.data, pic.linesize))
{
char szPic[256] = { 0 };
sprintf( szPic, "decoded/%d.bmp", video_frame_count );
FILE *pf = fopen(szPic,"w");
if ( NULL != pf )
{
BITMAPFILEHEADER bmpFileHeader = {0};
bmpFileHeader.bfReserved1 = 0;
bmpFileHeader.bfReserved2 = 0;
bmpFileHeader.bfType = 0x4D42;
bmpFileHeader.bfSize = sizeof(bmpFileHeader) + sizeof(BITMAPINFOHEADER) + pic.linesize[0] * frame->height;
bmpFileHeader.bfOffBits = sizeof(bmpFileHeader) + sizeof(BITMAPINFOHEADER);
BITMAPINFOHEADER bmiHeader = { 0 };
bmiHeader.biSize = sizeof(BITMAPINFOHEADER);
bmiHeader.biWidth = frame->width;
bmiHeader.biHeight = 0 - frame->height;
bmiHeader.biPlanes = 1;
bmiHeader.biBitCount = 24;
bmiHeader.biCompression = BI_RGB;
bmiHeader.biSizeImage = pic.linesize[0] * frame->height;
bmiHeader.biXPelsPerMeter = 0;
bmiHeader.biYPelsPerMeter = 0;
bmiHeader.biClrUsed = 0;
bmiHeader.biClrImportant = 0;
fwrite( &bmpFileHeader, 1, sizeof(bmpFileHeader), pf );
fwrite( &bmiHeader, 1, sizeof(bmiHeader), pf );
fwrite( pic.data[0], 1, pic.linesize[0] * frame->height, pf );
fclose( pf );
}
}
// pic.data[0] now contains the image data in RGB format (3 bytes)
// and pic.linesize[0] is the pitch of the data (ie. size of a row in memory, which can be larger than width*sizeof(pixel))
avpicture_free(&pic);
sws_freeContext(ctxt);
}
above only decode frame then convert this from to RGB24, then write a bitmap.
original video frame like this,
but converted image,
is there missing some code or some code is wrong?
thanks in advance.
fwrite( pic.data[0], 1, pic.linesize[0] * frame->height, pf );
For an image of e.g. 1280x720, linesize is typically larger, e.g. 1312, so you'll be writing more data than image size if you write linesize*height. You want to write (in a loop) width pixels offset by linesize bytes:
uint8_t *ptr = pic.data[0];
for (int y = 0; y < frame->height; y++) {
fwrite(ptr, 1, frame->width, pf);
ptr += pic.linesize[0];
}
And then it should work correctly.
maybe these codes can help you. these works good.
int got_frame = 0;
auto len = avcodec_decode_video2(m_avCodecContext
, m_avFrame
, &got_frame
, &avpkt);
if (len < 0)
{
return;
}
if (got_frame /*&& !silentMode*/)
{
//if (videoRenderer != nullptr)
{
if (frameSize == NULL)
{
return;
}
uint8_t *dst_data[4];
int dst_linesize[4];
int dst_w, dst_h;
int ret = 0;
if (1)// avcodec_alloc_frame()
{
auto stride = m_avFrame->linesize;
auto scan0 = m_avFrame->data;
SwsContext *scaleContext = sws_getContext(m_avCodecContext->width
, m_avCodecContext->height
, m_avCodecContext->pix_fmt
, m_avCodecContext->width
, m_avCodecContext->height
, PixelFormat::PIX_FMT_BGR24
, SWS_FAST_BILINEAR, NULL, NULL, NULL);
if (scaleContext == NULL)
{
//TODO: log error
return;
}
try
{
//*vb->signal = 1;
ret = avpicture_alloc(&m_dst_picture
, PixelFormat::PIX_FMT_BGR24
, m_avCodecContext->width
, m_avCodecContext->height);
// AVFrame *picture_RGB;
// uint8_t *bufferRGB;
// picture_RGB = avcodec_alloc_frame();
// bufferRGB = (uint8_t*)malloc(720*576*(24/8)/*avpicture_get_size(PIX_FMT_RGB24, 720, 576)*/);
// avpicture_fill((AVPicture *)picture_RGB, bufferRGB, PIX_FMT_RGB24, 720, 576);
if (ret < 0)
{
return;
}
int retScale = sws_scale(scaleContext
, scan0
, stride
, 0
, m_avCodecContext->height
, m_dst_picture.data //picture_RGB->data
, m_dst_picture.linesize //picture_RGB->linesize
);
if (1)
{
HWND hwnd = m_pParent->GetSafeHwnd();
SetFocus(hwnd);
CRect rc;
m_pParent->GetClientRect(rc);
CDC *cdc = m_pParent->GetDC();
char* bitmap = (char*)m_dst_picture.data[0];
// static unsigned int i = 0;
// bmp_save(bitmap, m_avCodecContext->width, m_avCodecContext->height, i++);
BITMAPINFO bmpinfo;
bmpinfo.bmiHeader.biSize = sizeof(BITMAPINFOHEADER);
bmpinfo.bmiHeader.biWidth = m_avCodecContext->width;
bmpinfo.bmiHeader.biHeight = -m_avCodecContext->height;
bmpinfo.bmiHeader.biPlanes = 1;
bmpinfo.bmiHeader.biBitCount = 24;
bmpinfo.bmiHeader.biCompression = BI_RGB;
bmpinfo.bmiHeader.biSizeImage =
m_avCodecContext->width * m_avCodecContext->height * (24 / 8);
bmpinfo.bmiHeader.biXPelsPerMeter = 100;
bmpinfo.bmiHeader.biYPelsPerMeter = 100;
bmpinfo.bmiHeader.biClrUsed = 0;
bmpinfo.bmiHeader.biClrImportant = 0;
HBITMAP hBitmap = CreateDIBitmap(cdc->GetSafeHdc(), &bmpinfo.bmiHeader, CBM_INIT, bitmap, &bmpinfo/*bi*/, DIB_RGB_COLORS);
DrawBitmap(cdc, hBitmap, m_pParent);
::DeleteObject(hBitmap);
::DeleteObject(cdc->GetSafeHdc());
}
avpicture_free(&m_dst_picture);
sws_freeContext(scaleContext);
}
catch (int e)
{
sws_freeContext(scaleContext);
}
}
}
}
void DrawBitmap(CDC *pDC, HBITMAP hbitmap,CWnd *wnd)
{
CBitmap *pBitmap = CBitmap::FromHandle(hbitmap);
BITMAP bm;
pBitmap -> GetBitmap(&bm);
CDC MemDC;
MemDC.CreateCompatibleDC(pDC);
HGDIOBJ gob= MemDC.SelectObject(pBitmap);
CRect rc;
wnd->GetClientRect(rc);
pDC->SetStretchBltMode( COLORONCOLOR);
pDC->StretchBlt(0, 0,rc.Width(),rc.Height() , &MemDC, 0, 0, bm.bmWidth, bm.bmHeight, SRCCOPY);
MemDC.SelectObject(gob);
DeleteObject(pBitmap);
DeleteObject(MemDC);
DeleteObject(&bm);
ReleaseDC(wnd->GetSafeHwnd(), MemDC);
}
void initDecoder()
{
m_avCodecContext = avcodec_alloc_context();
if (!m_avCodecContext)
{
//failed to allocate codec context
Cleanup();
return;
}
m_avCodecContext->flags = 0;
uint8_t startCode[] = { 0x00, 0x00, 0x01 };
//////////////////////////////////////////////////////////////////////////
//I thought for play live video you can comment these lines.
if (m_sProps != NULL)
{
// USES_CONVERSION;
// ::MessageBox(NULL, A2T(sprops), TEXT("sprops"), MB_OK);
unsigned spropCount;
SPropRecord* spropRecords = parseSPropParameterSets(m_sProps, spropCount);
try
{
for (unsigned i = 0; i < spropCount; ++i)
{
AddExtraData(startCode, sizeof(startCode));
AddExtraData(spropRecords[i].sPropBytes, spropRecords[i].sPropLength);
}
}
catch (void*)
{
//extradata exceeds size limit
delete[] spropRecords;
Cleanup();
return;
}
delete[] spropRecords;
m_avCodecContext->extradata = extraDataBuffer;
m_avCodecContext->extradata_size = extraDataSize;
}
AddExtraData(startCode, sizeof(startCode));
bInitEx = true;
av_register_all();
avcodec_register_all();
m_codecId = CODEC_ID_H264;
m_avCodec = avcodec_find_decoder(m_codecId);
if (m_avCodec == NULL)
{
return;
}
if (avcodec_open(m_avCodecContext, m_avCodec) < 0)
{
//failed to open codec
Cleanup();
return;
}
if (m_avCodecContext->codec_id == CODEC_ID_H264)
{
m_avCodecContext->flags2 |= CODEC_FLAG2_CHUNKS;
//avCodecContext->flags2 |= CODEC_FLAG2_SHOW_ALL;
}
m_avFrame = avcodec_alloc_frame();
if (!m_avFrame)
{
//failed to allocate frame
Cleanup();
return;
}
}