gpt4 book ai didi

c - 缓冲区源是否将像素格式更改为 `pix_fmt` 还是仅读取输入,就好像它是该格式一样?

转载 作者:行者123 更新时间:2023-12-04 22:56:49 25 4
gpt4 key购买 nike

我在学习libav和相关的事情。
我遇到了this ffmpeg 文档中的示例:

     /* buffer video source: the decoded frames from the decoder will be inserted here. */
snprintf(args, sizeof(args),
"video_size=%dx%d:pix_fmt=%d:time_base=%d/%d:pixel_aspect=%d/%d",
dec_ctx->width, dec_ctx->height, dec_ctx->pix_fmt,
time_base.num, time_base.den,
dec_ctx->sample_aspect_ratio.num, dec_ctx->sample_aspect_ratio.den);

ret = avfilter_graph_create_filter(&buffersrc_ctx, buffersrc, "in",
args, NULL, filter_graph);
如果我指定 pix_fmt除了 dec_ctx->pix_fmt (例如 rgb24 ),此缓冲区源是否会将像素格式转换为 rgb24 , 还是会像在 rgb24 中一样读取源代码?格式,从而导致错误解码?
如果我设置不同的 video_size 会发生什么? ?

最佳答案

指定 pix_fmt到 rgb24,将像素格式转换为 rgb24。

在没有太多关于过滤图的知识的情况下,我们可以执行代码并检查输出。
为了显示输出帧,我将“Trivial ASCII grayscale display”替换为 OpenCV方法cv::imshow .
建立一个同时使用 Libav 和 OpenCV 的项目需要一些初步的努力......
这是带有原始代码的输出帧(输出为灰度):
enter image description here
这是带有 AV_PIX_FMT_BGR24 的输出帧像素格式(输出为 BGR):
enter image description here
注意:使用 BGR(而不是 RGB),因为 OpenCV 的颜色排序约定是 BGR。

使用 BGR 格式时,会出现警告消息:

Changing video frame properties on the fly is not supported by all filters.


设置 pix_fmt 可能不是最佳实践。以这种方式...

完整代码:
//https://github.com/FFmpeg/FFmpeg/blob/master/doc/examples/filtering_video.c

/*
* Copyright (c) 2010 Nicolas George
* Copyright (c) 2011 Stefano Sabatini
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/

/**
* @file
* API example for decoding and filtering
* @example filtering_video.c
*/

#define _XOPEN_SOURCE 600 /* for usleep */
#ifdef __GNUC__
#include <unistd.h>
#else
//Windows - use C++11 for usleep
#include <chrono>
#include <thread>
#endif

#include <stdio.h>
#include <stdlib.h>

#include <opencv2/opencv.hpp>
#include <opencv2/highgui.hpp>

extern "C" {
#include <libavcodec/avcodec.h>
#include <libavformat/avformat.h>
#include <libavfilter/buffersink.h>
#include <libavfilter/buffersrc.h>
#include <libavutil/opt.h>
}


#define DO_TEST_PIX_FMT_BGR24 //If defined, test pixel format BGR24


const char* filter_descr = "scale=78:24,transpose=cclock";
/* other way:
scale=78:24 [scl]; [scl] transpose=cclock // assumes "[in]" and "[out]" to be input output pads respectively
*/

static AVFormatContext* fmt_ctx;
static AVCodecContext* dec_ctx;
AVFilterContext* buffersink_ctx;
AVFilterContext* buffersrc_ctx;
AVFilterGraph* filter_graph;
static int video_stream_index = -1;
static int64_t last_pts = AV_NOPTS_VALUE;

static int open_input_file(const char* filename)
{
AVCodec* dec;
int ret;

if ((ret = avformat_open_input(&fmt_ctx, filename, NULL, NULL)) < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot open input file\n");
return ret;
}

if ((ret = avformat_find_stream_info(fmt_ctx, NULL)) < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot find stream information\n");
return ret;
}

/* select the video stream */
ret = av_find_best_stream(fmt_ctx, AVMEDIA_TYPE_VIDEO, -1, -1, &dec, 0);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot find a video stream in the input file\n");
return ret;
}
video_stream_index = ret;

/* create decoding context */
dec_ctx = avcodec_alloc_context3(dec);
if (!dec_ctx)
return AVERROR(ENOMEM);
avcodec_parameters_to_context(dec_ctx, fmt_ctx->streams[video_stream_index]->codecpar);

/* init the video decoder */
if ((ret = avcodec_open2(dec_ctx, dec, NULL)) < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot open video decoder\n");
return ret;
}

return 0;
}

static int init_filters(const char* filters_descr)
{
char args[512];
int ret = 0;
const AVFilter* buffersrc = avfilter_get_by_name("buffer");
const AVFilter* buffersink = avfilter_get_by_name("buffersink");
AVFilterInOut* outputs = avfilter_inout_alloc();
AVFilterInOut* inputs = avfilter_inout_alloc();
AVRational time_base = fmt_ctx->streams[video_stream_index]->time_base;

#ifdef DO_TEST_PIX_FMT_BGR24
enum AVPixelFormat pix_fmts[] = { AV_PIX_FMT_BGR24, AV_PIX_FMT_NONE }; //Replace AV_PIX_FMT_GRAY8 with AV_PIX_FMT_BGR24
#else
enum AVPixelFormat pix_fmts[] = { AV_PIX_FMT_GRAY8, AV_PIX_FMT_NONE };
#endif


filter_graph = avfilter_graph_alloc();
if (!outputs || !inputs || !filter_graph) {
ret = AVERROR(ENOMEM);
goto end;
}

/* buffer video source: the decoded frames from the decoder will be inserted here. */
#ifdef DO_TEST_PIX_FMT_BGR24
snprintf(args, sizeof(args),
"video_size=%dx%d:pix_fmt=%d:time_base=%d/%d:pixel_aspect=%d/%d",
dec_ctx->width, dec_ctx->height, (int)AV_PIX_FMT_BGR24 /*dec_ctx->pix_fmt*/, //Replace dec_ctx->pix_fmt with AV_PIX_FMT_BGR24
time_base.num, time_base.den,
dec_ctx->sample_aspect_ratio.num, dec_ctx->sample_aspect_ratio.den);
#else
snprintf(args, sizeof(args),
"video_size=%dx%d:pix_fmt=%d:time_base=%d/%d:pixel_aspect=%d/%d",
dec_ctx->width, dec_ctx->height, dec_ctx->pix_fmt,
time_base.num, time_base.den,
dec_ctx->sample_aspect_ratio.num, dec_ctx->sample_aspect_ratio.den);
#endif

ret = avfilter_graph_create_filter(&buffersrc_ctx, buffersrc, "in",
args, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create buffer source\n");
goto end;
}

/* buffer video sink: to terminate the filter chain. */
ret = avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out",
NULL, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create buffer sink\n");
goto end;
}

ret = av_opt_set_int_list(buffersink_ctx, "pix_fmts", pix_fmts,
AV_PIX_FMT_NONE, AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output pixel format\n");
goto end;
}

/*
* Set the endpoints for the filter graph. The filter_graph will
* be linked to the graph described by filters_descr.
*/

/*
* The buffer source output must be connected to the input pad of
* the first filter described by filters_descr; since the first
* filter input label is not specified, it is set to "in" by
* default.
*/
outputs->name = av_strdup("in");
outputs->filter_ctx = buffersrc_ctx;
outputs->pad_idx = 0;
outputs->next = NULL;

/*
* The buffer sink input must be connected to the output pad of
* the last filter described by filters_descr; since the last
* filter output label is not specified, it is set to "out" by
* default.
*/
inputs->name = av_strdup("out");
inputs->filter_ctx = buffersink_ctx;
inputs->pad_idx = 0;
inputs->next = NULL;

if ((ret = avfilter_graph_parse_ptr(filter_graph, filters_descr,
&inputs, &outputs, NULL)) < 0)
goto end;

if ((ret = avfilter_graph_config(filter_graph, NULL)) < 0)
goto end;

end:
avfilter_inout_free(&inputs);
avfilter_inout_free(&outputs);

return ret;
}

static void display_frame(const AVFrame* frame, AVRational time_base)
{
//int x, y;
//uint8_t* p0, * p;
int64_t delay;

const AVRational av_time_base_q = {1, AV_TIME_BASE};

if (frame->pts != AV_NOPTS_VALUE) {
if (last_pts != AV_NOPTS_VALUE) {
/* sleep roughly the right amount of time;
* usleep is in microseconds, just like AV_TIME_BASE. */
delay = av_rescale_q(frame->pts - last_pts,
time_base, av_time_base_q);
if (delay > 0 && delay < 1000000)
#ifdef __GNUC__
usleep(delay);
#else
//Windows
//https://stackoverflow.com/questions/4184468/sleep-for-milliseconds
std::this_thread::sleep_for(std::chrono::microseconds(delay));
#endif
}
last_pts = frame->pts;
}

/* Trivial ASCII grayscale display. */
//p0 = frame->data[0];
//puts("\033c");
//for (y = 0; y < frame->height; y++) {
// p = p0;
// for (x = 0; x < frame->width; x++)
// putchar(" .-+#"[*(p++) / 52]);
// putchar('\n');
// p0 += frame->linesize[0];
//}
//fflush(stdout);

//Use OpenCV for display
#ifdef DO_TEST_PIX_FMT_BGR24
cv::Mat img = cv::Mat(frame->height, frame->width, CV_8UC3, frame->data[0], frame->linesize[0]); //3 Color channels (BGR)
#else
cv::Mat img = cv::Mat(frame->height, frame->width, CV_8UC1, frame->data[0], frame->linesize[0]); //1 Color channels (Grayscale)
#endif
cv::imshow("img", img);
cv::waitKey(1);
}

int main(int argc, char** argv)
{
int ret;
AVPacket* packet;
AVFrame* frame;
AVFrame* filt_frame;

if (argc != 2) {
fprintf(stderr, "Usage: %s file\n", argv[0]);
exit(1);
}

frame = av_frame_alloc();
filt_frame = av_frame_alloc();
packet = av_packet_alloc();
if (!frame || !filt_frame || !packet) {
fprintf(stderr, "Could not allocate frame or packet\n");
exit(1);
}

if ((ret = open_input_file(argv[1])) < 0)
goto end;
if ((ret = init_filters(filter_descr)) < 0)
goto end;

/* read all packets */
while (1) {
if ((ret = av_read_frame(fmt_ctx, packet)) < 0)
break;

if (packet->stream_index == video_stream_index) {
ret = avcodec_send_packet(dec_ctx, packet);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Error while sending a packet to the decoder\n");
break;
}

while (ret >= 0) {
ret = avcodec_receive_frame(dec_ctx, frame);
if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF) {
break;
}
else if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Error while receiving a frame from the decoder\n");
goto end;
}

frame->pts = frame->best_effort_timestamp;

/* push the decoded frame into the filtergraph */
if (av_buffersrc_add_frame_flags(buffersrc_ctx, frame, AV_BUFFERSRC_FLAG_KEEP_REF) < 0) {
av_log(NULL, AV_LOG_ERROR, "Error while feeding the filtergraph\n");
break;
}

/* pull filtered frames from the filtergraph */
while (1) {
ret = av_buffersink_get_frame(buffersink_ctx, filt_frame);
if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
break;
if (ret < 0)
goto end;
display_frame(filt_frame, buffersink_ctx->inputs[0]->time_base);
av_frame_unref(filt_frame);
}
av_frame_unref(frame);
}
}
av_packet_unref(packet);
}
end:
avfilter_graph_free(&filter_graph);
avcodec_free_context(&dec_ctx);
avformat_close_input(&fmt_ctx);
av_frame_free(&frame);
av_frame_free(&filt_frame);
av_packet_free(&packet);

if (ret < 0 && ret != AVERROR_EOF) {
//fprintf(stderr, "Error occurred: %s\n", av_err2str(ret));
char errbuf[AV_ERROR_MAX_STRING_SIZE];
av_make_error_string(errbuf, AV_ERROR_MAX_STRING_SIZE, ret);
fprintf(stderr, "Error occurred: %s\n", errbuf);
exit(1);
}

cv::destroyAllWindows();

exit(0);
}

关于c - 缓冲区源是否将像素格式更改为 `pix_fmt` 还是仅读取输入,就好像它是该格式一样?,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/71300824/

25 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com