1
我想使用ffmpeg api顯示裁剪和縮放幀，並且我正在使用GTK + 3作爲GUI組件。從以下this tutorial和ffmpeg examples，我能夠顯示未過濾的幀，雖然有一些不穩定。過濾後的幀根本無法正確顯示。它主要產生完全黑色的輸出。我懷疑這是由於sws_scale（），但我還沒有發現爲什麼會發生這種情況。使用GTK顯示已過濾的ffmpeg幀
使用ffmpeg示例中的「平凡」顯示，我可以確認該幀正在被裁剪和正確縮放。
運行下面的代碼，我收到了一堆錯誤：
[swscaler @ 0x7fb58b025400] bad src image pointers
[swscaler @ 0x7fb58b025400] bad dst image pointers
我也收到此錯誤：
[swscaler @ 0x7fd05c025600] Warning: data is not aligned! This can lead to a speedloss
我試圖使一個緩衝，這是16位對齊的，但事實並非如此似乎對結果有任何影響。
這是我的解碼框架和應用過濾器：
void decode(gpointer args) {
int ret;
AVPacket packet;
AVFrame *frame = av_frame_alloc();
AVFrame *filt_frame = av_frame_alloc();
int got_frame;
if(!frame || !filt_frame) {
perror("Could not allocate frame");
exit(1);
}
/* read all packets */
while (1) {
if ((ret = av_read_frame(fmt_ctx, &packet)) < 0)
break;
if (packet.stream_index == video_stream_index) {
got_frame = 0;
ret = avcodec_decode_video2(dec_ctx, frame, &got_frame, &packet);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Error decoding video\n");
break;
}
if (got_frame) {
frame->pts = av_frame_get_best_effort_timestamp(frame);
/* 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_frame2(filt_frame, buffersink_ctx->inputs[0]->time_base);
av_frame_unref(filt_frame);
}
av_frame_unref(frame);
}
}
av_free_packet(&packet);
}
end:
avfilter_graph_free(&filter_graph);
avcodec_close(dec_ctx);
avformat_close_input(&fmt_ctx);
av_frame_free(&frame);
av_frame_free(&filt_frame);
if (ret < 0 && ret != AVERROR_EOF) {
fprintf(stderr, "Error occurred: %s\n", av_err2str(ret));
exit(1);
}
}
而且我這是怎麼顯示的幀。
void display_frame2(const AVFrame *frame, AVRational time_base) {
GdkPixbuf *pixbuf;
int64_t delay;
AVFrame *filt;
uint8_t *buffer;
int num_bytes, i;
buffer = NULL;
filt = av_frame_alloc();
num_bytes = avpicture_get_size(PIX_FMT_RGB24, dec_ctx->width, dec_ctx->height);
buffer = (uint8_t *)av_malloc(num_bytes * sizeof(uint8_t));
avpicture_fill((AVPicture *)filt, buffer, PIX_FMT_RGB24, dec_ctx->width, dec_ctx->height);
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)
usleep(delay);
}
last_pts = frame->pts;
}
sws_scale( sws_ctx,
(uint8_t const * const *)frame->data,
frame->linesize,
0,
frame->height,
filt->data,
filt->linesize);
pixbuf = gdk_pixbuf_new_from_data( filt->data[0], GDK_COLORSPACE_RGB,
0, 8, dec_ctx->width, dec_ctx->height,
filt->linesize[0], NULL, NULL);
gtk_image_set_from_pixbuf((GtkImage *)image, pixbuf);
free(filt);
free(buffer);
}
編輯： 經過一番更多的思考和實驗得到了我要顯示的過濾框架，儘管在SDL，不是GTK +。我使用ffmpeg的代碼轉換示例來了解是否可以使用過濾器對視頻進行重新編碼，而且確實有效。在這個例子中，我基本上改變了filtergtaph的過濾器，大部分工作已經完成。此時，我所做的只是使用SDL顯示視頻，如危險教程中所示。裁剪過濾器會創建很多工件，但至少會顯示某些內容。
我必須做一些更多的工作來看看它是否可以與GTK +一起工作。我沒有仔細研究上述程序和轉碼示例中的區別，所以我還沒有弄清楚爲什麼我的舊代碼不顯示過濾的幀。這兩組代碼都使用sws_scale（），但我沒有得到新代碼的錯誤，所以這必定意味着有些不同。一旦我取得更多進展，我會更新這篇文章。
編輯2： 根據@ drahnr的請求添加了一個可編譯的小例子，它應該可以工作。我沒有機會嘗試替換GtkPixbuf。
#define _XOPEN_SOURCE 600
#include <libavformat/avformat.h>
#include <libavformat/avio.h>
#include <libavfilter/avfiltergraph.h>
#include <libavfilter/avcodec.h>
#include <libavfilter/buffersink.h>
#include <libavfilter/buffersrc.h>
#include <libavcodec/avcodec.h>
#include <libswscale/swscale.h>
#include <libavutil/avstring.h>
#include <libavutil/time.h>
#include <libavutil/opt.h>
#include <unistd.h>
#include <gtk/gtk.h>
#include <gdk/gdkx.h>
GtkWidget *image;
GtkWidget *window;
struct SwsContext *sws_ctx;
char *filter_descr = "crop=100:100,scale=640:360";
static AVFormatContext *fmt_ctx;
static AVCodecContext *dec_ctx;
AVFilterContext *buffersink_ctx;
AVFilterContext *buffersrc_ctx;
AVFilterGraph *filter_graph;
static int video_stream_index = -1;
static void open_input_file(const char *filename)
{
AVCodec *dec;
avformat_open_input(&fmt_ctx, filename, NULL, NULL);
avformat_find_stream_info(fmt_ctx, NULL);
video_stream_index = av_find_best_stream(fmt_ctx, AVMEDIA_TYPE_VIDEO, -1, -1, &dec, 0);
dec_ctx = fmt_ctx->streams[video_stream_index]->codec;
av_opt_set_int(dec_ctx, "refcounted_frames", 1, 0);
avcodec_open2(dec_ctx, dec, NULL);
}
static void init_filters(const char *filters_descr)
{
char args[512];
AVFilter *buffersrc = avfilter_get_by_name("buffer");
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;
enum AVPixelFormat pix_fmts[] = { PIX_FMT_RGB24, AV_PIX_FMT_NONE };
filter_graph = avfilter_graph_alloc();
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);
avfilter_graph_create_filter(&buffersrc_ctx, buffersrc, "in", args, NULL, filter_graph);
avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out", NULL, NULL, filter_graph);
av_opt_set_int_list(buffersink_ctx, "pix_fmts", pix_fmts, AV_PIX_FMT_NONE, AV_OPT_SEARCH_CHILDREN);
outputs->name = av_strdup("in");
outputs->filter_ctx = buffersrc_ctx;
outputs->pad_idx = 0;
outputs->next = NULL;
inputs->name = av_strdup("out");
inputs->filter_ctx = buffersink_ctx;
inputs->pad_idx = 0;
inputs->next = NULL;
avfilter_graph_parse_ptr(filter_graph, filters_descr, &inputs, &outputs, NULL);
avfilter_graph_config(filter_graph, NULL);
}
static void display_frame2(const AVFrame *frame, AVRational time_base) {
GdkPixbuf *pixbuf;
AVFrame *filt;
uint8_t *buffer;
int num_bytes;
buffer = NULL;
filt = av_frame_alloc();
num_bytes = avpicture_get_size(PIX_FMT_RGB24, dec_ctx->width, dec_ctx->height);
buffer = (uint8_t *)av_malloc(num_bytes * sizeof(uint8_t));
avpicture_fill((AVPicture *)filt, buffer, PIX_FMT_RGB24, dec_ctx->width, dec_ctx->height);
usleep(33670/4);
sws_scale( sws_ctx,
(uint8_t const * const *)frame->data,
frame->linesize,
0,
frame->height,
filt->data,
filt->linesize);
pixbuf = gdk_pixbuf_new_from_data( filt->data[0], GDK_COLORSPACE_RGB,
0, 8, dec_ctx->width, dec_ctx->height,
filt->linesize[0], NULL, NULL);
gtk_image_set_from_pixbuf((GtkImage *)image, pixbuf);
free(filt);
free(buffer);
}
void decode(gpointer args) {
int ret;
AVPacket packet;
AVFrame *frame = av_frame_alloc();
AVFrame *filt_frame = av_frame_alloc();
int got_frame;
while (1) {
av_read_frame(fmt_ctx, &packet);
if (packet.stream_index == video_stream_index) {
got_frame = 0;
avcodec_decode_video2(dec_ctx, frame, &got_frame, &packet);
if (got_frame) {
frame->pts = av_frame_get_best_effort_timestamp(frame);
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;
}
while (1) {
ret = av_buffersink_get_frame(buffersink_ctx, filt_frame);
if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
break;
// Display original frame
display_frame2(frame, buffersink_ctx->inputs[0]->time_base);
// Display filtered frame
// display_frame2(filt_frame, buffersink_ctx->inputs[0]->time_base);
av_frame_unref(filt_frame);
}
av_frame_unref(frame);
}
}
av_free_packet(&packet);
}
}
static void realize_cb(GtkWidget *widget, gpointer data) {
GThread *tid;
tid = g_thread_new("video", decode, NULL);
}
static void destroy(GtkWidget *widget, gpointer data) {
gtk_main_quit();
}
int main(int argc, char **argv)
{
av_register_all();
avfilter_register_all();
open_input_file(argv[1]);
init_filters(filter_descr);
sws_ctx = NULL;
sws_ctx = sws_getContext( dec_ctx->width, dec_ctx->height, dec_ctx->pix_fmt, dec_ctx->width, dec_ctx->height,
PIX_FMT_RGB24, SWS_BILINEAR, NULL, NULL, NULL);
av_dump_format(fmt_ctx, 0, argv[1], 0);
gtk_init(&argc, &argv);
window = gtk_window_new(GTK_WINDOW_TOPLEVEL);
g_signal_connect(window, "realize", G_CALLBACK(realize_cb), NULL);
g_signal_connect(window, "destroy", G_CALLBACK(destroy), NULL);
gtk_container_set_border_width(GTK_CONTAINER(window), 10);
image = gtk_image_new();
gtk_widget_show(image);
gtk_container_add(GTK_CONTAINER(window), image);
gtk_widget_show(window);
gtk_main();
return 0;
}
你究竟在哪裏指定緩衝區？你爲什麼要把它調整到16bits？我期望16 **字節**對齊SSE的樂趣。 – drahnr
@drahnr在'displayFrame2（）'緩衝區是我聲明的第四個變量。我用這個緩衝區=（uint8_t *）av_malloc（num_bytes * sizeof（uint8_t））;'它正在使用像這樣''avpicture_fill（（AVPicture *）filt，buffer，PIX_FMT_RGB24，dec_ctx->寬，dec_ctx-> height）;'This [post]（http://forum.doom9.org/archive/index.php/t-167010.html）表示緩衝區需要16位對齊。使緩衝區成爲16的倍數似乎沒有什麼區別。 – Fjotten
今晚我會看看它，但沒有承諾。 – drahnr