FFmpeg
vf_xmedian.c
Go to the documentation of this file.
1 /*
2  * Copyright (c) 2019 Paul B Mahol
3  *
4  * This file is part of FFmpeg.
5  *
6  * FFmpeg is free software; you can redistribute it and/or
7  * modify it under the terms of the GNU Lesser General Public
8  * License as published by the Free Software Foundation; either
9  * version 2.1 of the License, or (at your option) any later version.
10  *
11  * FFmpeg is distributed in the hope that it will be useful,
12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14  * Lesser General Public License for more details.
15  *
16  * You should have received a copy of the GNU Lesser General Public
17  * License along with FFmpeg; if not, write to the Free Software
18  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
19  */
20 
21 #include "libavutil/avstring.h"
22 #include "libavutil/imgutils.h"
23 #include "libavutil/intreadwrite.h"
24 #include "libavutil/opt.h"
25 #include "libavutil/pixdesc.h"
26 #include "libavutil/qsort.h"
27 
28 #include "avfilter.h"
29 #include "formats.h"
30 #include "internal.h"
31 #include "framesync.h"
32 #include "video.h"
33 
34 typedef struct XMedianContext {
35  const AVClass *class;
37  int nb_inputs;
38  int planes;
39 
40  int radius;
41  int depth;
42  int max;
43  int nb_planes;
44  int linesize[4];
45  int width[4];
46  int height[4];
47 
50 
51  int (*median_frames)(AVFilterContext *ctx, void *arg, int jobnr, int nb_jobs);
53 
55 {
56  static const enum AVPixelFormat pixel_fmts[] = {
79  };
81  if (!formats)
82  return AVERROR(ENOMEM);
84 }
85 
87 {
88  XMedianContext *s = ctx->priv;
89  int ret;
90 
91  s->radius = s->nb_inputs / 2;
92  s->frames = av_calloc(s->nb_inputs, sizeof(*s->frames));
93  if (!s->frames)
94  return AVERROR(ENOMEM);
95 
96  for (int i = 0; i < s->nb_inputs; i++) {
97  AVFilterPad pad = { 0 };
98 
100  pad.name = av_asprintf("input%d", i);
101  if (!pad.name)
102  return AVERROR(ENOMEM);
103 
104  if ((ret = ff_insert_inpad(ctx, i, &pad)) < 0) {
105  av_freep(&pad.name);
106  return ret;
107  }
108  }
109 
110  return 0;
111 }
112 
113 typedef struct ThreadData {
114  AVFrame **in, *out;
115 } ThreadData;
116 
117 static int comparei(const void *p1, const void *p2)
118 {
119  int left = *(const int *)p1;
120  int right = *(const int *)p2;
121  return FFDIFFSIGN(left, right);
122 }
123 
124 static int median_frames16(AVFilterContext *ctx, void *arg, int jobnr, int nb_jobs)
125 {
126  XMedianContext *s = ctx->priv;
127  ThreadData *td = arg;
128  AVFrame **in = td->in;
129  AVFrame *out = td->out;
130  const int nb_inputs = s->nb_inputs;
131  const int radius = s->radius;
132  int values[256];
133 
134  for (int p = 0; p < s->nb_planes; p++) {
135  const int slice_start = (s->height[p] * jobnr) / nb_jobs;
136  const int slice_end = (s->height[p] * (jobnr+1)) / nb_jobs;
137  uint16_t *dst = (uint16_t *)(out->data[p] + slice_start * out->linesize[p]);
138 
139  if (!((1 << p) & s->planes)) {
140  av_image_copy_plane((uint8_t *)dst, out->linesize[p],
141  in[0]->data[p] + slice_start * in[radius]->linesize[p],
142  in[0]->linesize[p],
143  s->linesize[p], slice_end - slice_start);
144  continue;
145  }
146 
147  for (int y = slice_start; y < slice_end; y++) {
148  for (int x = 0; x < s->width[p]; x++) {
149  for (int i = 0; i < nb_inputs; i++) {
150  const uint16_t *src = (const uint16_t *)(in[i]->data[p] + y * in[i]->linesize[p]);
151  values[i] = src[x];
152  }
153 
154  AV_QSORT(values, nb_inputs, int, comparei);
155  if (radius & 1)
156  dst[x] = values[radius];
157  else
158  dst[x] = (values[radius] + values[radius - 1]) >> 1;
159  }
160 
161  dst += out->linesize[p] / 2;
162  }
163  }
164 
165  return 0;
166 }
167 
168 static int median_frames8(AVFilterContext *ctx, void *arg, int jobnr, int nb_jobs)
169 {
170  XMedianContext *s = ctx->priv;
171  ThreadData *td = arg;
172  AVFrame **in = td->in;
173  AVFrame *out = td->out;
174  const int nb_inputs = s->nb_inputs;
175  const int radius = s->radius;
176  int values[256];
177 
178  for (int p = 0; p < s->nb_planes; p++) {
179  const int slice_start = (s->height[p] * jobnr) / nb_jobs;
180  const int slice_end = (s->height[p] * (jobnr+1)) / nb_jobs;
181  uint8_t *dst = out->data[p] + slice_start * out->linesize[p];
182 
183  if (!((1 << p) & s->planes)) {
184  av_image_copy_plane(dst, out->linesize[p],
185  in[0]->data[p] + slice_start * in[0]->linesize[p],
186  in[0]->linesize[p],
187  s->linesize[p], slice_end - slice_start);
188  continue;
189  }
190 
191  for (int y = slice_start; y < slice_end; y++) {
192  for (int x = 0; x < s->width[p]; x++) {
193  for (int i = 0; i < nb_inputs; i++)
194  values[i] = in[i]->data[p][y * in[i]->linesize[p] + x];
195 
196  AV_QSORT(values, nb_inputs, int, comparei);
197  if (radius & 1)
198  dst[x] = values[radius];
199  else
200  dst[x] = (values[radius] + values[radius - 1]) >> 1;
201  }
202 
203  dst += out->linesize[p];
204  }
205  }
206 
207  return 0;
208 }
209 
211 {
212  AVFilterContext *ctx = fs->parent;
213  AVFilterLink *outlink = ctx->outputs[0];
214  XMedianContext *s = fs->opaque;
215  AVFrame **in = s->frames;
216  AVFrame *out;
217  ThreadData td;
218  int i, ret;
219 
220  for (i = 0; i < s->nb_inputs; i++) {
221  if ((ret = ff_framesync_get_frame(&s->fs, i, &in[i], 0)) < 0)
222  return ret;
223  }
224 
225  out = ff_get_video_buffer(outlink, outlink->w, outlink->h);
226  if (!out)
227  return AVERROR(ENOMEM);
228  out->pts = av_rescale_q(s->fs.pts, s->fs.time_base, outlink->time_base);
229 
230  td.in = in;
231  td.out = out;
232  ctx->internal->execute(ctx, s->median_frames, &td, NULL, FFMIN(s->height[1], ff_filter_get_nb_threads(ctx)));
233 
234  return ff_filter_frame(outlink, out);
235 }
236 
237 static int config_output(AVFilterLink *outlink)
238 {
239  AVFilterContext *ctx = outlink->src;
240  XMedianContext *s = ctx->priv;
241  AVRational frame_rate = ctx->inputs[0]->frame_rate;
242  AVRational sar = ctx->inputs[0]->sample_aspect_ratio;
243  AVFilterLink *inlink = ctx->inputs[0];
244  int height = ctx->inputs[0]->h;
245  int width = ctx->inputs[0]->w;
246  FFFrameSyncIn *in;
247  int i, ret;
248 
249  for (int i = 1; i < s->nb_inputs; i++) {
250  if (ctx->inputs[i]->h != height || ctx->inputs[i]->w != width) {
251  av_log(ctx, AV_LOG_ERROR, "Input %d size (%dx%d) does not match input %d size (%dx%d).\n", i, ctx->inputs[i]->w, ctx->inputs[i]->h, 0, width, height);
252  return AVERROR(EINVAL);
253  }
254  }
255 
256  s->desc = av_pix_fmt_desc_get(outlink->format);
257  if (!s->desc)
258  return AVERROR_BUG;
259  s->nb_planes = av_pix_fmt_count_planes(outlink->format);
260  s->depth = s->desc->comp[0].depth;
261  s->max = (1 << s->depth) - 1;
262 
263  if (s->depth <= 8)
264  s->median_frames = median_frames8;
265  else
266  s->median_frames = median_frames16;
267 
268  if ((ret = av_image_fill_linesizes(s->linesize, inlink->format, inlink->w)) < 0)
269  return ret;
270 
271  s->width[1] = s->width[2] = AV_CEIL_RSHIFT(inlink->w, s->desc->log2_chroma_w);
272  s->width[0] = s->width[3] = inlink->w;
273  s->height[1] = s->height[2] = AV_CEIL_RSHIFT(inlink->h, s->desc->log2_chroma_h);
274  s->height[0] = s->height[3] = inlink->h;
275 
276  outlink->w = width;
277  outlink->h = height;
278  outlink->frame_rate = frame_rate;
279  outlink->sample_aspect_ratio = sar;
280 
281  if ((ret = ff_framesync_init(&s->fs, ctx, s->nb_inputs)) < 0)
282  return ret;
283 
284  in = s->fs.in;
285  s->fs.opaque = s;
286  s->fs.on_event = process_frame;
287 
288  for (i = 0; i < s->nb_inputs; i++) {
289  AVFilterLink *inlink = ctx->inputs[i];
290 
291  in[i].time_base = inlink->time_base;
292  in[i].sync = 1;
293  in[i].before = EXT_STOP;
294  in[i].after = EXT_STOP;
295  }
296 
297  ret = ff_framesync_configure(&s->fs);
298  outlink->time_base = s->fs.time_base;
299 
300  return ret;
301 }
302 
304 {
305  XMedianContext *s = ctx->priv;
306 
307  ff_framesync_uninit(&s->fs);
308  av_freep(&s->frames);
309 
310  for (int i = 0; i < ctx->nb_inputs; i++)
311  av_freep(&ctx->input_pads[i].name);
312 }
313 
315 {
316  XMedianContext *s = ctx->priv;
317  return ff_framesync_activate(&s->fs);
318 }
319 
320 #define OFFSET(x) offsetof(XMedianContext, x)
321 #define FLAGS AV_OPT_FLAG_VIDEO_PARAM | AV_OPT_FLAG_FILTERING_PARAM
322 
323 static const AVOption xmedian_options[] = {
324  { "inputs", "set number of inputs", OFFSET(nb_inputs), AV_OPT_TYPE_INT, {.i64=3}, 3, 255, .flags = FLAGS },
325  { "planes", "set planes to filter", OFFSET(planes), AV_OPT_TYPE_INT, {.i64=15}, 0, 15, .flags = FLAGS },
326  { NULL },
327 };
328 
329 static const AVFilterPad outputs[] = {
330  {
331  .name = "default",
332  .type = AVMEDIA_TYPE_VIDEO,
333  .config_props = config_output,
334  },
335  { NULL }
336 };
337 
338 AVFILTER_DEFINE_CLASS(xmedian);
339 
341  .name = "xmedian",
342  .description = NULL_IF_CONFIG_SMALL("Pick median pixels from several video inputs."),
343  .priv_size = sizeof(XMedianContext),
344  .priv_class = &xmedian_class,
346  .outputs = outputs,
347  .init = init,
348  .uninit = uninit,
349  .activate = activate,
351 };
formats
formats
Definition: signature.h:48
ff_get_video_buffer
AVFrame * ff_get_video_buffer(AVFilterLink *link, int w, int h)
Request a picture buffer with a specific set of permissions.
Definition: video.c:99
ff_framesync_configure
int ff_framesync_configure(FFFrameSync *fs)
Configure a frame sync structure.
Definition: framesync.c:117
td
#define td
Definition: regdef.h:70
AVPixelFormat
AVPixelFormat
Pixel format.
Definition: pixfmt.h:64
AVERROR
Filter the word “frame” indicates either a video frame or a group of audio as stored in an AVFrame structure Format for each input and each output the list of supported formats For video that means pixel format For audio that means channel sample they are references to shared objects When the negotiation mechanism computes the intersection of the formats supported at each end of a all references to both lists are replaced with a reference to the intersection And when a single format is eventually chosen for a link amongst the remaining all references to the list are updated That means that if a filter requires that its input and output have the same format amongst a supported all it has to do is use a reference to the same list of formats query_formats can leave some formats unset and return AVERROR(EAGAIN) to cause the negotiation mechanism toagain later. That can be used by filters with complex requirements to use the format negotiated on one link to set the formats supported on another. Frame references ownership and permissions
opt.h
FLAGS
#define FLAGS
Definition: vf_xmedian.c:321
ff_make_format_list
AVFilterFormats * ff_make_format_list(const int *fmts)
Create a list of supported formats.
Definition: formats.c:283
ff_framesync_uninit
void ff_framesync_uninit(FFFrameSync *fs)
Free all memory currently allocated.
Definition: framesync.c:293
out
FILE * out
Definition: movenc.c:54
median_frames8
static int median_frames8(AVFilterContext *ctx, void *arg, int jobnr, int nb_jobs)
Definition: vf_xmedian.c:168
ff_filter_frame
int ff_filter_frame(AVFilterLink *link, AVFrame *frame)
Send a frame of data to the next filter.
Definition: avfilter.c:1080
av_pix_fmt_desc_get
const AVPixFmtDescriptor * av_pix_fmt_desc_get(enum AVPixelFormat pix_fmt)
Definition: pixdesc.c:2522
ff_framesync_get_frame
int ff_framesync_get_frame(FFFrameSync *fs, unsigned in, AVFrame **rframe, unsigned get)
Get the current frame in an input.
Definition: framesync.c:256
inlink
The exact code depends on how similar the blocks are and how related they are to the and needs to apply these operations to the correct inlink or outlink if there are several Macros are available to factor that when no extra processing is inlink
Definition: filter_design.txt:212
av_asprintf
char * av_asprintf(const char *fmt,...)
Definition: avstring.c:113
XMedianContext::median_frames
int(* median_frames)(AVFilterContext *ctx, void *arg, int jobnr, int nb_jobs)
Definition: vf_xmedian.c:51
AVFrame
This structure describes decoded (raw) audio or video data.
Definition: frame.h:295
pixdesc.h
AVOption
AVOption.
Definition: opt.h:246
data
const char data[16]
Definition: mxf.c:91
AV_PIX_FMT_YUV420P10
#define AV_PIX_FMT_YUV420P10
Definition: pixfmt.h:387
AVFILTER_DEFINE_CLASS
AVFILTER_DEFINE_CLASS(xmedian)
AV_PIX_FMT_YUV440P
@ AV_PIX_FMT_YUV440P
planar YUV 4:4:0 (1 Cr & Cb sample per 1x2 Y samples)
Definition: pixfmt.h:99
AVFilter::name
const char * name
Filter name.
Definition: avfilter.h:148
FFFrameSync
Frame sync structure.
Definition: framesync.h:146
ThreadData::out
AVFrame * out
Definition: af_adeclick.c:488
video.h
AVFormatContext::internal
AVFormatInternal * internal
An opaque field for libavformat internal usage.
Definition: avformat.h:1795
AV_PIX_FMT_GRAY9
#define AV_PIX_FMT_GRAY9
Definition: pixfmt.h:367
av_image_copy_plane
void av_image_copy_plane(uint8_t *dst, int dst_linesize, const uint8_t *src, int src_linesize, int bytewidth, int height)
Copy image plane from src to dst.
Definition: imgutils.c:338
AVFilterFormats
A list of supported formats for one end of a filter link.
Definition: formats.h:64
formats.h
ff_insert_inpad
static int ff_insert_inpad(AVFilterContext *f, unsigned index, AVFilterPad *p)
Insert a new input pad for the filter.
Definition: internal.h:277
av_pix_fmt_count_planes
int av_pix_fmt_count_planes(enum AVPixelFormat pix_fmt)
Definition: pixdesc.c:2562
EXT_STOP
@ EXT_STOP
Completely stop all streams with this one.
Definition: framesync.h:65
AV_PIX_FMT_GBRP14
#define AV_PIX_FMT_GBRP14
Definition: pixfmt.h:405
XMedianContext::planes
int planes
Definition: vf_xmedian.c:38
XMedianContext::fs
FFFrameSync fs
Definition: vf_xmedian.c:49
xmedian_options
static const AVOption xmedian_options[]
Definition: vf_xmedian.c:323
AV_PIX_FMT_GBRP10
#define AV_PIX_FMT_GBRP10
Definition: pixfmt.h:403
FFFrameSyncIn
Input stream structure.
Definition: framesync.h:81
AV_PIX_FMT_YUV422P9
#define AV_PIX_FMT_YUV422P9
Definition: pixfmt.h:385
AV_PIX_FMT_GRAY16
#define AV_PIX_FMT_GRAY16
Definition: pixfmt.h:371
AVFILTER_FLAG_DYNAMIC_INPUTS
#define AVFILTER_FLAG_DYNAMIC_INPUTS
The number of the filter inputs is not determined just by AVFilter.inputs.
Definition: avfilter.h:105
src
#define src
Definition: vp8dsp.c:254
config_output
static int config_output(AVFilterLink *outlink)
Definition: vf_xmedian.c:237
AVFilterPad
A filter pad used for either input or output.
Definition: internal.h:54
AV_PIX_FMT_YUV444P10
#define AV_PIX_FMT_YUV444P10
Definition: pixfmt.h:390
AV_PIX_FMT_YUVJ411P
@ AV_PIX_FMT_YUVJ411P
planar YUV 4:1:1, 12bpp, (1 Cr & Cb sample per 4x1 Y samples) full scale (JPEG), deprecated in favor ...
Definition: pixfmt.h:258
AV_LOG_ERROR
#define AV_LOG_ERROR
Something went wrong and cannot losslessly be recovered.
Definition: log.h:176
av_cold
#define av_cold
Definition: attributes.h:84
AV_PIX_FMT_YUV422P16
#define AV_PIX_FMT_YUV422P16
Definition: pixfmt.h:399
ff_set_common_formats
int ff_set_common_formats(AVFilterContext *ctx, AVFilterFormats *formats)
A helper for query_formats() which sets all links to the same list of formats.
Definition: formats.c:568
AV_PIX_FMT_YUVJ422P
@ AV_PIX_FMT_YUVJ422P
planar YUV 4:2:2, 16bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV422P and setting col...
Definition: pixfmt.h:79
width
#define width
av_image_fill_linesizes
int av_image_fill_linesizes(int linesizes[4], enum AVPixelFormat pix_fmt, int width)
Fill plane linesizes for an image with pixel format pix_fmt and width width.
Definition: imgutils.c:89
intreadwrite.h
s
#define s(width, name)
Definition: cbs_vp9.c:257
AV_PIX_FMT_YUV444P16
#define AV_PIX_FMT_YUV444P16
Definition: pixfmt.h:400
AV_CEIL_RSHIFT
#define AV_CEIL_RSHIFT(a, b)
Definition: common.h:58
query_formats
static int query_formats(AVFilterContext *ctx)
Definition: vf_xmedian.c:54
XMedianContext::depth
int depth
Definition: vf_xmedian.c:41
slice_end
static int slice_end(AVCodecContext *avctx, AVFrame *pict)
Handle slice ends.
Definition: mpeg12dec.c:2026
AV_PIX_FMT_YUV420P9
#define AV_PIX_FMT_YUV420P9
Definition: pixfmt.h:384
AV_PIX_FMT_YUV420P16
#define AV_PIX_FMT_YUV420P16
Definition: pixfmt.h:398
process_frame
static int process_frame(FFFrameSync *fs)
Definition: vf_xmedian.c:210
ctx
AVFormatContext * ctx
Definition: movenc.c:48
AV_PIX_FMT_GRAY14
#define AV_PIX_FMT_GRAY14
Definition: pixfmt.h:370
av_rescale_q
int64_t av_rescale_q(int64_t a, AVRational bq, AVRational cq)
Rescale a 64-bit integer by 2 rational numbers.
Definition: mathematics.c:142
AV_PIX_FMT_YUV420P
@ AV_PIX_FMT_YUV420P
planar YUV 4:2:0, 12bpp, (1 Cr & Cb sample per 2x2 Y samples)
Definition: pixfmt.h:66
AV_PIX_FMT_YUVJ444P
@ AV_PIX_FMT_YUVJ444P
planar YUV 4:4:4, 24bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV444P and setting col...
Definition: pixfmt.h:80
arg
const char * arg
Definition: jacosubdec.c:66
AV_PIX_FMT_GRAY10
#define AV_PIX_FMT_GRAY10
Definition: pixfmt.h:368
AV_PIX_FMT_GBRP16
#define AV_PIX_FMT_GBRP16
Definition: pixfmt.h:406
XMedianContext::width
int width[4]
Definition: vf_xmedian.c:45
AVClass
Describe the class of an AVClass context structure.
Definition: log.h:67
NULL
#define NULL
Definition: coverity.c:32
fs
#define fs(width, name, subs,...)
Definition: cbs_vp9.c:259
init
static av_cold int init(AVFilterContext *ctx)
Definition: vf_xmedian.c:86
AVRational
Rational number (pair of numerator and denominator).
Definition: rational.h:58
AV_PIX_FMT_YUVJ420P
@ AV_PIX_FMT_YUVJ420P
planar YUV 4:2:0, 12bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV420P and setting col...
Definition: pixfmt.h:78
AV_PIX_FMT_YUV440P10
#define AV_PIX_FMT_YUV440P10
Definition: pixfmt.h:389
AV_PIX_FMT_YUV422P10
#define AV_PIX_FMT_YUV422P10
Definition: pixfmt.h:388
AV_PIX_FMT_GRAY8
@ AV_PIX_FMT_GRAY8
Y , 8bpp.
Definition: pixfmt.h:74
AV_PIX_FMT_GBRP9
#define AV_PIX_FMT_GBRP9
Definition: pixfmt.h:402
ff_vf_xmedian
AVFilter ff_vf_xmedian
Definition: vf_xmedian.c:340
XMedianContext::height
int height[4]
Definition: vf_xmedian.c:46
qsort.h
planes
static const struct @314 planes[]
NULL_IF_CONFIG_SMALL
#define NULL_IF_CONFIG_SMALL(x)
Return NULL if CONFIG_SMALL is true, otherwise the argument without modification.
Definition: internal.h:188
comparei
static int comparei(const void *p1, const void *p2)
Definition: vf_xmedian.c:117
AV_PIX_FMT_YUV422P12
#define AV_PIX_FMT_YUV422P12
Definition: pixfmt.h:392
median_frames16
static int median_frames16(AVFilterContext *ctx, void *arg, int jobnr, int nb_jobs)
Definition: vf_xmedian.c:124
AV_PIX_FMT_YUV444P12
#define AV_PIX_FMT_YUV444P12
Definition: pixfmt.h:394
FFDIFFSIGN
#define FFDIFFSIGN(x, y)
Comparator.
Definition: common.h:92
height
#define height
FFMIN
#define FFMIN(a, b)
Definition: common.h:96
XMedianContext::desc
const AVPixFmtDescriptor * desc
Definition: vf_xmedian.c:36
XMedianContext
Definition: vf_xmedian.c:34
internal.h
in
uint8_t pi<< 24) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_U8, uint8_t,(*(const uint8_t *) pi - 0x80) *(1.0f/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_U8, uint8_t,(*(const uint8_t *) pi - 0x80) *(1.0/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S16, int16_t,(*(const int16_t *) pi >> 8)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S16, int16_t, *(const int16_t *) pi *(1.0f/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S16, int16_t, *(const int16_t *) pi *(1.0/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S32, int32_t,(*(const int32_t *) pi >> 24)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S32, int32_t, *(const int32_t *) pi *(1.0f/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S32, int32_t, *(const int32_t *) pi *(1.0/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_FLT, float, av_clip_uint8(lrintf(*(const float *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_FLT, float, av_clip_int16(lrintf(*(const float *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_FLT, float, av_clipl_int32(llrintf(*(const float *) pi *(1U<< 31)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_DBL, double, av_clip_uint8(lrint(*(const double *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_DBL, double, av_clip_int16(lrint(*(const double *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_DBL, double, av_clipl_int32(llrint(*(const double *) pi *(1U<< 31)))) #define SET_CONV_FUNC_GROUP(ofmt, ifmt) static void set_generic_function(AudioConvert *ac) { } void ff_audio_convert_free(AudioConvert **ac) { if(! *ac) return;ff_dither_free(&(*ac) ->dc);av_freep(ac);} AudioConvert *ff_audio_convert_alloc(AVAudioResampleContext *avr, enum AVSampleFormat out_fmt, enum AVSampleFormat in_fmt, int channels, int sample_rate, int apply_map) { AudioConvert *ac;int in_planar, out_planar;ac=av_mallocz(sizeof(*ac));if(!ac) return NULL;ac->avr=avr;ac->out_fmt=out_fmt;ac->in_fmt=in_fmt;ac->channels=channels;ac->apply_map=apply_map;if(avr->dither_method !=AV_RESAMPLE_DITHER_NONE &&av_get_packed_sample_fmt(out_fmt)==AV_SAMPLE_FMT_S16 &&av_get_bytes_per_sample(in_fmt) > 2) { ac->dc=ff_dither_alloc(avr, out_fmt, in_fmt, channels, sample_rate, apply_map);if(!ac->dc) { av_free(ac);return NULL;} return ac;} in_planar=ff_sample_fmt_is_planar(in_fmt, channels);out_planar=ff_sample_fmt_is_planar(out_fmt, channels);if(in_planar==out_planar) { ac->func_type=CONV_FUNC_TYPE_FLAT;ac->planes=in_planar ? ac->channels :1;} else if(in_planar) ac->func_type=CONV_FUNC_TYPE_INTERLEAVE;else ac->func_type=CONV_FUNC_TYPE_DEINTERLEAVE;set_generic_function(ac);if(ARCH_AARCH64) ff_audio_convert_init_aarch64(ac);if(ARCH_ARM) ff_audio_convert_init_arm(ac);if(ARCH_X86) ff_audio_convert_init_x86(ac);return ac;} int ff_audio_convert(AudioConvert *ac, AudioData *out, AudioData *in) { int use_generic=1;int len=in->nb_samples;int p;if(ac->dc) { av_log(ac->avr, AV_LOG_TRACE, "%d samples - audio_convert: %s to %s (dithered)\n", len, av_get_sample_fmt_name(ac->in_fmt), av_get_sample_fmt_name(ac->out_fmt));return ff_convert_dither(ac-> in
Definition: audio_convert.c:326
i
#define i(width, name, range_min, range_max)
Definition: cbs_h2645.c:259
AV_QSORT
#define AV_QSORT(p, num, type, cmp)
Quicksort This sort is fast, and fully inplace but not stable and it is possible to construct input t...
Definition: qsort.h:33
XMedianContext::linesize
int linesize[4]
Definition: vf_xmedian.c:44
AV_PIX_FMT_GBRP12
#define AV_PIX_FMT_GBRP12
Definition: pixfmt.h:404
ff_filter_get_nb_threads
int ff_filter_get_nb_threads(AVFilterContext *ctx)
Get number of threads for current filter instance.
Definition: avfilter.c:802
XMedianContext::max
int max
Definition: vf_xmedian.c:42
ThreadData
Used for passing data between threads.
Definition: af_adeclick.c:487
AV_PIX_FMT_YUVJ440P
@ AV_PIX_FMT_YUVJ440P
planar YUV 4:4:0 full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV440P and setting color_range
Definition: pixfmt.h:100
uint8_t
uint8_t
Definition: audio_convert.c:194
AVFilterPad::name
const char * name
Pad name.
Definition: internal.h:60
AV_PIX_FMT_YUV444P9
#define AV_PIX_FMT_YUV444P9
Definition: pixfmt.h:386
AVFilter
Filter definition.
Definition: avfilter.h:144
ret
ret
Definition: filter_design.txt:187
AVFilterPad::type
enum AVMediaType type
AVFilterPad type.
Definition: internal.h:65
XMedianContext::nb_inputs
int nb_inputs
Definition: vf_xmedian.c:37
ff_framesync_init
int ff_framesync_init(FFFrameSync *fs, AVFilterContext *parent, unsigned nb_in)
Initialize a frame sync structure.
Definition: framesync.c:77
AV_PIX_FMT_YUV420P12
#define AV_PIX_FMT_YUV420P12
Definition: pixfmt.h:391
XMedianContext::frames
AVFrame ** frames
Definition: vf_xmedian.c:48
left
Tag MUST be and< 10hcoeff half pel interpolation filter coefficients, hcoeff[0] are the 2 middle coefficients[1] are the next outer ones and so on, resulting in a filter like:...eff[2], hcoeff[1], hcoeff[0], hcoeff[0], hcoeff[1], hcoeff[2] ... the sign of the coefficients is not explicitly stored but alternates after each coeff and coeff[0] is positive, so ...,+,-,+,-,+,+,-,+,-,+,... hcoeff[0] is not explicitly stored but found by subtracting the sum of all stored coefficients with signs from 32 hcoeff[0]=32 - hcoeff[1] - hcoeff[2] - ... a good choice for hcoeff and htaps is htaps=6 hcoeff={40,-10, 2} an alternative which requires more computations at both encoder and decoder side and may or may not be better is htaps=8 hcoeff={42,-14, 6,-2}ref_frames minimum of the number of available reference frames and max_ref_frames for example the first frame after a key frame always has ref_frames=1spatial_decomposition_type wavelet type 0 is a 9/7 symmetric compact integer wavelet 1 is a 5/3 symmetric compact integer wavelet others are reserved stored as delta from last, last is reset to 0 if always_reset||keyframeqlog quality(logarithmic quantizer scale) stored as delta from last, last is reset to 0 if always_reset||keyframemv_scale stored as delta from last, last is reset to 0 if always_reset||keyframe FIXME check that everything works fine if this changes between framesqbias dequantization bias stored as delta from last, last is reset to 0 if always_reset||keyframeblock_max_depth maximum depth of the block tree stored as delta from last, last is reset to 0 if always_reset||keyframequant_table quantization tableHighlevel bitstream structure:==============================--------------------------------------------|Header|--------------------------------------------|------------------------------------|||Block0||||split?||||yes no||||......... intra?||||:Block01 :yes no||||:Block02 :....... ..........||||:Block03 ::y DC ::ref index:||||:Block04 ::cb DC ::motion x :||||......... :cr DC ::motion y :||||....... ..........|||------------------------------------||------------------------------------|||Block1|||...|--------------------------------------------|------------ ------------ ------------|||Y subbands||Cb subbands||Cr subbands||||--- ---||--- ---||--- ---|||||LL0||HL0||||LL0||HL0||||LL0||HL0|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||LH0||HH0||||LH0||HH0||||LH0||HH0|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||HL1||LH1||||HL1||LH1||||HL1||LH1|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||HH1||HL2||||HH1||HL2||||HH1||HL2|||||...||...||...|||------------ ------------ ------------|--------------------------------------------Decoding process:=================------------|||Subbands|------------||||------------|Intra DC||||LL0 subband prediction ------------|\ Dequantization ------------------- \||Reference frames|\ IDWT|------- -------|Motion \|||Frame 0||Frame 1||Compensation . OBMC v -------|------- -------|--------------. \------> Frame n output Frame Frame<----------------------------------/|...|------------------- Range Coder:============Binary Range Coder:------------------- The implemented range coder is an adapted version based upon "Range encoding: an algorithm for removing redundancy from a digitised message." by G. N. N. Martin. The symbols encoded by the Snow range coder are bits(0|1). The associated probabilities are not fix but change depending on the symbol mix seen so far. bit seen|new state ---------+----------------------------------------------- 0|256 - state_transition_table[256 - old_state];1|state_transition_table[old_state];state_transition_table={ 0, 0, 0, 0, 0, 0, 0, 0, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150, 151, 152, 152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 190, 191, 192, 194, 194, 195, 196, 197, 198, 199, 200, 201, 202, 202, 204, 205, 206, 207, 208, 209, 209, 210, 211, 212, 213, 215, 215, 216, 217, 218, 219, 220, 220, 222, 223, 224, 225, 226, 227, 227, 229, 229, 230, 231, 232, 234, 234, 235, 236, 237, 238, 239, 240, 241, 242, 243, 244, 245, 246, 247, 248, 248, 0, 0, 0, 0, 0, 0, 0};FIXME Range Coding of integers:------------------------- FIXME Neighboring Blocks:===================left and top are set to the respective blocks unless they are outside of the image in which case they are set to the Null block top-left is set to the top left block unless it is outside of the image in which case it is set to the left block if this block has no larger parent block or it is at the left side of its parent block and the top right block is not outside of the image then the top right block is used for top-right else the top-left block is used Null block y, cb, cr are 128 level, ref, mx and my are 0 Motion Vector Prediction:=========================1. the motion vectors of all the neighboring blocks are scaled to compensate for the difference of reference frames scaled_mv=(mv *(256 *(current_reference+1)/(mv.reference+1))+128)> the median of the scaled left
Definition: snow.txt:386
AV_PIX_FMT_YUV422P14
#define AV_PIX_FMT_YUV422P14
Definition: pixfmt.h:396
av_calloc
void * av_calloc(size_t nmemb, size_t size)
Non-inlined equivalent of av_mallocz_array().
Definition: mem.c:244
framesync.h
XMedianContext::radius
int radius
Definition: vf_xmedian.c:40
AV_PIX_FMT_NONE
@ AV_PIX_FMT_NONE
Definition: pixfmt.h:65
AV_OPT_TYPE_INT
@ AV_OPT_TYPE_INT
Definition: opt.h:223
avfilter.h
uninit
static av_cold void uninit(AVFilterContext *ctx)
Definition: vf_xmedian.c:303
values
these buffered frames must be flushed immediately if a new input produces new the filter must not call request_frame to get more It must just process the frame or queue it The task of requesting more frames is left to the filter s request_frame method or the application If a filter has several the filter must be ready for frames arriving randomly on any input any filter with several inputs will most likely require some kind of queuing mechanism It is perfectly acceptable to have a limited queue and to drop frames when the inputs are too unbalanced request_frame For filters that do not use the this method is called when a frame is wanted on an output For a it should directly call filter_frame on the corresponding output For a if there are queued frames already one of these frames should be pushed If the filter should request a frame on one of its repeatedly until at least one frame has been pushed Return values
Definition: filter_design.txt:263
AV_PIX_FMT_YUV444P
@ AV_PIX_FMT_YUV444P
planar YUV 4:4:4, 24bpp, (1 Cr & Cb sample per 1x1 Y samples)
Definition: pixfmt.h:71
activate
static int activate(AVFilterContext *ctx)
Definition: vf_xmedian.c:314
AVFilterContext
An instance of a filter.
Definition: avfilter.h:338
XMedianContext::nb_planes
int nb_planes
Definition: vf_xmedian.c:43
AV_PIX_FMT_GBRP
@ AV_PIX_FMT_GBRP
planar GBR 4:4:4 24bpp
Definition: pixfmt.h:168
AVFILTER_FLAG_SLICE_THREADS
#define AVFILTER_FLAG_SLICE_THREADS
The filter supports multithreading by splitting frames into multiple parts and processing them concur...
Definition: avfilter.h:116
AVMEDIA_TYPE_VIDEO
@ AVMEDIA_TYPE_VIDEO
Definition: avutil.h:201
AV_PIX_FMT_YUV422P
@ AV_PIX_FMT_YUV422P
planar YUV 4:2:2, 16bpp, (1 Cr & Cb sample per 2x1 Y samples)
Definition: pixfmt.h:70
ThreadData::in
AVFrame * in
Definition: af_afftdn.c:1082
AVPixFmtDescriptor
Descriptor that unambiguously describes how the bits of a pixel are stored in the up to 4 data planes...
Definition: pixdesc.h:81
outputs
static const AVFilterPad outputs[]
Definition: vf_xmedian.c:329
av_freep
#define av_freep(p)
Definition: tableprint_vlc.h:35
AV_PIX_FMT_YUV411P
@ AV_PIX_FMT_YUV411P
planar YUV 4:1:1, 12bpp, (1 Cr & Cb sample per 4x1 Y samples)
Definition: pixfmt.h:73
imgutils.h
flags
#define flags(name, subs,...)
Definition: cbs_av1.c:565
AVERROR_BUG
#define AVERROR_BUG
Internal bug, also see AVERROR_BUG2.
Definition: error.h:50
AV_PIX_FMT_YUV410P
@ AV_PIX_FMT_YUV410P
planar YUV 4:1:0, 9bpp, (1 Cr & Cb sample per 4x4 Y samples)
Definition: pixfmt.h:72
av_log
#define av_log(a,...)
Definition: tableprint_vlc.h:28
AV_PIX_FMT_YUV440P12
#define AV_PIX_FMT_YUV440P12
Definition: pixfmt.h:393
AV_PIX_FMT_YUV444P14
#define AV_PIX_FMT_YUV444P14
Definition: pixfmt.h:397
ff_framesync_activate
int ff_framesync_activate(FFFrameSync *fs)
Examine the frames in the filter's input and try to produce output.
Definition: framesync.c:344
avstring.h
AV_PIX_FMT_GRAY12
#define AV_PIX_FMT_GRAY12
Definition: pixfmt.h:369
int
int
Definition: ffmpeg_filter.c:191
OFFSET
#define OFFSET(x)
Definition: vf_xmedian.c:320
AV_PIX_FMT_YUV420P14
#define AV_PIX_FMT_YUV420P14
Definition: pixfmt.h:395