FFmpeg
vf_entropy.c
Go to the documentation of this file.
1 /*
2  * Copyright (c) 2017 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/imgutils.h"
22 #include "libavutil/opt.h"
23 #include "libavutil/pixdesc.h"
24 #include "avfilter.h"
25 #include "drawutils.h"
26 #include "formats.h"
27 #include "internal.h"
28 #include "video.h"
29 
30 typedef struct EntropyContext {
31  const AVClass *class;
32 
33  int mode;
34 
35  int nb_planes;
36  int planeheight[4];
37  int planewidth[4];
38  int depth;
39  int is_rgb;
41  char planenames[4];
42  int64_t *histogram;
44 
45 #define OFFSET(x) offsetof(EntropyContext, x)
46 #define FLAGS AV_OPT_FLAG_FILTERING_PARAM|AV_OPT_FLAG_VIDEO_PARAM
47 static const AVOption entropy_options[] = {
48  { "mode", "set kind of histogram entropy measurement", OFFSET(mode), AV_OPT_TYPE_INT, {.i64=0}, 0, 1, FLAGS, "mode" },
49  { "normal", NULL, 0, AV_OPT_TYPE_CONST, {.i64=0}, 0, 0, FLAGS, "mode" },
50  { "diff", NULL, 0, AV_OPT_TYPE_CONST, {.i64=1}, 0, 0, FLAGS, "mode" },
51  { NULL }
52 };
53 
54 AVFILTER_DEFINE_CLASS(entropy);
55 
57 {
58  static const enum AVPixelFormat pixfmts[] = {
74  };
75 
77  if (!formats)
78  return AVERROR(ENOMEM);
79  return ff_set_common_formats(ctx, formats);
80 }
81 
83 {
85  AVFilterContext *ctx = inlink->dst;
86  EntropyContext *s = ctx->priv;
87 
88  s->nb_planes = desc->nb_components;
89 
90  s->planeheight[1] = s->planeheight[2] = AV_CEIL_RSHIFT(inlink->h, desc->log2_chroma_h);
91  s->planeheight[0] = s->planeheight[3] = inlink->h;
92  s->planewidth[1] = s->planewidth[2] = AV_CEIL_RSHIFT(inlink->w, desc->log2_chroma_w);
93  s->planewidth[0] = s->planewidth[3] = inlink->w;
94 
95  s->depth = desc->comp[0].depth;
96  s->is_rgb = ff_fill_rgba_map(s->rgba_map, inlink->format) >= 0;
97 
98  s->planenames[0] = s->is_rgb ? 'R' : 'Y';
99  s->planenames[1] = s->is_rgb ? 'G' : 'U';
100  s->planenames[2] = s->is_rgb ? 'B' : 'V';
101  s->planenames[3] = 'A';
102 
103  s->histogram = av_malloc_array(1 << s->depth, sizeof(*s->histogram));
104  if (!s->histogram)
105  return AVERROR(ENOMEM);
106 
107  return 0;
108 }
109 
111 {
112  AVFilterContext *ctx = inlink->dst;
113  AVFilterLink *outlink = ctx->outputs[0];
114  EntropyContext *s = ctx->priv;
115  int plane, y, x;
116 
117  for (plane = 0; plane < s->nb_planes; plane++) {
118  int cidx = s->is_rgb ? s->rgba_map[plane] : plane;
119  const uint8_t *src8 = in->data[plane];
120  const uint16_t *src16 = (const uint16_t *)in->data[plane];
121  float total = s->planewidth[plane] * s->planeheight[plane];
122  float entropy = 0;
123  char metabuf[128];
124  char key[128];
125 
126  memset(s->histogram, 0, (1 << s->depth) * sizeof(*s->histogram));
127 
128  if (s->depth <= 8) {
129  for (y = 0; y < s->planeheight[plane]; y++) {
130  for (x = 0; x < s->planewidth[plane]; x++) {
131  s->histogram[src8[x]]++;
132  }
133 
134  src8 += in->linesize[plane];
135  }
136  } else {
137  for (y = 0; y < s->planeheight[plane]; y++) {
138  for (x = 0; x < s->planewidth[plane]; x++) {
139  s->histogram[src16[x]]++;
140  }
141 
142  src16 += in->linesize[plane] / 2;
143  }
144  }
145 
146  for (y = 0; y < 1 << s->depth; y++) {
147  if (s->mode == 0) {
148  if (s->histogram[y]) {
149  float p = s->histogram[y] / total;
150  entropy += -log2(p) * p;
151  }
152  } else if (s->mode == 1) {
153  if (y && (s->histogram[y] - s->histogram[y - 1]) != 0) {
154  float p = FFABS(s->histogram[y] - s->histogram[y - 1]) / total;
155  entropy += -log2(p) * p;
156  }
157  }
158  }
159 
160  snprintf(key, sizeof(key), "lavfi.entropy.entropy.%s.%c", s->mode ? "diff" : "normal", s->planenames[cidx]);
161  snprintf(metabuf, sizeof(metabuf), "%f", entropy);
162  av_dict_set(&in->metadata, key, metabuf, 0);
163  snprintf(key, sizeof(key), "lavfi.entropy.normalized_entropy.%s.%c", s->mode ? "diff" : "normal", s->planenames[cidx]);
164  snprintf(metabuf, sizeof(metabuf), "%f", entropy / log2(1 << s->depth));
165  av_dict_set(&in->metadata, key, metabuf, 0);
166  }
167 
168  return ff_filter_frame(outlink, in);
169 }
170 
172 {
173  EntropyContext *s = ctx->priv;
174 
175  av_freep(&s->histogram);
176 }
177 
178 static const AVFilterPad inputs[] = {
179  {
180  .name = "default",
181  .type = AVMEDIA_TYPE_VIDEO,
182  .filter_frame = filter_frame,
183  .config_props = config_input,
184  },
185  { NULL }
186 };
187 
188 static const AVFilterPad outputs[] = {
189  {
190  .name = "default",
191  .type = AVMEDIA_TYPE_VIDEO,
192  },
193  { NULL }
194 };
195 
197  .name = "entropy",
198  .description = NULL_IF_CONFIG_SMALL("Measure video frames entropy."),
199  .priv_size = sizeof(EntropyContext),
200  .uninit = uninit,
202  .inputs = inputs,
203  .outputs = outputs,
204  .priv_class = &entropy_class,
206 };
int plane
Definition: avisynth_c.h:384
#define NULL
Definition: coverity.c:32
#define AV_PIX_FMT_YUV440P10
Definition: pixfmt.h:389
const AVPixFmtDescriptor * av_pix_fmt_desc_get(enum AVPixelFormat pix_fmt)
Definition: pixdesc.c:2522
This structure describes decoded (raw) audio or video data.
Definition: frame.h:295
AVOption.
Definition: opt.h:246
#define AV_PIX_FMT_YUV444P14
Definition: pixfmt.h:397
planar YUV 4:4:4, 24bpp, (1 Cr & Cb sample per 1x1 Y samples)
Definition: pixfmt.h:71
misc image utilities
Main libavfilter public API header.
const char * desc
Definition: nvenc.c:68
planar GBR 4:4:4 24bpp
Definition: pixfmt.h:168
#define AV_PIX_FMT_GBRP10
Definition: pixfmt.h:403
#define AV_PIX_FMT_GRAY9
Definition: pixfmt.h:367
#define AV_PIX_FMT_YUV420P12
Definition: pixfmt.h:391
const char * key
uint8_t log2_chroma_w
Amount to shift the luma width right to find the chroma width.
Definition: pixdesc.h:92
#define log2(x)
Definition: libm.h:404
AVFilterFormats * ff_make_format_list(const int *fmts)
Create a list of supported formats.
Definition: formats.c:283
#define AV_PIX_FMT_GRAY10
Definition: pixfmt.h:368
#define AVFILTER_FLAG_SUPPORT_TIMELINE_GENERIC
Some filters support a generic "enable" expression option that can be used to enable or disable a fil...
Definition: avfilter.h:125
const char * name
Pad name.
Definition: internal.h:60
int planeheight[4]
Definition: vf_entropy.c:36
#define AV_PIX_FMT_GRAY12
Definition: pixfmt.h:369
int ff_filter_frame(AVFilterLink *link, AVFrame *frame)
Send a frame of data to the next filter.
Definition: avfilter.c:1093
AVComponentDescriptor comp[4]
Parameters that describe how pixels are packed.
Definition: pixdesc.h:117
uint8_t
#define av_cold
Definition: attributes.h:82
AVOptions.
#define AV_PIX_FMT_GBRP9
Definition: pixfmt.h:402
planar YUV 4:4:0 full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV440P and setting color_range...
Definition: pixfmt.h:100
planar YUV 4:2:2, 16bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV422P and setting col...
Definition: pixfmt.h:79
AVDictionary * metadata
metadata.
Definition: frame.h:581
#define AV_PIX_FMT_YUV444P16
Definition: pixfmt.h:400
#define AV_PIX_FMT_YUV422P12
Definition: pixfmt.h:392
static const AVFilterPad inputs[]
Definition: vf_entropy.c:178
A filter pad used for either input or output.
Definition: internal.h:54
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:569
uint8_t log2_chroma_h
Amount to shift the luma height right to find the chroma height.
Definition: pixdesc.h:101
static int config_input(AVFilterLink *inlink)
Definition: vf_entropy.c:82
#define NULL_IF_CONFIG_SMALL(x)
Return NULL if CONFIG_SMALL is true, otherwise the argument without modification. ...
Definition: internal.h:186
void * priv
private data for use by the filter
Definition: avfilter.h:353
#define AV_PIX_FMT_YUV444P10
Definition: pixfmt.h:390
planar YUV 4:2:2, 16bpp, (1 Cr & Cb sample per 2x1 Y samples)
Definition: pixfmt.h:70
#define AV_PIX_FMT_YUV422P9
Definition: pixfmt.h:385
uint8_t nb_components
The number of components each pixel has, (1-4)
Definition: pixdesc.h:83
#define AV_PIX_FMT_GBRP16
Definition: pixfmt.h:406
#define AV_PIX_FMT_GRAY16
Definition: pixfmt.h:371
planar YUV 4:2:0, 12bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV420P and setting col...
Definition: pixfmt.h:78
AVFormatContext * ctx
Definition: movenc.c:48
#define FFABS(a)
Absolute value, Note, INT_MIN / INT64_MIN result in undefined behavior as they are not representable ...
Definition: common.h:72
#define s(width, name)
Definition: cbs_vp9.c:257
int planewidth[4]
Definition: vf_entropy.c:37
char planenames[4]
Definition: vf_entropy.c:41
static int query_formats(AVFilterContext *ctx)
Definition: vf_entropy.c:56
#define AV_PIX_FMT_YUV444P9
Definition: pixfmt.h:386
#define AV_PIX_FMT_GBRP14
Definition: pixfmt.h:405
int ff_fill_rgba_map(uint8_t *rgba_map, enum AVPixelFormat pix_fmt)
Definition: drawutils.c:35
#define AV_PIX_FMT_YUV420P16
Definition: pixfmt.h:398
#define AV_PIX_FMT_YUV420P14
Definition: pixfmt.h:395
misc drawing utilities
int linesize[AV_NUM_DATA_POINTERS]
For video, size in bytes of each picture line.
Definition: frame.h:326
#define FLAGS
Definition: vf_entropy.c:46
Descriptor that unambiguously describes how the bits of a pixel are stored in the up to 4 data planes...
Definition: pixdesc.h:81
#define AV_PIX_FMT_GRAY14
Definition: pixfmt.h:370
int av_dict_set(AVDictionary **pm, const char *key, const char *value, int flags)
Set the given entry in *pm, overwriting an existing entry.
Definition: dict.c:70
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
#define AV_PIX_FMT_YUV420P10
Definition: pixfmt.h:387
Describe the class of an AVClass context structure.
Definition: log.h:67
Filter definition.
Definition: avfilter.h:144
static av_cold void uninit(AVFilterContext *ctx)
Definition: vf_entropy.c:171
static const AVOption entropy_options[]
Definition: vf_entropy.c:47
uint8_t rgba_map[4]
Definition: vf_entropy.c:40
const char * name
Filter name.
Definition: avfilter.h:148
#define AV_PIX_FMT_YUV440P12
Definition: pixfmt.h:393
#define AV_PIX_FMT_YUV420P9
Definition: pixfmt.h:384
#define snprintf
Definition: snprintf.h:34
AVFilterLink ** outputs
array of pointers to output links
Definition: avfilter.h:350
AVFILTER_DEFINE_CLASS(entropy)
#define AV_PIX_FMT_YUV422P14
Definition: pixfmt.h:396
#define AV_PIX_FMT_GBRP12
Definition: pixfmt.h:404
#define flags(name, subs,...)
Definition: cbs_av1.c:561
#define AV_PIX_FMT_YUV422P10
Definition: pixfmt.h:388
#define AV_PIX_FMT_YUV444P12
Definition: pixfmt.h:394
uint8_t * data[AV_NUM_DATA_POINTERS]
pointer to the picture/channel planes.
Definition: frame.h:309
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
planar YUV 4:2:0, 12bpp, (1 Cr & Cb sample per 2x2 Y samples)
Definition: pixfmt.h:66
Y , 8bpp.
Definition: pixfmt.h:74
planar YUV 4:4:4, 24bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV444P and setting col...
Definition: pixfmt.h:80
planar YUV 4:1:1, 12bpp, (1 Cr & Cb sample per 4x1 Y samples)
Definition: pixfmt.h:73
AVFilter ff_vf_entropy
Definition: vf_entropy.c:196
static int filter_frame(AVFilterLink *inlink, AVFrame *in)
Definition: vf_entropy.c:110
static const AVFilterPad outputs[]
Definition: vf_entropy.c:188
int64_t * histogram
Definition: vf_entropy.c:42
A list of supported formats for one end of a filter link.
Definition: formats.h:64
planar YUV 4:1:1, 12bpp, (1 Cr & Cb sample per 4x1 Y samples) full scale (JPEG), deprecated in favor ...
Definition: pixfmt.h:258
An instance of a filter.
Definition: avfilter.h:338
#define av_freep(p)
planar YUV 4:4:0 (1 Cr & Cb sample per 1x2 Y samples)
Definition: pixfmt.h:99
#define OFFSET(x)
Definition: vf_entropy.c:45
#define av_malloc_array(a, b)
formats
Definition: signature.h:48
internal API functions
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
int depth
Number of bits in the component.
Definition: pixdesc.h:58
AVPixelFormat
Pixel format.
Definition: pixfmt.h:64
mode
Use these values in ebur128_init (or&#39;ed).
Definition: ebur128.h:83
#define AV_PIX_FMT_YUV422P16
Definition: pixfmt.h:399
#define AV_CEIL_RSHIFT(a, b)
Definition: common.h:58