Go to the documentation of this file.
63 #define OFFSET(x) offsetof(HistogramContext, x)
64 #define FLAGS AV_OPT_FLAG_FILTERING_PARAM|AV_OPT_FLAG_VIDEO_PARAM
66 #define COMMON_OPTIONS \
67 { "display_mode", "set display mode", OFFSET(display_mode), AV_OPT_TYPE_INT, {.i64=2}, 0, 2, FLAGS, "display_mode"}, \
68 { "d", "set display mode", OFFSET(display_mode), AV_OPT_TYPE_INT, {.i64=2}, 0, 2, FLAGS, "display_mode"}, \
69 { "overlay", NULL, 0, AV_OPT_TYPE_CONST, {.i64=0}, 0, 0, FLAGS, "display_mode" }, \
70 { "parade", NULL, 0, AV_OPT_TYPE_CONST, {.i64=1}, 0, 0, FLAGS, "display_mode" }, \
71 { "stack", NULL, 0, AV_OPT_TYPE_CONST, {.i64=2}, 0, 0, FLAGS, "display_mode" }, \
72 { "levels_mode", "set levels mode", OFFSET(levels_mode), AV_OPT_TYPE_INT, {.i64=0}, 0, 1, FLAGS, "levels_mode"}, \
73 { "m", "set levels mode", OFFSET(levels_mode), AV_OPT_TYPE_INT, {.i64=0}, 0, 1, FLAGS, "levels_mode"}, \
74 { "linear", NULL, 0, AV_OPT_TYPE_CONST, {.i64=0}, 0, 0, FLAGS, "levels_mode" }, \
75 { "logarithmic", NULL, 0, AV_OPT_TYPE_CONST, {.i64=1}, 0, 0, FLAGS, "levels_mode" }, \
76 { "components", "set color components to display", OFFSET(components), AV_OPT_TYPE_INT, {.i64=7}, 1, 15, FLAGS}, \
77 { "c", "set color components to display", OFFSET(components), AV_OPT_TYPE_INT, {.i64=7}, 1, 15, FLAGS},
159 if (!
ctx->inputs[0]->incfg.formats ||
160 !
ctx->inputs[0]->incfg.formats->nb_formats) {
164 if (!
ctx->inputs[0]->outcfg.formats)
167 avff =
ctx->inputs[0]->incfg.formats;
212 s->ncomp =
s->desc->nb_components;
213 s->histogram_size = 1 <<
s->desc->comp[0].depth;
214 s->mult =
s->histogram_size / 256;
226 s->start[0] =
s->start[1] =
s->start[2] =
s->start[3] = 0;
227 memcpy(
s->envelope_color,
s->envelope_rgba, 4);
232 s->start[0] =
s->start[3] = 0;
233 s->start[1] =
s->start[2] =
s->histogram_size / 2;
234 s->envelope_color[0] =
RGB_TO_Y_BT709(
s->envelope_rgba[0],
s->envelope_rgba[1],
s->envelope_rgba[2]);
235 s->envelope_color[1] =
RGB_TO_U_BT709(
s->envelope_rgba[0],
s->envelope_rgba[1],
s->envelope_rgba[2], 0);
236 s->envelope_color[2] =
RGB_TO_V_BT709(
s->envelope_rgba[0],
s->envelope_rgba[1],
s->envelope_rgba[2], 0);
237 s->envelope_color[3] =
s->envelope_rgba[3];
240 s->fg_color[3] =
s->fgopacity * 255;
241 s->bg_color[3] =
s->bgopacity * 255;
244 s->planeheight[0] =
s->planeheight[3] =
inlink->h;
246 s->planewidth[0] =
s->planewidth[3] =
inlink->w;
257 if (!strcmp(
ctx->filter->name,
"thistogram"))
260 for (
i = 0;
i <
s->ncomp;
i++) {
261 if ((1 <<
i) &
s->components)
267 s->width =
ctx->inputs[0]->w;
268 outlink->
w =
s->width *
FFMAX(ncomp * (
s->display_mode == 1), 1);
269 outlink->
h =
s->histogram_size *
FFMAX(ncomp * (
s->display_mode == 2), 1);
271 outlink->
w =
s->histogram_size *
FFMAX(ncomp * (
s->display_mode == 1), 1);
272 outlink->
h = (
s->level_height +
s->scale_height) *
FFMAX(ncomp * (
s->display_mode == 2), 1);
276 s->dncomp =
s->odesc->nb_components;
290 if (!
s->thistogram || !
out) {
298 for (k = 0; k < 4 &&
out->data[k]; k++) {
299 const int is_chroma = (k == 1 || k == 2);
300 const int dst_h =
AV_CEIL_RSHIFT(outlink->
h, (is_chroma ?
s->odesc->log2_chroma_h : 0));
301 const int dst_w =
AV_CEIL_RSHIFT(outlink->
w, (is_chroma ?
s->odesc->log2_chroma_w : 0));
303 if (
s->histogram_size <= 256) {
304 for (
i = 0;
i < dst_h ;
i++)
305 memset(
out->data[
s->odesc->comp[k].plane] +
306 i *
out->linesize[
s->odesc->comp[k].plane],
307 s->bg_color[k], dst_w);
309 const int mult =
s->mult;
311 for (
i = 0;
i < dst_h ;
i++)
312 for (j = 0; j < dst_w; j++)
314 i *
out->linesize[
s->odesc->comp[k].plane] + j * 2,
315 s->bg_color[k] *
mult);
320 for (m = 0, k = 0; k <
s->ncomp; k++) {
321 const int p =
s->desc->comp[k].plane;
322 const int max_value =
s->histogram_size - 1 -
s->start[p];
323 const int height =
s->planeheight[p];
324 const int width =
s->planewidth[p];
326 unsigned max_hval = 0;
329 if (!((1 << k) &
s->components))
332 starty = m *
s->histogram_size * (
s->display_mode == 2);
333 startx = m++ *
s->width * (
s->display_mode == 1);
335 startx = m *
s->histogram_size * (
s->display_mode == 1);
336 starty = m++ * (
s->level_height +
s->scale_height) * (
s->display_mode == 2);
339 if (
s->histogram_size <= 256) {
342 for (j = 0; j <
width; j++)
343 s->histogram[
src[j]]++;
347 const uint16_t *
src = (
const uint16_t *)(
in->data[p] +
i *
in->linesize[p]);
348 for (j = 0; j <
width; j++)
349 s->histogram[
src[j]]++;
353 for (
i = 0;
i <
s->histogram_size;
i++)
354 max_hval =
FFMAX(max_hval,
s->histogram[
i]);
355 max_hval_log =
log2(max_hval + 1);
358 const int bpp = 1 + (
s->histogram_size > 256);
359 int minh =
s->histogram_size - 1, maxh = 0;
362 s->x_pos =
out->width - 1;
363 for (j = 0; j < outlink->
h; j++) {
364 memmove(
out->data[p] + j *
out->linesize[p] ,
365 out->data[p] + j *
out->linesize[p] + bpp,
366 (outlink->
w - 1) * bpp);
368 }
else if (
s->slide == 3) {
370 for (j = 0; j < outlink->
h; j++) {
371 memmove(
out->data[p] + j *
out->linesize[p] + bpp,
372 out->data[p] + j *
out->linesize[p],
373 (outlink->
w - 1) * bpp);
377 for (
int i = 0;
i <
s->histogram_size;
i++) {
378 int idx =
s->histogram_size -
i - 1;
381 if (
s->envelope &&
s->histogram[idx]) {
387 value +=
lrint(max_value * (
log2(
s->histogram[idx] + 1) / max_hval_log));
389 value +=
lrint(max_value *
s->histogram[idx] / (
float)max_hval);
391 if (
s->histogram_size <= 256) {
392 s->out->data[p][(
i + starty) *
s->out->linesize[p] + startx +
s->x_pos] =
value;
394 AV_WN16(
s->out->data[p] + (
i + starty) *
s->out->linesize[p] + startx * 2 +
s->x_pos * 2,
value);
399 if (
s->histogram_size <= 256) {
400 s->out->data[0][(minh + starty) *
s->out->linesize[p] + startx +
s->x_pos] =
s->envelope_color[0];
401 s->out->data[0][(maxh + starty) *
s->out->linesize[p] + startx +
s->x_pos] =
s->envelope_color[0];
402 if (
s->dncomp >= 3) {
403 s->out->data[1][(minh + starty) *
s->out->linesize[p] + startx +
s->x_pos] =
s->envelope_color[1];
404 s->out->data[2][(minh + starty) *
s->out->linesize[p] + startx +
s->x_pos] =
s->envelope_color[2];
405 s->out->data[1][(maxh + starty) *
s->out->linesize[p] + startx +
s->x_pos] =
s->envelope_color[1];
406 s->out->data[2][(maxh + starty) *
s->out->linesize[p] + startx +
s->x_pos] =
s->envelope_color[2];
409 const int mult =
s->mult;
411 AV_WN16(
s->out->data[0] + (minh + starty) *
s->out->linesize[p] + startx * 2 +
s->x_pos * 2,
s->envelope_color[0] *
mult);
412 AV_WN16(
s->out->data[0] + (maxh + starty) *
s->out->linesize[p] + startx * 2 +
s->x_pos * 2,
s->envelope_color[0] *
mult);
413 if (
s->dncomp >= 3) {
414 AV_WN16(
s->out->data[1] + (minh + starty) *
s->out->linesize[p] + startx * 2 +
s->x_pos * 2,
s->envelope_color[1] *
mult);
415 AV_WN16(
s->out->data[2] + (minh + starty) *
s->out->linesize[p] + startx * 2 +
s->x_pos * 2,
s->envelope_color[2] *
mult);
416 AV_WN16(
s->out->data[1] + (maxh + starty) *
s->out->linesize[p] + startx * 2 +
s->x_pos * 2,
s->envelope_color[1] *
mult);
417 AV_WN16(
s->out->data[2] + (maxh + starty) *
s->out->linesize[p] + startx * 2 +
s->x_pos * 2,
s->envelope_color[2] *
mult);
422 for (
i = 0;
i <
s->histogram_size;
i++) {
426 col_height =
lrint(
s->level_height * (1. - (
log2(
s->histogram[
i] + 1) / max_hval_log)));
428 col_height =
s->level_height - (
s->histogram[
i] * (int64_t)
s->level_height + max_hval - 1) / max_hval;
430 if (
s->histogram_size <= 256) {
431 for (j =
s->level_height - 1; j >= col_height; j--) {
432 if (
s->display_mode) {
433 for (l = 0; l <
s->dncomp; l++)
434 out->data[l][(j + starty) *
out->linesize[l] + startx +
i] =
s->fg_color[l];
436 out->data[p][(j + starty) *
out->linesize[p] + startx +
i] = 255;
439 for (j =
s->level_height +
s->scale_height - 1; j >=
s->level_height; j--)
440 out->data[p][(j + starty) *
out->linesize[p] + startx +
i] =
i;
442 const int mult =
s->mult;
444 for (j =
s->level_height - 1; j >= col_height; j--) {
445 if (
s->display_mode) {
446 for (l = 0; l <
s->dncomp; l++)
447 AV_WN16(
out->data[l] + (j + starty) *
out->linesize[l] + startx * 2 +
i * 2,
s->fg_color[l] *
mult);
449 AV_WN16(
out->data[p] + (j + starty) *
out->linesize[p] + startx * 2 +
i * 2, 255 *
mult);
452 for (j =
s->level_height +
s->scale_height - 1; j >=
s->level_height; j--)
453 AV_WN16(
out->data[p] + (j + starty) *
out->linesize[p] + startx * 2 +
i * 2,
i);
458 memset(
s->histogram, 0,
s->histogram_size *
sizeof(
unsigned));
464 if (
s->x_pos >=
s->width) {
466 if (
s->thistogram && (
s->slide == 4 ||
s->slide == 0)) {
470 }
else if (
s->thistogram &&
s->slide == 4) {
504 #if CONFIG_HISTOGRAM_FILTER
513 .priv_class = &histogram_class,
518 #if CONFIG_THISTOGRAM_FILTER
527 static const AVOption thistogram_options[] = {
549 .
name =
"thistogram",
556 .priv_class = &thistogram_class,
AVFrame * ff_get_video_buffer(AVFilterLink *link, int w, int h)
Request a picture buffer with a specific set of permissions.
AVPixelFormat
Pixel format.
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 ff_filter_frame(AVFilterLink *link, AVFrame *frame)
Send a frame of data to the next filter.
static const AVFilterPad outputs[]
const AVPixFmtDescriptor * av_pix_fmt_desc_get(enum AVPixelFormat pix_fmt)
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
const AVPixFmtDescriptor * odesc
void av_frame_free(AVFrame **frame)
Free the frame and any dynamically allocated objects in it, e.g.
#define AV_PIX_FMT_YUVA422P9
static int query_formats(AVFilterContext *ctx)
This structure describes decoded (raw) audio or video data.
static const uint8_t black_yuva_color[4]
#define AV_PIX_FMT_YUVA420P10
static enum AVPixelFormat levels_out_yuv8_pix_fmts[]
#define AV_PIX_FMT_YUV420P10
static enum AVPixelFormat levels_out_yuv9_pix_fmts[]
@ AV_PIX_FMT_YUV440P
planar YUV 4:4:0 (1 Cr & Cb sample per 1x2 Y samples)
static int config_input(AVFilterLink *inlink)
static int filter_frame(AVFilterLink *inlink, AVFrame *in)
const char * name
Filter name.
static const uint8_t white_gbrp_color[4]
A link between two filters.
#define AV_PIX_FMT_YUVA422P10
#define AV_PIX_FMT_YUVA420P9
@ AV_PIX_FMT_GBRAP
planar GBRA 4:4:4:4 32bpp
#define AV_PIX_FMT_GBRP10
#define AV_PIX_FMT_YUV422P9
A filter pad used for either input or output.
static enum AVPixelFormat levels_out_rgb10_pix_fmts[]
#define AV_PIX_FMT_YUV444P10
@ AV_PIX_FMT_YUVJ411P
planar YUV 4:1:1, 12bpp, (1 Cr & Cb sample per 4x1 Y samples) full scale (JPEG), deprecated in favor ...
static int16_t mult(Float11 *f1, Float11 *f2)
@ AV_PIX_FMT_YUVJ422P
planar YUV 4:2:2, 16bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV422P and setting col...
#define AV_PIX_FMT_GBRAP10
#define RGB_TO_Y_BT709(r, g, b)
static const AVOption histogram_options[]
#define AV_PIX_FMT_GBRAP12
@ AV_PIX_FMT_YUVA420P
planar YUV 4:2:0, 20bpp, (1 Cr & Cb sample per 2x2 Y & A samples)
#define AV_CEIL_RSHIFT(a, b)
#define RGB_TO_U_BT709(r1, g1, b1, max)
AVRational sample_aspect_ratio
agreed upon sample aspect ratio
uint8_t envelope_color[4]
#define AV_PIX_FMT_YUVA444P12
#define AV_PIX_FMT_YUV420P9
AVFrame * av_frame_clone(const AVFrame *src)
Create a new frame that references the same data as src.
@ AV_PIX_FMT_YUV420P
planar YUV 4:2:0, 12bpp, (1 Cr & Cb sample per 2x2 Y samples)
@ AV_PIX_FMT_YUVJ444P
planar YUV 4:4:4, 24bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV444P and setting col...
Describe the class of an AVClass context structure.
Rational number (pair of numerator and denominator).
@ AV_PIX_FMT_YUVJ420P
planar YUV 4:2:0, 12bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV420P and setting col...
static enum AVPixelFormat levels_out_rgb12_pix_fmts[]
#define AV_PIX_FMT_YUV422P10
@ AV_PIX_FMT_GRAY8
Y , 8bpp.
static int config_output(AVFilterLink *outlink)
#define RGB_TO_V_BT709(r1, g1, b1, max)
static const AVFilterPad inputs[]
#define NULL_IF_CONFIG_SMALL(x)
Return NULL if CONFIG_SMALL is true, otherwise the argument without modification.
#define AV_PIX_FMT_FLAG_RGB
The pixel format contains RGB-like data (as opposed to YUV/grayscale).
AVFILTER_DEFINE_CLASS(histogram)
int format
agreed upon media format
#define AV_PIX_FMT_YUV422P12
#define AV_PIX_FMT_YUV444P12
AVFilterContext * src
source filter
@ AV_PIX_FMT_YUVA444P
planar YUV 4:4:4 32bpp, (1 Cr & Cb sample per 1x1 Y & A samples)
#define AV_PIX_FMT_YUVA444P10
AVFilter ff_vf_thistogram
static enum AVPixelFormat levels_in_pix_fmts[]
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
static float envelope(const float x)
int w
agreed upon image width
#define AV_PIX_FMT_GBRP12
static enum AVPixelFormat out_pix_fmts[]
static enum AVPixelFormat levels_out_yuv10_pix_fmts[]
it s the only field you need to keep assuming you have a context There is some magic you don t need to care about around this just let it vf default value
const AVPixFmtDescriptor * desc
const char * name
Pad name.
#define AV_PIX_FMT_YUV444P9
#define AV_PIX_FMT_YUVA444P9
#define AV_PIX_FMT_YUV420P12
int h
agreed upon image height
#define AV_PIX_FMT_YUVA422P12
static enum AVPixelFormat levels_out_rgb8_pix_fmts[]
@ AV_PIX_FMT_YUV444P
planar YUV 4:4:4, 24bpp, (1 Cr & Cb sample per 1x1 Y samples)
@ AV_PIX_FMT_GBRP
planar GBR 4:4:4 24bpp
@ AV_PIX_FMT_YUV422P
planar YUV 4:2:2, 16bpp, (1 Cr & Cb sample per 2x1 Y samples)
static enum AVPixelFormat levels_out_yuv12_pix_fmts[]
Descriptor that unambiguously describes how the bits of a pixel are stored in the up to 4 data planes...
@ AV_PIX_FMT_YUV411P
planar YUV 4:1:1, 12bpp, (1 Cr & Cb sample per 4x1 Y samples)
static const SheerTable rgb[2]
@ AV_PIX_FMT_YUV410P
planar YUV 4:1:0, 9bpp, (1 Cr & Cb sample per 4x4 Y samples)
static enum AVPixelFormat levels_out_rgb9_pix_fmts[]
unsigned histogram[256 *256]
static av_cold int uninit(AVCodecContext *avctx)
#define AV_PIX_FMT_YUV440P12
static const uint8_t black_gbrp_color[4]
@ AV_PIX_FMT_YUVA422P
planar YUV 4:2:2 24bpp, (1 Cr & Cb sample per 2x1 Y & A samples)
static const uint8_t white_yuva_color[4]