[FFmpeg-devel] [PATCH] lavfi: avectorscope filter
Stefano Sabatini
stefasab at gmail.com
Fri May 10 12:42:21 CEST 2013
On date Monday 2013-04-29 13:17:58 +0000, Paul B Mahol encoded:
> Signed-off-by: Paul B Mahol <onemda at gmail.com>
> ---
> doc/filters.texi | 44 +++++++
> libavfilter/Makefile | 1 +
> libavfilter/allfilters.c | 1 +
> libavfilter/avf_avectorscope.c | 262 +++++++++++++++++++++++++++++++++++++++++
> 4 files changed, 308 insertions(+)
> create mode 100644 libavfilter/avf_avectorscope.c
>
> diff --git a/doc/filters.texi b/doc/filters.texi
> index a1d5581..8f030a3 100644
> --- a/doc/filters.texi
> +++ b/doc/filters.texi
> @@ -7142,6 +7142,50 @@ tools.
>
> Below is a description of the currently available multimedia filters.
>
> + at section avectorscope
> +
> +Convert input audio to a video output, representing the audio vector
> +scope.
> +
> +The filter is used to measure the difference between channels of stereo
> +audio stream. A monoaural signal, consisting of identical left and right
> +signal, results in straight vertical line. Any stereo separation is visible
> +as a deviation from this line, creating a Lissajous figure.
> +If the straight (or deviation from it) but horizontal line appears this
> +indicates that the left and right channels are out of phase.
> +
> +The filter accepts the following options:
> +
> + at table @option
> + at item mode, m
> +Set the vectorscope mode. Default value is @code{lissajous}.
> +
> +Available values are:
> + at table @samp
> + at item lissajous
> +Lissajous rotated by 45 degrees.
> +
> + at item lissajous_xy
> +Same as above but not rotated.
> + at end table
> +
> + at item size, s
> +Set the video size for the output. Default value is @code{320x240}.
> +
> + at item rate, r
> +Set the output frame rate. Default value is @code{25}.
> +
> + at item rc
> + at item gc
> + at item bc
> +Specify the red, green and blue contrast.
> +
> + at item rf
> + at item gf
> + at item bf
> +Specify the red, green and blue fade.
> + at end table
> +
> @section concat
>
> Concatenate audio and video streams, joining them together one after the
> diff --git a/libavfilter/Makefile b/libavfilter/Makefile
> index 6f41d71..9f1f96b 100644
> --- a/libavfilter/Makefile
> +++ b/libavfilter/Makefile
> @@ -220,6 +220,7 @@ OBJS-$(CONFIG_MP_FILTER) += libmpcodecs/vf_uspp.o
> OBJS-$(CONFIG_MP_FILTER) += libmpcodecs/pullup.o
>
> # multimedia filters
> +OBJS-$(CONFIG_AVECTORSCOPE_FILTER) += avf_avectorscope.o
> OBJS-$(CONFIG_CONCAT_FILTER) += avf_concat.o
> OBJS-$(CONFIG_SHOWSPECTRUM_FILTER) += avf_showspectrum.o
> OBJS-$(CONFIG_SHOWWAVES_FILTER) += avf_showwaves.o
> diff --git a/libavfilter/allfilters.c b/libavfilter/allfilters.c
> index 97e558b..53e54aa 100644
> --- a/libavfilter/allfilters.c
> +++ b/libavfilter/allfilters.c
> @@ -196,6 +196,7 @@ void avfilter_register_all(void)
> REGISTER_FILTER(NULLSINK, nullsink, vsink);
>
> /* multimedia filters */
> + REGISTER_FILTER(AVECTORSCOPE, avectorscope, avf);
> REGISTER_FILTER(CONCAT, concat, avf);
> REGISTER_FILTER(SHOWSPECTRUM, showspectrum, avf);
> REGISTER_FILTER(SHOWWAVES, showwaves, avf);
> diff --git a/libavfilter/avf_avectorscope.c b/libavfilter/avf_avectorscope.c
> new file mode 100644
> index 0000000..a99a09c
> --- /dev/null
> +++ b/libavfilter/avf_avectorscope.c
> @@ -0,0 +1,262 @@
> +/*
> + * Copyright (c) 2013 Paul B Mahol
> + *
> + * This file is part of FFmpeg.
> + *
> + * FFmpeg is free software; you can redistribute it and/or
> + * modify it under the terms of the GNU Lesser General Public
> + * License as published by the Free Software Foundation; either
> + * version 2.1 of the License, or (at your option) any later version.
> + *
> + * FFmpeg is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
> + * Lesser General Public License for more details.
> + *
> + * You should have received a copy of the GNU Lesser General Public
> + * License along with FFmpeg; if not, write to the Free Software
> + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
> + */
> +
> +/**
> + * @file
> + * audio to video multimedia vector scope filter
> + */
> +
> +#include "libavutil/avassert.h"
> +#include "libavutil/channel_layout.h"
> +#include "libavutil/opt.h"
> +#include "libavutil/parseutils.h"
> +#include "avfilter.h"
> +#include "formats.h"
> +#include "audio.h"
> +#include "video.h"
> +#include "internal.h"
> +
> +enum VectorScopeMode {
> + LISSAJOUS,
> + LISSAJOUS_XY,
> + MODE_NB,
> +};
> +
> +typedef struct AudioVectorScopeContext {
> + const AVClass *class;
> + AVFrame *outpicref;
> + int w, h;
> + int hw, hh;
> + enum VectorScopeMode mode;
> + int contrast[3];
> + int fade[3];
> + AVRational frame_rate;
> +} AudioVectorScopeContext;
> +
> +#define OFFSET(x) offsetof(AudioVectorScopeContext, x)
> +#define FLAGS AV_OPT_FLAG_FILTERING_PARAM|AV_OPT_FLAG_VIDEO_PARAM
> +
> +static const AVOption avectorscope_options[] = {
> + { "mode", "set mode", OFFSET(mode), AV_OPT_TYPE_INT, {.i64=LISSAJOUS}, 0, MODE_NB-1, FLAGS, "mode" },
> + { "m", "set mode", OFFSET(mode), AV_OPT_TYPE_INT, {.i64=LISSAJOUS}, 0, MODE_NB-1, FLAGS, "mode" },
> + { "lissajous", "", 0, AV_OPT_TYPE_CONST, {.i64=LISSAJOUS}, 0, 0, FLAGS, "mode" },
> + { "lissajous_xy", "", 0, AV_OPT_TYPE_CONST, {.i64=LISSAJOUS_XY}, 0, 0, FLAGS, "mode" },
> + { "rate", "set video rate", OFFSET(frame_rate), AV_OPT_TYPE_VIDEO_RATE, {.str="25"}, 0, 0, FLAGS },
> + { "r", "set video rate", OFFSET(frame_rate), AV_OPT_TYPE_VIDEO_RATE, {.str="25"}, 0, 0, FLAGS },
> + { "size", "set video size", OFFSET(w), AV_OPT_TYPE_IMAGE_SIZE, {.str="320x240"}, 0, 0, FLAGS },
> + { "s", "set video size", OFFSET(w), AV_OPT_TYPE_IMAGE_SIZE, {.str="320x240"}, 0, 0, FLAGS },
> + { "rc", "set red contrast", OFFSET(contrast[0]), AV_OPT_TYPE_INT, {.i64=40}, 1, 255, FLAGS },
> + { "gc", "set green contrast", OFFSET(contrast[1]), AV_OPT_TYPE_INT, {.i64=160}, 1, 255, FLAGS },
> + { "bc", "set blue contrast", OFFSET(contrast[2]), AV_OPT_TYPE_INT, {.i64=80}, 1, 255, FLAGS },
> + { "rf", "set red fade", OFFSET(fade[0]), AV_OPT_TYPE_INT, {.i64=15}, 0, 255, FLAGS },
> + { "gf", "set green fade", OFFSET(fade[1]), AV_OPT_TYPE_INT, {.i64=10}, 0, 255, FLAGS },
> + { "bf", "set blue fade", OFFSET(fade[2]), AV_OPT_TYPE_INT, {.i64=5}, 0, 255, FLAGS },
> + {NULL},
> +};
> +
> +AVFILTER_DEFINE_CLASS(avectorscope);
> +
> +static void draw_dot(AudioVectorScopeContext *p, unsigned x, unsigned y)
> +{
> + const int linesize = p->outpicref->linesize[0];
> + uint8_t *dst;
> +
> + y = FFMIN(y, p->h - 1);
> + x = FFMIN(x, p->w - 1);
> +
> + dst = &p->outpicref->data[0][y * linesize + x * 4];
> + dst[0] = FFMIN(dst[0] + p->contrast[0], 255);
> + dst[1] = FFMIN(dst[1] + p->contrast[1], 255);
> + dst[2] = FFMIN(dst[2] + p->contrast[2], 255);
> +}
> +
> +static void fade(AudioVectorScopeContext *p)
> +{
> + const int linesize = p->outpicref->linesize[0];
> + int i, j;
> +
> + if (p->fade[0] || p->fade[1] || p->fade[2]) {
> + uint8_t *d = p->outpicref->data[0];
> + for (i = 0; i < p->h; i++) {
> + for (j = 0; j < p->w*4; j+=4) {
> + d[j+0] = FFMAX(d[j+0] - p->fade[0], 0);
> + d[j+1] = FFMAX(d[j+1] - p->fade[1], 0);
> + d[j+2] = FFMAX(d[j+2] - p->fade[2], 0);
> + }
> + d += linesize;
> + }
> + }
> +
> +}
> +
> +static av_cold void uninit(AVFilterContext *ctx)
> +{
> + AudioVectorScopeContext *p = ctx->priv;
> +
> + av_frame_free(&p->outpicref);
> +}
> +
> +static int query_formats(AVFilterContext *ctx)
> +{
> + AVFilterFormats *formats = NULL;
> + AVFilterChannelLayouts *layout = NULL;
> + AVFilterLink *inlink = ctx->inputs[0];
> + AVFilterLink *outlink = ctx->outputs[0];
> + static const enum AVSampleFormat sample_fmts[] = { AV_SAMPLE_FMT_S16, AV_SAMPLE_FMT_FLT, AV_SAMPLE_FMT_NONE };
> + static const enum AVPixelFormat pix_fmts[] = { AV_PIX_FMT_RGBA, AV_PIX_FMT_NONE };
> +
> + formats = ff_make_format_list(sample_fmts);
> + if (!formats)
> + return AVERROR(ENOMEM);
> + ff_formats_ref(formats, &inlink->out_formats);
> +
> + ff_add_channel_layout(&layout, AV_CH_LAYOUT_STEREO);
> + ff_channel_layouts_ref(layout, &inlink->out_channel_layouts);
> +
> + formats = ff_all_samplerates();
> + if (!formats)
> + return AVERROR(ENOMEM);
> + ff_formats_ref(formats, &inlink->out_samplerates);
> +
> + formats = ff_make_format_list(pix_fmts);
> + if (!formats)
> + return AVERROR(ENOMEM);
> + ff_formats_ref(formats, &outlink->in_formats);
> +
> + return 0;
> +}
> +
> +static int config_input(AVFilterLink *inlink)
> +{
> + AVFilterContext *ctx = inlink->dst;
> + AudioVectorScopeContext *p = ctx->priv;
> + int nb_samples;
> +
> + nb_samples = FFMAX(1024, ((double)inlink->sample_rate / av_q2d(p->frame_rate)) + 0.5);
> + inlink->partial_buf_size =
> + inlink->min_samples =
> + inlink->max_samples = nb_samples;
> +
> + return 0;
> +}
> +
> +static int config_output(AVFilterLink *outlink)
> +{
> + AudioVectorScopeContext *p = outlink->src->priv;
> + int size;
> +
> + outlink->w = p->w;
> + outlink->h = p->h;
> + outlink->sample_aspect_ratio = (AVRational){1,1};
> + outlink->frame_rate = p->frame_rate;
> + p->outpicref = ff_get_video_buffer(outlink, outlink->w, outlink->h);
> + if (!p->outpicref)
> + return AVERROR(ENOMEM);
This is potentially unsafe, since at this stage we are not sure that
the filtergraph is already configured. Possibly safer: you ask the
buffer lazily when you need it.
How do we tackle this in other filters?
> + size = outlink->h * p->outpicref->linesize[0];
> + memset(p->outpicref->data[0] + size, 0, FFABS(size));
> +
> + p->hw = p->w / 2;
> + p->hh = p->h / 2;
> +
> + return 0;
> +}
> +
> +static int filter_frame(AVFilterLink *inlink, AVFrame *insamples)
> +{
> + AVFilterContext *ctx = inlink->dst;
> + AVFilterLink *outlink = ctx->outputs[0];
> + AudioVectorScopeContext *p = ctx->priv;
> +
> + p->outpicref->pts = insamples->pts;
> +
> + const int hw = p->hw;
> + const int hh = p->hh;
> + unsigned x, y;
> + int i;
> +
> + fade(p);
> +
> + switch (insamples->format) {
> + case AV_SAMPLE_FMT_S16:
> + for (i = 0; i < insamples->nb_samples; i++) {
> + int16_t *src = (int16_t *)insamples->data[0] + i * 2;
> +
> + if (p->mode == LISSAJOUS) {
> + x = ((src[1] - src[0]) / (float)(UINT16_MAX) + 1) * hw;
> + y = (1.0 - (src[0] + src[1]) / (float)UINT16_MAX) * hh;
what's +1 good for?
> + } else {
> + x = (src[1] / (float)INT16_MAX + 1) * hw;
> + y = (src[0] / (float)INT16_MAX + 1) * hh;
> + }
> +
> + draw_dot(p, x, y);
> + }
> + break;
> + case AV_SAMPLE_FMT_FLT:
> + for (i = 0; i < insamples->nb_samples; i++) {
> + float *src = (float *)insamples->data[0] + i * 2;
> +
> + if (p->mode == LISSAJOUS) {
> + x = ((src[1] - src[0]) / 2 + 1) * hw;
> + y = (1.0 - (src[0] + src[1]) / 2) * hh;
> + } else {
> + x = (src[1] + 1) * hw;
> + y = (src[0] + 1) * hh;
> + }
> +
> + draw_dot(p, x, y);
> + }
> + break;
> + }
> +
> + av_frame_free(&insamples);
> +
> + return ff_filter_frame(outlink, av_frame_clone(p->outpicref));
> +}
> +
LGTM otherwise and very nice work.
--
FFmpeg = Faithless Formidable Majestic Portable Explosive Gymnast
More information about the ffmpeg-devel
mailing list