From: Yigithan Yigit <yigithanyigitdevel@gmail.com>
To: ffmpeg-devel@ffmpeg.org
Cc: thilo.borgmann@mail.de, yigithanyigitdevel@gmail.com
Subject: [FFmpeg-devel] [PATCH v5 2/2] avfilter/af_volumedetect.c: Add 32bit float audio support
Date: Mon, 15 Jul 2024 01:38:05 +0300
Message-ID: <20240714223805.9760-3-yigithanyigitdevel@gmail.com> (raw)
In-Reply-To: <20240714223805.9760-1-yigithanyigitdevel@gmail.com>
---
libavfilter/af_volumedetect.c | 222 +++++++++++++++++++++++++---------
1 file changed, 166 insertions(+), 56 deletions(-)
diff --git a/libavfilter/af_volumedetect.c b/libavfilter/af_volumedetect.c
index 327801a7f9..ce68c56962 100644
--- a/libavfilter/af_volumedetect.c
+++ b/libavfilter/af_volumedetect.c
@@ -1,5 +1,6 @@
/*
* Copyright (c) 2012 Nicolas George
+ * Copyright (c) 2024 Yigithan Yigit - 32 Bit Float Audio Support
*
* This file is part of FFmpeg.
*
@@ -20,98 +21,196 @@
#include "libavutil/channel_layout.h"
#include "libavutil/avassert.h"
+#include "libavutil/mem.h"
#include "audio.h"
#include "avfilter.h"
#include "internal.h"
+#define MAX_DB_FLT 1024
#define MAX_DB 91
+#define HISTOGRAM_SIZE 0x10000
+#define HISTOGRAM_SIZE_FLT (MAX_DB_FLT*2)
typedef struct VolDetectContext {
- /**
- * Number of samples at each PCM value.
- * histogram[0x8000 + i] is the number of samples at value i.
- * The extra element is there for symmetry.
- */
- uint64_t histogram[0x10001];
+ uint64_t* histogram; ///< for integer number of samples at each PCM value, for float number of samples at each dB
+ uint64_t nb_samples; ///< number of samples
+ size_t histogram_size; ///< size of the histogram
+ double sum2; ///< sum of the squares of the samples
+ double max; ///< maximum sample value
+ enum AVSampleFormat sample_fmt; ///< sample format
+ void (*process_samples)(struct VolDetectContext *vd, AVFrame *samples);
} VolDetectContext;
-static inline double logdb(uint64_t v)
+static inline double logdb(double v, const int max_db)
{
- double d = v / (double)(0x8000 * 0x8000);
if (!v)
- return MAX_DB;
- return -log10(d) * 10;
+ return max_db;
+
+ return -log10(v) * 10;
+}
+
+#define PROCESS_SAMPLES(name, type, update_func) \
+static void process_samples_##name(VolDetectContext *vd, AVFrame *samples) \
+{ \
+ const type *p = (const type *)samples->extended_data[0]; \
+ const int nb_samples = samples->nb_samples * samples->ch_layout.nb_channels; \
+ int i; \
+ for (i = 0; i < nb_samples; i++) \
+ update_func(vd, p, i); \
}
+#define PROCESS_SAMPLES_PLANAR(name, type, update_func ) \
+static void process_samples_planar_##name(VolDetectContext *vd, AVFrame *samples) \
+{ \
+ const int channels = samples->ch_layout.nb_channels; \
+ const int nb_samples = samples->nb_samples; \
+ int ch, i; \
+ for (ch = 0; ch < channels; ch++) { \
+ const type *p = (const type *)samples->extended_data[ch]; \
+ for (i = 0; i < nb_samples; i++) \
+ update_func(vd, p, i); \
+ } \
+}
+
+#define UPDATE_FLOAT_STATS(vd,p, i ) \
+do { \
+ double sample, power; \
+ int idx; \
+ if(!isfinite(p[i])) \
+ continue; \
+ sample = FFABS(p[i]); \
+ vd->max = FFMAX(vd->max, sample); \
+ power = sample * sample; \
+ vd->sum2 += power; \
+ idx = (int)logdb(power, MAX_DB_FLT) + MAX_DB_FLT; \
+ vd->histogram[idx]++; \
+ vd->nb_samples++; \
+} while(0)
+
+#define UPDATE_INT_STATS(vd, p, i) \
+do { \
+ vd->histogram[p[i] + 0x8000]++; \
+ vd->nb_samples++; \
+} while(0)
+
+PROCESS_SAMPLES(flt, float, UPDATE_FLOAT_STATS)
+PROCESS_SAMPLES(s16, int16_t, UPDATE_INT_STATS)
+
+PROCESS_SAMPLES_PLANAR(flt, float, UPDATE_FLOAT_STATS)
+PROCESS_SAMPLES_PLANAR(s16, int16_t,UPDATE_INT_STATS)
+
static int filter_frame(AVFilterLink *inlink, AVFrame *samples)
{
AVFilterContext *ctx = inlink->dst;
VolDetectContext *vd = ctx->priv;
- int nb_samples = samples->nb_samples;
- int nb_channels = samples->ch_layout.nb_channels;
- int nb_planes = nb_channels;
- int plane, i;
- int16_t *pcm;
-
- if (!av_sample_fmt_is_planar(samples->format)) {
- nb_samples *= nb_channels;
- nb_planes = 1;
- }
- for (plane = 0; plane < nb_planes; plane++) {
- pcm = (int16_t *)samples->extended_data[plane];
- for (i = 0; i < nb_samples; i++)
- vd->histogram[pcm[i] + 0x8000]++;
- }
+
+ vd->process_samples(vd, samples);
return ff_filter_frame(inlink->dst->outputs[0], samples);
}
-static void print_stats(AVFilterContext *ctx)
+static av_cold void print_stats(AVFilterContext *ctx)
{
VolDetectContext *vd = ctx->priv;
int i, max_volume, shift;
uint64_t nb_samples = 0, power = 0, nb_samples_shift = 0, sum = 0;
uint64_t histdb[MAX_DB + 1] = { 0 };
- for (i = 0; i < 0x10000; i++)
+ for (i = 0; i < vd->histogram_size; i++)
nb_samples += vd->histogram[i];
- av_log(ctx, AV_LOG_INFO, "n_samples: %"PRId64"\n", nb_samples);
+
if (!nb_samples)
return;
- /* If nb_samples > 1<<34, there is a risk of overflow in the
- multiplication or the sum: shift all histogram values to avoid that.
- The total number of samples must be recomputed to avoid rounding
- errors. */
- shift = av_log2(nb_samples >> 33);
- for (i = 0; i < 0x10000; i++) {
- nb_samples_shift += vd->histogram[i] >> shift;
- power += (i - 0x8000) * (i - 0x8000) * (vd->histogram[i] >> shift);
+ av_log(ctx, AV_LOG_INFO, "n_samples: %"PRId64"\n", nb_samples);
+ switch(vd->sample_fmt) {
+ case AV_SAMPLE_FMT_FLTP:
+ case AV_SAMPLE_FMT_FLT:
+ av_log(ctx, AV_LOG_INFO, "mean_volume: %.1f dB\n", -logdb(vd->sum2 / vd->nb_samples, MAX_DB_FLT));
+ av_log(ctx, AV_LOG_INFO, "max_volume: %.1f dB\n", -logdb(vd->max * vd->max, MAX_DB_FLT));
+ for (i = 0; i < HISTOGRAM_SIZE_FLT && !vd->histogram[i]; i++);
+ for (; i < HISTOGRAM_SIZE_FLT && sum < vd->nb_samples / 1000; i++) {
+ if (!vd->histogram[i])
+ continue;
+ av_log(ctx, AV_LOG_INFO, "histogram_%ddb: %" PRId64 "\n", MAX_DB_FLT - i, vd->histogram[i]);
+ sum += vd->histogram[i];
+ }
+ break;
+ case AV_SAMPLE_FMT_S16P:
+ case AV_SAMPLE_FMT_S16:
+ /* If nb_samples > 1<<34, there is a risk of overflow in the
+ multiplication or the sum: shift all histogram values to avoid that.
+ The total number of samples must be recomputed to avoid rounding
+ errors. */
+ shift = av_log2(nb_samples >> 33);
+ for (i = 0; i < vd->histogram_size; i++) {
+ nb_samples_shift += vd->histogram[i] >> shift;
+ power += (i - 0x8000) * (i - 0x8000) * (vd->histogram[i] >> shift);
+ }
+ if (!nb_samples_shift)
+ return;
+ power = (power + nb_samples_shift / 2) / nb_samples_shift;
+ av_assert0(power <= 0x8000 * 0x8000);
+ av_log(ctx, AV_LOG_INFO, "mean_volume: %.1f dB\n", -logdb(ldexp((double)power, -av_log2(HISTOGRAM_SIZE >> 1) * 2), MAX_DB));
+ max_volume = 0x8000;
+ while (max_volume > 0 && !vd->histogram[0x8000 + max_volume] &&
+ !vd->histogram[0x8000 - max_volume])
+ max_volume--;
+ av_log(ctx, AV_LOG_INFO, "max_volume: %.1f dB\n", -logdb(ldexp((double)max_volume * max_volume, -av_log2(HISTOGRAM_SIZE >> 1) * 2), MAX_DB));
+ for (i = 0; i < vd->histogram_size; i++)
+ histdb[(int)logdb(ldexp((double)(i - 0x8000) * (i - 0x8000), -av_log2(HISTOGRAM_SIZE >> 1) * 2), MAX_DB)] += vd->histogram[i];
+ for (i = 0; i <= MAX_DB && !histdb[i]; i++);
+ for (; i <= MAX_DB && sum < nb_samples / 1000; i++) {
+ av_log(ctx, AV_LOG_INFO, "histogram_%ddb: %"PRId64"\n", -i, histdb[i]);
+ sum += histdb[i];
+ }
+ break;
}
- if (!nb_samples_shift)
- return;
- power = (power + nb_samples_shift / 2) / nb_samples_shift;
- av_assert0(power <= 0x8000 * 0x8000);
- av_log(ctx, AV_LOG_INFO, "mean_volume: %.1f dB\n", -logdb(power));
-
- max_volume = 0x8000;
- while (max_volume > 0 && !vd->histogram[0x8000 + max_volume] &&
- !vd->histogram[0x8000 - max_volume])
- max_volume--;
- av_log(ctx, AV_LOG_INFO, "max_volume: %.1f dB\n", -logdb(max_volume * max_volume));
-
- for (i = 0; i < 0x10000; i++)
- histdb[(int)logdb((i - 0x8000) * (i - 0x8000))] += vd->histogram[i];
- for (i = 0; i <= MAX_DB && !histdb[i]; i++);
- for (; i <= MAX_DB && sum < nb_samples / 1000; i++) {
- av_log(ctx, AV_LOG_INFO, "histogram_%ddb: %"PRId64"\n", i, histdb[i]);
- sum += histdb[i];
+}
+
+static int config_output(AVFilterLink *outlink)
+{
+ AVFilterContext *ctx = outlink->src;
+ VolDetectContext *vd = ctx->priv;
+
+ switch (outlink->format) {
+ case AV_SAMPLE_FMT_S16P:
+ case AV_SAMPLE_FMT_S16:
+ /*
+ * Number of samples at each PCM value.
+ * Only used for integer formats.
+ * For 16 bit signed PCM there are 65536.
+ * histogram[0x8000 + i] is the number of samples at value i.
+ * The extra element is there for symmetry.
+ */
+ vd->histogram_size = HISTOGRAM_SIZE + 1;
+ vd->process_samples = av_sample_fmt_is_planar(outlink->format)
+ ? process_samples_planar_s16 : process_samples_s16;
+ break;
+ case AV_SAMPLE_FMT_FLT:
+ case AV_SAMPLE_FMT_FLTP:
+ /*
+ * The histogram is used to store the number of samples at each dB
+ * instead of the number of samples at each PCM value.
+ */
+ vd->histogram_size = HISTOGRAM_SIZE_FLT + 1;
+ vd->process_samples = av_sample_fmt_is_planar(outlink->format)
+ ? process_samples_planar_flt : process_samples_flt;
+ break;
}
+ vd->sample_fmt = outlink->format;
+ vd->histogram = av_calloc(vd->histogram_size, sizeof(uint64_t));
+ if (!vd->histogram)
+ return AVERROR(ENOMEM);
+ return 0;
}
static av_cold void uninit(AVFilterContext *ctx)
{
+ VolDetectContext *vd = ctx->priv;
print_stats(ctx);
+ if (vd->histogram)
+ av_freep(&vd->histogram);
}
static const AVFilterPad volumedetect_inputs[] = {
@@ -122,6 +221,14 @@ static const AVFilterPad volumedetect_inputs[] = {
},
};
+static const AVFilterPad volumedetect_outputs[] = {
+ {
+ .name = "default",
+ .type = AVMEDIA_TYPE_AUDIO,
+ .config_props = config_output,
+ },
+};
+
const AVFilter ff_af_volumedetect = {
.name = "volumedetect",
.description = NULL_IF_CONFIG_SMALL("Detect audio volume."),
@@ -129,6 +236,9 @@ const AVFilter ff_af_volumedetect = {
.uninit = uninit,
.flags = AVFILTER_FLAG_METADATA_ONLY,
FILTER_INPUTS(volumedetect_inputs),
- FILTER_OUTPUTS(ff_audio_default_filterpad),
- FILTER_SAMPLEFMTS(AV_SAMPLE_FMT_S16, AV_SAMPLE_FMT_S16P),
+ FILTER_OUTPUTS(volumedetect_outputs),
+ FILTER_SAMPLEFMTS(AV_SAMPLE_FMT_S16,
+ AV_SAMPLE_FMT_S16P,
+ AV_SAMPLE_FMT_FLT,
+ AV_SAMPLE_FMT_FLTP),
};
--
2.45.2
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
next prev parent reply other threads:[~2024-07-14 22:38 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-07-14 22:38 [FFmpeg-devel] [PATCH v5 0/2] " Yigithan Yigit
2024-07-14 22:38 ` [FFmpeg-devel] [PATCH v5 1/2] avfilter/af_volumedetect.c: Move logdb function Yigithan Yigit
2024-07-14 22:38 ` Yigithan Yigit [this message]
2024-07-21 22:49 ` [FFmpeg-devel] [PATCH v5 2/2] avfilter/af_volumedetect.c: Add 32bit float audio support Yigithan Yigit
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240714223805.9760-3-yigithanyigitdevel@gmail.com \
--to=yigithanyigitdevel@gmail.com \
--cc=ffmpeg-devel@ffmpeg.org \
--cc=thilo.borgmann@mail.de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Git Inbox Mirror of the ffmpeg-devel mailing list - see https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
This inbox may be cloned and mirrored by anyone:
git clone --mirror https://master.gitmailbox.com/ffmpegdev/0 ffmpegdev/git/0.git
# If you have public-inbox 1.1+ installed, you may
# initialize and index your mirror using the following commands:
public-inbox-init -V2 ffmpegdev ffmpegdev/ https://master.gitmailbox.com/ffmpegdev \
ffmpegdev@gitmailbox.com
public-inbox-index ffmpegdev
Example config snippet for mirrors.
AGPL code for this site: git clone https://public-inbox.org/public-inbox.git