FFmpeg
af_stereowiden.c
Go to the documentation of this file.
1 /*
2  * Copyright (C) 2012 VLC authors and VideoLAN
3  * Author : Sukrit Sangwan < sukritsangwan at gmail dot com >
4  *
5  * This file is part of FFmpeg.
6  *
7  * FFmpeg is free software; you can redistribute it and/or
8  * modify it under the terms of the GNU Lesser General Public
9  * License as published by the Free Software Foundation; either
10  * version 2.1 of the License, or (at your option) any later version.
11  *
12  * FFmpeg is distributed in the hope that it will be useful,
13  * but WITHOUT ANY WARRANTY; without even the implied warranty of
14  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
15  * Lesser General Public License for more details.
16  *
17  * You should have received a copy of the GNU Lesser General Public
18  * License along with FFmpeg; if not, write to the Free Software
19  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
20  */
21 
23 #include "libavutil/mem.h"
24 #include "libavutil/opt.h"
25 #include "avfilter.h"
26 #include "audio.h"
27 #include "filters.h"
28 #include "formats.h"
29 
30 typedef struct StereoWidenContext {
31  const AVClass *class;
32 
33  float delay;
34  float feedback;
35  float crossfeed;
36  float drymix;
37 
38  float *buffer;
39  float *cur;
40  int length;
42 
43 #define OFFSET(x) offsetof(StereoWidenContext, x)
44 #define A AV_OPT_FLAG_AUDIO_PARAM|AV_OPT_FLAG_FILTERING_PARAM
45 #define AT AV_OPT_FLAG_AUDIO_PARAM|AV_OPT_FLAG_FILTERING_PARAM|AV_OPT_FLAG_RUNTIME_PARAM
46 
47 static const AVOption stereowiden_options[] = {
48  { "delay", "set delay time", OFFSET(delay), AV_OPT_TYPE_FLOAT, {.dbl=20}, 1, 100, A },
49  { "feedback", "set feedback gain", OFFSET(feedback), AV_OPT_TYPE_FLOAT, {.dbl=.3}, 0, 0.9, AT },
50  { "crossfeed", "set cross feed", OFFSET(crossfeed), AV_OPT_TYPE_FLOAT, {.dbl=.3}, 0, 0.8, AT },
51  { "drymix", "set dry-mix", OFFSET(drymix), AV_OPT_TYPE_FLOAT, {.dbl=.8}, 0, 1.0, AT },
52  { NULL }
53 };
54 
55 AVFILTER_DEFINE_CLASS(stereowiden);
56 
57 static int query_formats(const AVFilterContext *ctx,
58  AVFilterFormatsConfig **cfg_in,
59  AVFilterFormatsConfig **cfg_out)
60 {
61  static const enum AVSampleFormat formats[] = {
64  };
65  static const AVChannelLayout layouts[] = {
67  { .nb_channels = 0 },
68  };
69 
70  int ret;
71 
72  ret = ff_set_common_formats_from_list2(ctx, cfg_in, cfg_out, formats);
73  if (ret < 0)
74  return ret;
75 
77  if (ret < 0)
78  return ret;
79 
80  return 0;
81 }
82 
84 {
85  AVFilterContext *ctx = inlink->dst;
86  StereoWidenContext *s = ctx->priv;
87 
88  s->length = lrintf(s->delay * inlink->sample_rate / 1000);
89  s->length *= 2;
90  if (s->length == 0)
91  return AVERROR(EINVAL);
92  s->buffer = av_calloc(s->length, sizeof(*s->buffer));
93  if (!s->buffer)
94  return AVERROR(ENOMEM);
95  s->cur = s->buffer;
96 
97  return 0;
98 }
99 
101 {
102  AVFilterContext *ctx = inlink->dst;
103  AVFilterLink *outlink = ctx->outputs[0];
104  StereoWidenContext *s = ctx->priv;
105  const float *src = (const float *)in->data[0];
106  const float drymix = s->drymix;
107  const float crossfeed = s->crossfeed;
108  const float feedback = s->feedback;
109  AVFrame *out;
110  float *dst;
111  int n;
112 
113  if (av_frame_is_writable(in)) {
114  out = in;
115  } else {
116  out = ff_get_audio_buffer(outlink, in->nb_samples);
117  if (!out) {
118  av_frame_free(&in);
119  return AVERROR(ENOMEM);
120  }
122  }
123  dst = (float *)out->data[0];
124 
125  for (n = 0; n < in->nb_samples; n++, src += 2, dst += 2, s->cur += 2) {
126  const float left = src[0], right = src[1];
127 
128  if (s->cur == s->buffer + s->length)
129  s->cur = s->buffer;
130 
131  if (ctx->is_disabled) {
132  dst[0] = left;
133  dst[1] = right;
134  } else {
135  dst[0] = drymix * left - crossfeed * right - feedback * s->cur[1];
136  dst[1] = drymix * right - crossfeed * left - feedback * s->cur[0];
137  }
138 
139  s->cur[0] = left;
140  s->cur[1] = right;
141  }
142 
143  if (out != in)
144  av_frame_free(&in);
145  return ff_filter_frame(outlink, out);
146 }
147 
149 {
150  StereoWidenContext *s = ctx->priv;
151 
152  av_freep(&s->buffer);
153 }
154 
155 static const AVFilterPad inputs[] = {
156  {
157  .name = "default",
158  .type = AVMEDIA_TYPE_AUDIO,
159  .filter_frame = filter_frame,
160  .config_props = config_input,
161  },
162 };
163 
165  .name = "stereowiden",
166  .description = NULL_IF_CONFIG_SMALL("Apply stereo widening effect."),
167  .priv_size = sizeof(StereoWidenContext),
168  .priv_class = &stereowiden_class,
169  .uninit = uninit,
174  .process_command = ff_filter_process_command,
175 };
formats
formats
Definition: signature.h:47
ff_get_audio_buffer
AVFrame * ff_get_audio_buffer(AVFilterLink *link, int nb_samples)
Request an audio samples buffer with a specific set of permissions.
Definition: audio.c:98
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
query_formats
static int query_formats(const AVFilterContext *ctx, AVFilterFormatsConfig **cfg_in, AVFilterFormatsConfig **cfg_out)
Definition: af_stereowiden.c:57
out
FILE * out
Definition: movenc.c:55
AV_CHANNEL_LAYOUT_STEREO
#define AV_CHANNEL_LAYOUT_STEREO
Definition: channel_layout.h:387
uninit
static av_cold void uninit(AVFilterContext *ctx)
Definition: af_stereowiden.c:148
A
#define A
Definition: af_stereowiden.c:44
ff_filter_frame
int ff_filter_frame(AVFilterLink *link, AVFrame *frame)
Send a frame of data to the next filter.
Definition: avfilter.c:1062
layouts
enum MovChannelLayoutTag * layouts
Definition: mov_chan.c:335
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_frame_free
void av_frame_free(AVFrame **frame)
Free the frame and any dynamically allocated objects in it, e.g.
Definition: frame.c:162
inputs
static const AVFilterPad inputs[]
Definition: af_stereowiden.c:155
FILTER_INPUTS
#define FILTER_INPUTS(array)
Definition: filters.h:262
AVFrame
This structure describes decoded (raw) audio or video data.
Definition: frame.h:389
AVOption
AVOption.
Definition: opt.h:429
ff_set_common_channel_layouts_from_list2
int ff_set_common_channel_layouts_from_list2(const AVFilterContext *ctx, AVFilterFormatsConfig **cfg_in, AVFilterFormatsConfig **cfg_out, const AVChannelLayout *fmts)
Definition: formats.c:920
AVFilter::name
const char * name
Filter name.
Definition: avfilter.h:205
AVFrame::data
uint8_t * data[AV_NUM_DATA_POINTERS]
pointer to the picture/channel planes.
Definition: frame.h:410
formats.h
StereoWidenContext::feedback
float feedback
Definition: af_stereowiden.c:34
AVFilterPad
A filter pad used for either input or output.
Definition: filters.h:38
StereoWidenContext
Definition: af_stereowiden.c:30
av_cold
#define av_cold
Definition: attributes.h:90
AVFILTER_DEFINE_CLASS
AVFILTER_DEFINE_CLASS(stereowiden)
ff_af_stereowiden
const AVFilter ff_af_stereowiden
Definition: af_stereowiden.c:164
s
#define s(width, name)
Definition: cbs_vp9.c:198
AVMEDIA_TYPE_AUDIO
@ AVMEDIA_TYPE_AUDIO
Definition: avutil.h:202
filters.h
StereoWidenContext::buffer
float * buffer
Definition: af_stereowiden.c:38
ctx
AVFormatContext * ctx
Definition: movenc.c:49
FILTER_OUTPUTS
#define FILTER_OUTPUTS(array)
Definition: filters.h:263
filter_frame
static int filter_frame(AVFilterLink *inlink, AVFrame *in)
Definition: af_stereowiden.c:100
if
if(ret)
Definition: filter_design.txt:179
AVClass
Describe the class of an AVClass context structure.
Definition: log.h:75
NULL
#define NULL
Definition: coverity.c:32
av_frame_copy_props
int av_frame_copy_props(AVFrame *dst, const AVFrame *src)
Copy only "metadata" fields from src to dst.
Definition: frame.c:713
StereoWidenContext::drymix
float drymix
Definition: af_stereowiden.c:36
StereoWidenContext::delay
float delay
Definition: af_stereowiden.c:33
ff_audio_default_filterpad
const AVFilterPad ff_audio_default_filterpad[1]
An AVFilterPad array whose only entry has name "default" and is of type AVMEDIA_TYPE_AUDIO.
Definition: audio.c:34
AVFilterFormatsConfig
Lists of formats / etc.
Definition: avfilter.h:111
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:94
AVChannelLayout
An AVChannelLayout holds information about the channel layout of audio data.
Definition: channel_layout.h:311
dst
uint8_t ptrdiff_t const uint8_t ptrdiff_t int intptr_t intptr_t int int16_t * dst
Definition: dsp.h:83
for
for(k=2;k<=8;++k)
Definition: h264pred_template.c:425
AV_SAMPLE_FMT_NONE
@ AV_SAMPLE_FMT_NONE
Definition: samplefmt.h:56
av_frame_is_writable
int av_frame_is_writable(AVFrame *frame)
Check if the frame data is writable.
Definition: frame.c:649
ff_filter_process_command
int ff_filter_process_command(AVFilterContext *ctx, const char *cmd, const char *arg, char *res, int res_len, int flags)
Generic processing of user supplied commands that are set in the same way as the filter options.
Definition: avfilter.c:901
StereoWidenContext::length
int length
Definition: af_stereowiden.c:40
AV_OPT_TYPE_FLOAT
@ AV_OPT_TYPE_FLOAT
Underlying C type is float.
Definition: opt.h:271
AT
#define AT
Definition: af_stereowiden.c:45
AVFrame::nb_samples
int nb_samples
number of audio samples (per channel) described by this frame
Definition: frame.h:469
lrintf
#define lrintf(x)
Definition: libm_mips.h:72
AVSampleFormat
AVSampleFormat
Audio sample formats.
Definition: samplefmt.h:55
FILTER_QUERY_FUNC2
#define FILTER_QUERY_FUNC2(func)
Definition: filters.h:239
AVFilterPad::name
const char * name
Pad name.
Definition: filters.h:44
av_calloc
void * av_calloc(size_t nmemb, size_t size)
Definition: mem.c:264
AVFilter
Filter definition.
Definition: avfilter.h:201
ret
ret
Definition: filter_design.txt:187
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
ff_set_common_formats_from_list2
int ff_set_common_formats_from_list2(const AVFilterContext *ctx, AVFilterFormatsConfig **cfg_in, AVFilterFormatsConfig **cfg_out, const int *fmts)
Definition: formats.c:1016
channel_layout.h
avfilter.h
StereoWidenContext::cur
float * cur
Definition: af_stereowiden.c:39
AVFilterContext
An instance of a filter.
Definition: avfilter.h:457
mem.h
audio.h
av_freep
#define av_freep(p)
Definition: tableprint_vlc.h:34
OFFSET
#define OFFSET(x)
Definition: af_stereowiden.c:43
AVFILTER_FLAG_SUPPORT_TIMELINE_INTERNAL
#define AVFILTER_FLAG_SUPPORT_TIMELINE_INTERNAL
Same as AVFILTER_FLAG_SUPPORT_TIMELINE_GENERIC, except that the filter will have its filter_frame() c...
Definition: avfilter.h:190
AV_SAMPLE_FMT_FLT
@ AV_SAMPLE_FMT_FLT
float
Definition: samplefmt.h:60
StereoWidenContext::crossfeed
float crossfeed
Definition: af_stereowiden.c:35
config_input
static int config_input(AVFilterLink *inlink)
Definition: af_stereowiden.c:83
src
#define src
Definition: vp8dsp.c:248
stereowiden_options
static const AVOption stereowiden_options[]
Definition: af_stereowiden.c:47