FFmpeg
vf_readvitc.c
Go to the documentation of this file.
1 /*
2  * Copyright (c) 2016 Tobias Rapp
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 /**
22  * @file
23  * Filter for reading the vertical interval timecode (VITC).
24  * See also https://en.wikipedia.org/wiki/Vertical_interval_timecode
25  */
26 
27 #include "libavutil/common.h"
28 #include "libavutil/internal.h"
29 #include "libavutil/opt.h"
30 #include "libavutil/timecode.h"
31 #include "avfilter.h"
32 #include "filters.h"
33 #include "video.h"
34 
35 #define LINE_DATA_SIZE 9
36 
37 typedef struct ReadVitcContext {
38  const AVClass *class;
39 
40  int scan_max;
41  double thr_b;
42  double thr_w;
43 
47  int grp_width;
51 
52 #define OFFSET(x) offsetof(ReadVitcContext, x)
53 #define FLAGS AV_OPT_FLAG_VIDEO_PARAM|AV_OPT_FLAG_FILTERING_PARAM
54 
55 static const AVOption readvitc_options[] = {
56  { "scan_max", "maximum line numbers to scan for VITC data", OFFSET(scan_max), AV_OPT_TYPE_INT, {.i64 = 45 }, -1, INT_MAX, FLAGS },
57  { "thr_b", "black color threshold", OFFSET(thr_b), AV_OPT_TYPE_DOUBLE, {.dbl = 0.2 }, 0, 1.0, FLAGS },
58  { "thr_w", "white color threshold", OFFSET(thr_w), AV_OPT_TYPE_DOUBLE, {.dbl = 0.6 }, 0, 1.0, FLAGS },
59  { NULL }
60 };
61 
62 AVFILTER_DEFINE_CLASS(readvitc);
63 
64 static uint8_t get_vitc_crc( uint8_t *line ) {
65  uint8_t crc;
66 
67  crc = 0x01 | (line[0] << 2);
68  crc ^= (line[0] >> 6) | 0x04 | (line[1] << 4);
69  crc ^= (line[1] >> 4) | 0x10 | (line[2] << 6);
70  crc ^= (line[2] >> 2) | 0x40;
71  crc ^= line[3];
72  crc ^= 0x01 | (line[4] << 2);
73  crc ^= (line[4] >> 6) | 0x04 | (line[5] << 4);
74  crc ^= (line[5] >> 4) | 0x10 | (line[6] << 6);
75  crc ^= (line[6] >> 2) | 0x40;
76  crc ^= line[7];
77  crc ^= 0x01;
78  crc = (crc >> 2) | (crc << 6); // rotate byte right by two bits
79  return crc;
80 }
81 
82 static inline uint8_t get_pit_avg3( uint8_t *line, int i ) {
83  return ((line[i-1] + line[i] + line[i+1]) / 3);
84 }
85 
86 static int read_vitc_line( ReadVitcContext *ctx, uint8_t *src, int line_size, int width, int height )
87 {
88  uint8_t *scan_line;
89  int grp_index, pit_index;
90  int grp_start_pos;
91  uint8_t pit_value;
92  int x, y, res = 0;
93 
94  if (ctx->scan_max >= 0)
95  height = FFMIN(height, ctx->scan_max);
96 
97  // scan lines for VITC data, starting from the top
98  for (y = 0; y < height; y++) {
99  scan_line = src;
100  memset(ctx->line_data, 0, LINE_DATA_SIZE);
101  grp_index = 0;
102  x = 0;
103  while ((x < width) && (grp_index < 9)) {
104  // search next sync pattern
105  while ((x < width) && (scan_line[x] < ctx->threshold_white))
106  x++;
107  while ((x < width) && (scan_line[x] > ctx->threshold_black))
108  x++;
109  x = FFMAX(x - ((ctx->grp_width+10) / 20), 1); // step back a half pit
110  grp_start_pos = x;
111  if ((grp_start_pos + ctx->grp_width) > width)
112  break; // not enough pixels for reading a whole pit group
113  pit_value = get_pit_avg3(scan_line, x);
114  if (pit_value < ctx->threshold_white)
115  break; // first sync bit mismatch
116  x = grp_start_pos + ((ctx->grp_width) / 10);
117  pit_value = get_pit_avg3(scan_line, x);
118  if (pit_value > ctx->threshold_black )
119  break; // second sync bit mismatch
120  for (pit_index = 0; pit_index <= 7; pit_index++) {
121  x = grp_start_pos + (((pit_index+2)*ctx->grp_width) / 10);
122  pit_value = get_pit_avg3(scan_line, x);
123  if (pit_value > ctx->threshold_gray)
124  ctx->line_data[grp_index] |= (1 << pit_index);
125  }
126  grp_index++;
127  }
128  if ((grp_index == 9) && (get_vitc_crc(ctx->line_data) == ctx->line_data[8])) {
129  res = 1;
130  break;
131  }
132  src += line_size;
133  }
134 
135  return res;
136 }
137 
138 static unsigned bcd2uint(uint8_t high, uint8_t low)
139 {
140  if (high > 9 || low > 9)
141  return 0;
142  return 10*high + low;
143 }
144 
145 static char *make_vitc_tc_string(char *buf, uint8_t *line)
146 {
147  unsigned hh = bcd2uint(line[7] & 0x03, line[6] & 0x0f); // 6-bit hours
148  unsigned mm = bcd2uint(line[5] & 0x07, line[4] & 0x0f); // 7-bit minutes
149  unsigned ss = bcd2uint(line[3] & 0x07, line[2] & 0x0f); // 7-bit seconds
150  unsigned ff = bcd2uint(line[1] & 0x03, line[0] & 0x0f); // 6-bit frames
151  unsigned drop = (line[1] & 0x04); // 1-bit drop flag
152  snprintf(buf, AV_TIMECODE_STR_SIZE, "%02u:%02u:%02u%c%02u",
153  hh, mm, ss, drop ? ';' : ':', ff);
154  return buf;
155 }
156 
158 {
159  ReadVitcContext *s = ctx->priv;
160 
161  s->threshold_black = s->thr_b * UINT8_MAX;
162  s->threshold_white = s->thr_w * UINT8_MAX;
163  if (s->threshold_black > s->threshold_white) {
164  av_log(ctx, AV_LOG_WARNING, "Black color threshold is higher than white color threshold (%g > %g)\n",
165  s->thr_b, s->thr_w);
166  return AVERROR(EINVAL);
167  }
168  s->threshold_gray = s->threshold_white - ((s->threshold_white - s->threshold_black) / 2);
169  av_log(ctx, AV_LOG_DEBUG, "threshold_black:%d threshold_white:%d threshold_gray:%d\n",
170  s->threshold_black, s->threshold_white, s->threshold_gray);
171 
172  return 0;
173 }
174 
176 {
177  AVFilterContext *ctx = inlink->dst;
178  ReadVitcContext *s = ctx->priv;
179 
180  s->grp_width = inlink->w * 5 / 48;
181  av_log(ctx, AV_LOG_DEBUG, "w:%d h:%d grp_width:%d scan_max:%d\n",
182  inlink->w, inlink->h, s->grp_width, s->scan_max);
183  return 0;
184 }
185 
186 static const enum AVPixelFormat pixel_fmts[] = {
206 };
207 
209 {
210  AVFilterContext *ctx = inlink->dst;
211  AVFilterLink *outlink = ctx->outputs[0];
212  ReadVitcContext *s = ctx->priv;
213  int found;
214 
215  found = read_vitc_line(s, frame->data[0], frame->linesize[0], inlink->w, inlink->h);
216  av_dict_set(&frame->metadata, "lavfi.readvitc.found", (found ? "1" : "0"), 0);
217  if (found)
218  av_dict_set(&frame->metadata, "lavfi.readvitc.tc_str", make_vitc_tc_string(s->tcbuf, s->line_data), 0);
219 
220  return ff_filter_frame(outlink, frame);
221 }
222 
223 static const AVFilterPad inputs[] = {
224  {
225  .name = "default",
226  .type = AVMEDIA_TYPE_VIDEO,
227  .filter_frame = filter_frame,
228  .config_props = config_props,
229  },
230 };
231 
233  .name = "readvitc",
234  .description = NULL_IF_CONFIG_SMALL("Read vertical interval timecode and write it to frame metadata."),
235  .priv_size = sizeof(ReadVitcContext),
236  .priv_class = &readvitc_class,
241  .init = init,
242 };
get_vitc_crc
static uint8_t get_vitc_crc(uint8_t *line)
Definition: vf_readvitc.c:64
AV_LOG_WARNING
#define AV_LOG_WARNING
Something somehow does not look correct.
Definition: log.h:215
AV_TIMECODE_STR_SIZE
#define AV_TIMECODE_STR_SIZE
Definition: timecode.h:33
AVPixelFormat
AVPixelFormat
Pixel format.
Definition: pixfmt.h:71
config_props
static int config_props(AVFilterLink *inlink)
Definition: vf_readvitc.c:175
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
OFFSET
#define OFFSET(x)
Definition: vf_readvitc.c:52
opt.h
init
static av_cold int init(AVFilterContext *ctx)
Definition: vf_readvitc.c:157
FILTER_PIXFMTS_ARRAY
#define FILTER_PIXFMTS_ARRAY(array)
Definition: filters.h:242
ff_filter_frame
int ff_filter_frame(AVFilterLink *link, AVFrame *frame)
Send a frame of data to the next filter.
Definition: avfilter.c:1062
make_vitc_tc_string
static char * make_vitc_tc_string(char *buf, uint8_t *line)
Definition: vf_readvitc.c:145
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
FILTER_INPUTS
#define FILTER_INPUTS(array)
Definition: filters.h:262
AVFrame
This structure describes decoded (raw) audio or video data.
Definition: frame.h:389
inputs
static const AVFilterPad inputs[]
Definition: vf_readvitc.c:223
AVOption
AVOption.
Definition: opt.h:429
high
int high
Definition: dovi_rpuenc.c:38
AV_PIX_FMT_YUV440P
@ AV_PIX_FMT_YUV440P
planar YUV 4:4:0 (1 Cr & Cb sample per 1x2 Y samples)
Definition: pixfmt.h:106
FFMAX
#define FFMAX(a, b)
Definition: macros.h:47
AVFilter::name
const char * name
Filter name.
Definition: avfilter.h:205
video.h
FLAGS
#define FLAGS
Definition: vf_readvitc.c:53
ReadVitcContext::threshold_white
int threshold_white
Definition: vf_readvitc.c:45
ReadVitcContext::threshold_gray
int threshold_gray
Definition: vf_readvitc.c:46
timecode.h
ReadVitcContext::thr_b
double thr_b
Definition: vf_readvitc.c:41
ss
#define ss(width, name, subs,...)
Definition: cbs_vp9.c:202
AVFilterPad
A filter pad used for either input or output.
Definition: filters.h:38
AV_PIX_FMT_YUVJ411P
@ AV_PIX_FMT_YUVJ411P
planar YUV 4:1:1, 12bpp, (1 Cr & Cb sample per 4x1 Y samples) full scale (JPEG), deprecated in favor ...
Definition: pixfmt.h:283
av_cold
#define av_cold
Definition: attributes.h:90
ff_video_default_filterpad
const AVFilterPad ff_video_default_filterpad[1]
An AVFilterPad array whose only entry has name "default" and is of type AVMEDIA_TYPE_VIDEO.
Definition: video.c:37
AV_PIX_FMT_YUVJ422P
@ AV_PIX_FMT_YUVJ422P
planar YUV 4:2:2, 16bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV422P and setting col...
Definition: pixfmt.h:86
s
#define s(width, name)
Definition: cbs_vp9.c:198
pixel_fmts
static enum AVPixelFormat pixel_fmts[]
Definition: vf_readvitc.c:186
AV_PIX_FMT_YUVA420P
@ AV_PIX_FMT_YUVA420P
planar YUV 4:2:0, 20bpp, (1 Cr & Cb sample per 2x2 Y & A samples)
Definition: pixfmt.h:108
AV_OPT_TYPE_DOUBLE
@ AV_OPT_TYPE_DOUBLE
Underlying C type is double.
Definition: opt.h:267
filters.h
AV_LOG_DEBUG
#define AV_LOG_DEBUG
Stuff which is only useful for libav* developers.
Definition: log.h:230
ctx
AVFormatContext * ctx
Definition: movenc.c:49
read_vitc_line
static int read_vitc_line(ReadVitcContext *ctx, uint8_t *src, int line_size, int width, int height)
Definition: vf_readvitc.c:86
AV_PIX_FMT_YUV420P
@ AV_PIX_FMT_YUV420P
planar YUV 4:2:0, 12bpp, (1 Cr & Cb sample per 2x2 Y samples)
Definition: pixfmt.h:73
FILTER_OUTPUTS
#define FILTER_OUTPUTS(array)
Definition: filters.h:263
AV_PIX_FMT_YUVJ444P
@ AV_PIX_FMT_YUVJ444P
planar YUV 4:4:4, 24bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV444P and setting col...
Definition: pixfmt.h:87
AVClass
Describe the class of an AVClass context structure.
Definition: log.h:75
NULL
#define NULL
Definition: coverity.c:32
AV_PIX_FMT_YUVJ420P
@ AV_PIX_FMT_YUVJ420P
planar YUV 4:2:0, 12bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV420P and setting col...
Definition: pixfmt.h:85
AV_PIX_FMT_GRAY8
@ AV_PIX_FMT_GRAY8
Y , 8bpp.
Definition: pixfmt.h:81
ReadVitcContext::scan_max
int scan_max
Definition: vf_readvitc.c:40
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
ReadVitcContext::thr_w
double thr_w
Definition: vf_readvitc.c:42
height
#define height
Definition: dsp.h:85
LINE_DATA_SIZE
#define LINE_DATA_SIZE
Definition: vf_readvitc.c:35
AV_PIX_FMT_NV16
@ AV_PIX_FMT_NV16
interleaved chroma YUV 4:2:2, 16bpp, (1 Cr & Cb sample per 2x1 Y samples)
Definition: pixfmt.h:198
AV_PIX_FMT_YUVA444P
@ AV_PIX_FMT_YUVA444P
planar YUV 4:4:4 32bpp, (1 Cr & Cb sample per 1x1 Y & A samples)
Definition: pixfmt.h:174
line
Definition: graph2dot.c:48
AVFILTER_DEFINE_CLASS
AVFILTER_DEFINE_CLASS(readvitc)
ReadVitcContext::threshold_black
int threshold_black
Definition: vf_readvitc.c:44
ReadVitcContext::line_data
uint8_t line_data[LINE_DATA_SIZE]
Definition: vf_readvitc.c:48
ReadVitcContext
Definition: vf_readvitc.c:37
i
#define i(width, name, range_min, range_max)
Definition: cbs_h2645.c:256
internal.h
common.h
FFMIN
#define FFMIN(a, b)
Definition: macros.h:49
AV_PIX_FMT_YUVJ440P
@ AV_PIX_FMT_YUVJ440P
planar YUV 4:4:0 full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV440P and setting color_range
Definition: pixfmt.h:107
AV_PIX_FMT_NV21
@ AV_PIX_FMT_NV21
as above, but U and V bytes are swapped
Definition: pixfmt.h:97
bcd2uint
static unsigned bcd2uint(uint8_t high, uint8_t low)
Definition: vf_readvitc.c:138
AVFilterPad::name
const char * name
Pad name.
Definition: filters.h:44
AVFilter
Filter definition.
Definition: avfilter.h:201
AV_PIX_FMT_NV12
@ AV_PIX_FMT_NV12
planar YUV 4:2:0, 12bpp, 1 plane for Y and 1 plane for the UV components, which are interleaved (firs...
Definition: pixfmt.h:96
frame
these buffered frames must be flushed immediately if a new input produces new the filter must not call request_frame to get more It must just process the frame or queue it The task of requesting more frames is left to the filter s request_frame method or the application If a filter has several the filter must be ready for frames arriving randomly on any input any filter with several inputs will most likely require some kind of queuing mechanism It is perfectly acceptable to have a limited queue and to drop frames when the inputs are too unbalanced request_frame For filters that do not use the this method is called when a frame is wanted on an output For a it should directly call filter_frame on the corresponding output For a if there are queued frames already one of these frames should be pushed If the filter should request a frame on one of its repeatedly until at least one frame has been pushed Return or at least make progress towards producing a frame
Definition: filter_design.txt:264
ff_vf_readvitc
const AVFilter ff_vf_readvitc
Definition: vf_readvitc.c:232
readvitc_options
static const AVOption readvitc_options[]
Definition: vf_readvitc.c:55
get_pit_avg3
static uint8_t get_pit_avg3(uint8_t *line, int i)
Definition: vf_readvitc.c:82
AV_PIX_FMT_NONE
@ AV_PIX_FMT_NONE
Definition: pixfmt.h:72
AV_OPT_TYPE_INT
@ AV_OPT_TYPE_INT
Underlying C type is int.
Definition: opt.h:259
avfilter.h
AVFILTER_FLAG_METADATA_ONLY
#define AVFILTER_FLAG_METADATA_ONLY
The filter is a "metadata" filter - it does not modify the frame data in any way.
Definition: avfilter.h:168
AV_PIX_FMT_YUV444P
@ AV_PIX_FMT_YUV444P
planar YUV 4:4:4, 24bpp, (1 Cr & Cb sample per 1x1 Y samples)
Definition: pixfmt.h:78
AVFilterContext
An instance of a filter.
Definition: avfilter.h:457
AVMEDIA_TYPE_VIDEO
@ AVMEDIA_TYPE_VIDEO
Definition: avutil.h:201
AV_PIX_FMT_YUV422P
@ AV_PIX_FMT_YUV422P
planar YUV 4:2:2, 16bpp, (1 Cr & Cb sample per 2x1 Y samples)
Definition: pixfmt.h:77
av_dict_set
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:88
AV_PIX_FMT_YUV411P
@ AV_PIX_FMT_YUV411P
planar YUV 4:1:1, 12bpp, (1 Cr & Cb sample per 4x1 Y samples)
Definition: pixfmt.h:80
ReadVitcContext::grp_width
int grp_width
Definition: vf_readvitc.c:47
flags
#define flags(name, subs,...)
Definition: cbs_av1.c:482
AV_PIX_FMT_YUV410P
@ AV_PIX_FMT_YUV410P
planar YUV 4:1:0, 9bpp, (1 Cr & Cb sample per 4x4 Y samples)
Definition: pixfmt.h:79
av_log
#define av_log(a,...)
Definition: tableprint_vlc.h:27
ReadVitcContext::tcbuf
char tcbuf[AV_TIMECODE_STR_SIZE]
Definition: vf_readvitc.c:49
width
#define width
Definition: dsp.h:85
snprintf
#define snprintf
Definition: snprintf.h:34
filter_frame
static int filter_frame(AVFilterLink *inlink, AVFrame *frame)
Definition: vf_readvitc.c:208
src
#define src
Definition: vp8dsp.c:248
AV_PIX_FMT_YUVA422P
@ AV_PIX_FMT_YUVA422P
planar YUV 4:2:2 24bpp, (1 Cr & Cb sample per 2x1 Y & A samples)
Definition: pixfmt.h:173