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/pixdesc.h"
31 #include "libavutil/timecode.h"
32 #include "avfilter.h"
33 #include "formats.h"
34 #include "internal.h"
35 
36 #define LINE_DATA_SIZE 9
37 
38 typedef struct ReadVitcContext {
39  const AVClass *class;
40 
41  int scan_max;
42  double thr_b;
43  double thr_w;
44 
48  int grp_width;
52 
53 #define OFFSET(x) offsetof(ReadVitcContext, x)
54 #define FLAGS AV_OPT_FLAG_VIDEO_PARAM|AV_OPT_FLAG_FILTERING_PARAM
55 
56 static const AVOption readvitc_options[] = {
57  { "scan_max", "maximum line numbers to scan for VITC data", OFFSET(scan_max), AV_OPT_TYPE_INT, {.i64 = 45 }, -1, INT_MAX, FLAGS },
58  { "thr_b", "black color threshold", OFFSET(thr_b), AV_OPT_TYPE_DOUBLE, {.dbl = 0.2 }, 0, 1.0, FLAGS },
59  { "thr_w", "white color threshold", OFFSET(thr_w), AV_OPT_TYPE_DOUBLE, {.dbl = 0.6 }, 0, 1.0, FLAGS },
60  { NULL }
61 };
62 
63 AVFILTER_DEFINE_CLASS(readvitc);
64 
66  uint8_t crc;
67 
68  crc = 0x01 | (line[0] << 2);
69  crc ^= (line[0] >> 6) | 0x04 | (line[1] << 4);
70  crc ^= (line[1] >> 4) | 0x10 | (line[2] << 6);
71  crc ^= (line[2] >> 2) | 0x40;
72  crc ^= line[3];
73  crc ^= 0x01 | (line[4] << 2);
74  crc ^= (line[4] >> 6) | 0x04 | (line[5] << 4);
75  crc ^= (line[5] >> 4) | 0x10 | (line[6] << 6);
76  crc ^= (line[6] >> 2) | 0x40;
77  crc ^= line[7];
78  crc ^= 0x01;
79  crc = (crc >> 2) | (crc << 6); // rotate byte right by two bits
80  return crc;
81 }
82 
83 static inline uint8_t get_pit_avg3( uint8_t *line, int i ) {
84  return ((line[i-1] + line[i] + line[i+1]) / 3);
85 }
86 
87 static int read_vitc_line( ReadVitcContext *ctx, uint8_t *src, int line_size, int width, int height )
88 {
89  uint8_t *scan_line;
90  int grp_index, pit_index;
91  int grp_start_pos;
92  uint8_t pit_value;
93  int x, y, res = 0;
94 
95  if (ctx->scan_max >= 0)
96  height = FFMIN(height, ctx->scan_max);
97 
98  // scan lines for VITC data, starting from the top
99  for (y = 0; y < height; y++) {
100  scan_line = src;
101  memset(ctx->line_data, 0, LINE_DATA_SIZE);
102  grp_index = 0;
103  x = 0;
104  while ((x < width) && (grp_index < 9)) {
105  // search next sync pattern
106  while ((x < width) && (scan_line[x] < ctx->threshold_white))
107  x++;
108  while ((x < width) && (scan_line[x] > ctx->threshold_black))
109  x++;
110  x = FFMAX(x - ((ctx->grp_width+10) / 20), 1); // step back a half pit
111  grp_start_pos = x;
112  if ((grp_start_pos + ctx->grp_width) > width)
113  break; // not enough pixels for reading a whole pit group
114  pit_value = get_pit_avg3(scan_line, x);
115  if (pit_value < ctx->threshold_white)
116  break; // first sync bit mismatch
117  x = grp_start_pos + ((ctx->grp_width) / 10);
118  pit_value = get_pit_avg3(scan_line, x);
119  if (pit_value > ctx->threshold_black )
120  break; // second sync bit mismatch
121  for (pit_index = 0; pit_index <= 7; pit_index++) {
122  x = grp_start_pos + (((pit_index+2)*ctx->grp_width) / 10);
123  pit_value = get_pit_avg3(scan_line, x);
124  if (pit_value > ctx->threshold_gray)
125  ctx->line_data[grp_index] |= (1 << pit_index);
126  }
127  grp_index++;
128  }
129  if ((grp_index == 9) && (get_vitc_crc(ctx->line_data) == ctx->line_data[8])) {
130  res = 1;
131  break;
132  }
133  src += line_size;
134  }
135 
136  return res;
137 }
138 
139 static unsigned bcd2uint(uint8_t high, uint8_t low)
140 {
141  if (high > 9 || low > 9)
142  return 0;
143  return 10*high + low;
144 }
145 
146 static char *make_vitc_tc_string(char *buf, uint8_t *line)
147 {
148  unsigned hh = bcd2uint(line[7] & 0x03, line[6] & 0x0f); // 6-bit hours
149  unsigned mm = bcd2uint(line[5] & 0x07, line[4] & 0x0f); // 7-bit minutes
150  unsigned ss = bcd2uint(line[3] & 0x07, line[2] & 0x0f); // 7-bit seconds
151  unsigned ff = bcd2uint(line[1] & 0x03, line[0] & 0x0f); // 6-bit frames
152  unsigned drop = (line[1] & 0x04); // 1-bit drop flag
153  snprintf(buf, AV_TIMECODE_STR_SIZE, "%02u:%02u:%02u%c%02u",
154  hh, mm, ss, drop ? ';' : ':', ff);
155  return buf;
156 }
157 
159 {
160  ReadVitcContext *s = ctx->priv;
161 
162  s->threshold_black = s->thr_b * UINT8_MAX;
163  s->threshold_white = s->thr_w * UINT8_MAX;
164  if (s->threshold_black > s->threshold_white) {
165  av_log(ctx, AV_LOG_WARNING, "Black color threshold is higher than white color threshold (%g > %g)\n",
166  s->thr_b, s->thr_w);
167  return AVERROR(EINVAL);
168  }
170  av_log(ctx, AV_LOG_DEBUG, "threshold_black:%d threshold_white:%d threshold_gray:%d\n",
172 
173  return 0;
174 }
175 
177 {
178  AVFilterContext *ctx = inlink->dst;
179  ReadVitcContext *s = ctx->priv;
180 
181  s->grp_width = inlink->w * 5 / 48;
182  av_log(ctx, AV_LOG_DEBUG, "w:%d h:%d grp_width:%d scan_max:%d\n",
183  inlink->w, inlink->h, s->grp_width, s->scan_max);
184  return 0;
185 }
186 
188 {
189  static const enum AVPixelFormat pixel_fmts[] = {
209  };
210  AVFilterFormats *fmts_list = ff_make_format_list(pixel_fmts);
211  if (!fmts_list)
212  return AVERROR(ENOMEM);
213  return ff_set_common_formats(ctx, fmts_list);
214 }
215 
217 {
218  AVFilterContext *ctx = inlink->dst;
219  AVFilterLink *outlink = ctx->outputs[0];
220  ReadVitcContext *s = ctx->priv;
221  int found;
222 
223  found = read_vitc_line(s, frame->data[0], frame->linesize[0], inlink->w, inlink->h);
224  av_dict_set(&frame->metadata, "lavfi.readvitc.found", (found ? "1" : "0"), 0);
225  if (found)
226  av_dict_set(&frame->metadata, "lavfi.readvitc.tc_str", make_vitc_tc_string(s->tcbuf, s->line_data), 0);
227 
228  return ff_filter_frame(outlink, frame);
229 }
230 
231 static const AVFilterPad inputs[] = {
232  {
233  .name = "default",
234  .type = AVMEDIA_TYPE_VIDEO,
235  .filter_frame = filter_frame,
236  .config_props = config_props,
237  },
238  { NULL }
239 };
240 
241 static const AVFilterPad outputs[] = {
242  {
243  .name = "default",
244  .type = AVMEDIA_TYPE_VIDEO,
245  },
246  { NULL }
247 };
248 
250  .name = "readvitc",
251  .description = NULL_IF_CONFIG_SMALL("Read vertical interval timecode and write it to frame metadata."),
252  .priv_size = sizeof(ReadVitcContext),
253  .priv_class = &readvitc_class,
254  .inputs = inputs,
255  .outputs = outputs,
256  .init = init,
258 };
#define NULL
Definition: coverity.c:32
This structure describes decoded (raw) audio or video data.
Definition: frame.h:295
AVOption.
Definition: opt.h:246
static int query_formats(AVFilterContext *ctx)
Definition: vf_readvitc.c:187
planar YUV 4:4:4, 24bpp, (1 Cr & Cb sample per 1x1 Y samples)
Definition: pixfmt.h:71
#define AV_LOG_WARNING
Something somehow does not look correct.
Definition: log.h:182
Main libavfilter public API header.
static unsigned bcd2uint(uint8_t high, uint8_t low)
Definition: vf_readvitc.c:139
static uint8_t get_pit_avg3(uint8_t *line, int i)
Definition: vf_readvitc.c:83
static uint8_t get_vitc_crc(uint8_t *line)
Definition: vf_readvitc.c:65
#define src
Definition: vp8dsp.c:254
AVFilterFormats * ff_make_format_list(const int *fmts)
Create a list of supported formats.
Definition: formats.c:283
const char * name
Pad name.
Definition: internal.h:60
int ff_filter_frame(AVFilterLink *link, AVFrame *frame)
Send a frame of data to the next filter.
Definition: avfilter.c:1093
planar YUV 4:2:0, 20bpp, (1 Cr & Cb sample per 2x2 Y & A samples)
Definition: pixfmt.h:101
uint8_t
#define av_cold
Definition: attributes.h:82
AVOptions.
#define height
planar YUV 4:4:0 full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV440P and setting color_range...
Definition: pixfmt.h:100
planar YUV 4:2:2, 16bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV422P and setting col...
Definition: pixfmt.h:79
AVDictionary * metadata
metadata.
Definition: frame.h:581
#define LINE_DATA_SIZE
Definition: vf_readvitc.c:36
#define av_log(a,...)
static char * make_vitc_tc_string(char *buf, uint8_t *line)
Definition: vf_readvitc.c:146
A filter pad used for either input or output.
Definition: internal.h:54
planar YUV 4:2:2 24bpp, (1 Cr & Cb sample per 2x1 Y & A samples)
Definition: pixfmt.h:176
#define i(width, name, range_min, range_max)
Definition: cbs_h2645.c:259
int ff_set_common_formats(AVFilterContext *ctx, AVFilterFormats *formats)
A helper for query_formats() which sets all links to the same list of formats.
Definition: formats.c:569
#define NULL_IF_CONFIG_SMALL(x)
Return NULL if CONFIG_SMALL is true, otherwise the argument without modification. ...
Definition: internal.h:186
void * priv
private data for use by the filter
Definition: avfilter.h:353
#define AV_LOG_DEBUG
Stuff which is only useful for libav* developers.
Definition: log.h:197
planar YUV 4:2:0, 12bpp, 1 plane for Y and 1 plane for the UV components, which are interleaved (firs...
Definition: pixfmt.h:89
Definition: graph2dot.c:48
static const AVOption readvitc_options[]
Definition: vf_readvitc.c:56
#define FFMAX(a, b)
Definition: common.h:94
AVFILTER_DEFINE_CLASS(readvitc)
planar YUV 4:2:2, 16bpp, (1 Cr & Cb sample per 2x1 Y samples)
Definition: pixfmt.h:70
common internal API header
as above, but U and V bytes are swapped
Definition: pixfmt.h:90
#define ss(width, name, subs,...)
Definition: cbs_vp9.c:261
#define FFMIN(a, b)
Definition: common.h:96
planar YUV 4:2:0, 12bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV420P and setting col...
Definition: pixfmt.h:78
#define width
AVFormatContext * ctx
Definition: movenc.c:48
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
#define s(width, name)
Definition: cbs_vp9.c:257
char tcbuf[AV_TIMECODE_STR_SIZE]
Definition: vf_readvitc.c:50
uint8_t line_data[LINE_DATA_SIZE]
Definition: vf_readvitc.c:49
AVFilter ff_vf_readvitc
Definition: vf_readvitc.c:249
Timecode helpers header.
int linesize[AV_NUM_DATA_POINTERS]
For video, size in bytes of each picture line.
Definition: frame.h:326
planar YUV 4:4:4 32bpp, (1 Cr & Cb sample per 1x1 Y & A samples)
Definition: pixfmt.h:177
static const AVFilterPad inputs[]
Definition: vf_readvitc.c:231
void * buf
Definition: avisynth_c.h:766
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:70
planar YUV 4:1:0, 9bpp, (1 Cr & Cb sample per 4x4 Y samples)
Definition: pixfmt.h:72
Describe the class of an AVClass context structure.
Definition: log.h:67
Filter definition.
Definition: avfilter.h:144
static int filter_frame(AVFilterLink *inlink, AVFrame *frame)
Definition: vf_readvitc.c:216
const char * name
Filter name.
Definition: avfilter.h:148
#define snprintf
Definition: snprintf.h:34
AVFilterLink ** outputs
array of pointers to output links
Definition: avfilter.h:350
uint8_t * data[AV_NUM_DATA_POINTERS]
pointer to the picture/channel planes.
Definition: frame.h:309
static av_cold int init(AVFilterContext *ctx)
Definition: vf_readvitc.c:158
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
planar YUV 4:2:0, 12bpp, (1 Cr & Cb sample per 2x2 Y samples)
Definition: pixfmt.h:66
Y , 8bpp.
Definition: pixfmt.h:74
common internal and external API header
planar YUV 4:4:4, 24bpp, full scale (JPEG), deprecated in favor of AV_PIX_FMT_YUV444P and setting col...
Definition: pixfmt.h:80
planar YUV 4:1:1, 12bpp, (1 Cr & Cb sample per 4x1 Y samples)
Definition: pixfmt.h:73
interleaved chroma YUV 4:2:2, 16bpp, (1 Cr & Cb sample per 2x1 Y samples)
Definition: pixfmt.h:201
static int read_vitc_line(ReadVitcContext *ctx, uint8_t *src, int line_size, int width, int height)
Definition: vf_readvitc.c:87
#define OFFSET(x)
Definition: vf_readvitc.c:53
static int config_props(AVFilterLink *inlink)
Definition: vf_readvitc.c:176
A list of supported formats for one end of a filter link.
Definition: formats.h:64
planar YUV 4:1:1, 12bpp, (1 Cr & Cb sample per 4x1 Y samples) full scale (JPEG), deprecated in favor ...
Definition: pixfmt.h:258
An instance of a filter.
Definition: avfilter.h:338
planar YUV 4:4:0 (1 Cr & Cb sample per 1x2 Y samples)
Definition: pixfmt.h:99
static const AVFilterPad outputs[]
Definition: vf_readvitc.c:241
internal API functions
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
#define FLAGS
Definition: vf_readvitc.c:54
AVPixelFormat
Pixel format.
Definition: pixfmt.h:64
#define AV_TIMECODE_STR_SIZE
Definition: timecode.h:33