Go to the documentation of this file.
1 /*
2  * Copyright (c) 2012 Stefano Sabatini
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
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  */
21 /**
22  * @file
23  * bounding box detection filter
24  */
26 #include "libavutil/opt.h"
27 #include "libavutil/pixdesc.h"
28 #include "libavutil/timestamp.h"
29 #include "avfilter.h"
30 #include "bbox.h"
31 #include "internal.h"
33 typedef struct BBoxContext {
34  const AVClass *class;
35  int min_val;
36 } BBoxContext;
38 #define OFFSET(x) offsetof(BBoxContext, x)
41 static const AVOption bbox_options[] = {
42  { "min_val", "set minimum luminance value for bounding box", OFFSET(min_val), AV_OPT_TYPE_INT, { .i64 = 16 }, 0, 254, FLAGS },
43  { NULL }
44 };
49 {
50  static const enum AVPixelFormat pix_fmts[] = {
57  };
59  AVFilterFormats *fmts_list = ff_make_format_list(pix_fmts);
60  if (!fmts_list)
61  return AVERROR(ENOMEM);
62  return ff_set_common_formats(ctx, fmts_list);
63 }
65 #define SET_META(key, value) \
66  av_dict_set_int(metadata, key, value, 0);
69 {
70  AVFilterContext *ctx = inlink->dst;
71  BBoxContext *bbox = ctx->priv;
72  FFBoundingBox box;
73  int has_bbox, w, h;
75  has_bbox =
77  frame->data[0], frame->linesize[0],
78  inlink->w, inlink->h, bbox->min_val);
79  w = box.x2 - box.x1 + 1;
80  h = box.y2 - box.y1 + 1;
82  av_log(ctx, AV_LOG_INFO,
83  "n:%"PRId64" pts:%s pts_time:%s", inlink->frame_count_out,
84  av_ts2str(frame->pts), av_ts2timestr(frame->pts, &inlink->time_base));
86  if (has_bbox) {
87  AVDictionary **metadata = &frame->metadata;
89  SET_META("lavfi.bbox.x1", box.x1)
90  SET_META("lavfi.bbox.x2", box.x2)
91  SET_META("lavfi.bbox.y1", box.y1)
92  SET_META("lavfi.bbox.y2", box.y2)
93  SET_META("lavfi.bbox.w", w)
94  SET_META("lavfi.bbox.h", h)
96  av_log(ctx, AV_LOG_INFO,
97  " x1:%d x2:%d y1:%d y2:%d w:%d h:%d"
98  " crop=%d:%d:%d:%d drawbox=%d:%d:%d:%d",
99  box.x1, box.x2, box.y1, box.y2, w, h,
100  w, h, box.x1, box.y1, /* crop params */
101  box.x1, box.y1, w, h); /* drawbox params */
102  }
103  av_log(ctx, AV_LOG_INFO, "\n");
105  return ff_filter_frame(inlink->dst->outputs[0], frame);
106 }
108 static const AVFilterPad bbox_inputs[] = {
109  {
110  .name = "default",
111  .type = AVMEDIA_TYPE_VIDEO,
112  .filter_frame = filter_frame,
113  },
114  { NULL }
115 };
117 static const AVFilterPad bbox_outputs[] = {
118  {
119  .name = "default",
120  .type = AVMEDIA_TYPE_VIDEO,
121  },
122  { NULL }
123 };
126  .name = "bbox",
127  .description = NULL_IF_CONFIG_SMALL("Compute bounding box for each frame."),
128  .priv_size = sizeof(BBoxContext),
129  .priv_class = &bbox_class,
131  .inputs = bbox_inputs,
132  .outputs = bbox_outputs,
134 };
#define NULL
Definition: coverity.c:32
static const AVFilterPad bbox_inputs[]
Definition: vf_bbox.c:108
static int filter_frame(AVFilterLink *inlink, AVFrame *frame)
Definition: vf_bbox.c:68
This structure describes decoded (raw) audio or video data.
Definition: frame.h:308
Definition: opt.h:248
planar YUV 4:4:4, 24bpp, (1 Cr & Cb sample per 1x1 Y samples)
Definition: pixfmt.h:71
Main libavfilter public API header.
AVFilter ff_vf_bbox
Definition: vf_bbox.c:125
AVFilterFormats * ff_make_format_list(const int *fmts)
Create a list of supported formats.
Definition: formats.c:283
Some filters support a generic "enable" expression option that can be used to enable or disable a fil...
Definition: avfilter.h:125
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:1091
timestamp utils, mostly useful for debugging/logging purposes
int64_t pts
Presentation timestamp in time_base units (time when frame should be shown to user).
Definition: frame.h:401
AVDictionary * metadata
Definition: frame.h:594
#define av_log(a,...)
#define SET_META(key, value)
Definition: vf_bbox.c:65
A filter pad used for either input or output.
Definition: internal.h:54
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:600
#define av_ts2timestr(ts, tb)
Convenience macro, the return value should be used only directly in function arguments but never stan...
Definition: timestamp.h:76
int x2
Definition: bbox.h:27
Return NULL if CONFIG_SMALL is true, otherwise the argument without modification. ...
Definition: internal.h:153
void * priv
private data for use by the filter
Definition: avfilter.h:353
planar YUV 4:2:2, 16bpp, (1 Cr & Cb sample per 2x1 Y samples)
Definition: pixfmt.h:70
#define FLAGS
Definition: vf_bbox.c:39
uint8_t w
Definition: llviddspenc.c:38
static const AVOption bbox_options[]
Definition: vf_bbox.c:41
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
int min_val
Definition: vf_bbox.c:35
int y1
Definition: bbox.h:27
static const AVFilterPad outputs[]
Definition: af_acontrast.c:203
#define AV_LOG_INFO
Standard information.
Definition: log.h:205
#define OFFSET(x)
Definition: vf_bbox.c:38
int linesize[AV_NUM_DATA_POINTERS]
For video, size in bytes of each picture line.
Definition: frame.h:339
static int query_formats(AVFilterContext *ctx)
Definition: vf_bbox.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 inputs
Describe the class of an AVClass context structure.
Definition: log.h:67
Filter definition.
Definition: avfilter.h:144
static const AVFilterPad bbox_outputs[]
Definition: vf_bbox.c:117
const char * name
Filter name.
Definition: avfilter.h:148
AVFilterLink ** outputs
array of pointers to output links
Definition: avfilter.h:350
static enum AVPixelFormat pix_fmts[]
Definition: libkvazaar.c:270
#define flags(name, subs,...)
Definition: cbs_av1.c:560
uint8_t * data[AV_NUM_DATA_POINTERS]
pointer to the picture/channel planes.
Definition: frame.h:322
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
int ff_calculate_bounding_box(FFBoundingBox *bbox, const uint8_t *data, int linesize, int w, int h, int min_val)
Calculate the smallest rectangle that will encompass the region with values > min_val.
Definition: bbox.c:23
planar YUV 4:1:1, 12bpp, (1 Cr & Cb sample per 4x1 Y samples)
Definition: pixfmt.h:73
int y2
Definition: bbox.h:27
#define av_ts2str(ts)
Convenience macro, the return value should be used only directly in function arguments but never stan...
Definition: timestamp.h:54
A list of supported formats for one end of a filter link.
Definition: formats.h:64
int x1
Definition: bbox.h:27
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
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
Pixel format.
Definition: pixfmt.h:64