FFmpeg: libavfilter/vf_vidstabtransform.c Source File

FFmpeg

[フレーム]

libavfilter

vf_vidstabtransform.c

Go to the documentation of this file.

1 /*

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 */

21 #define DEFAULT_INPUT_NAME "transforms.trf"

23 #include <vid.stab/libvidstab.h>

25 #include "libavutil/common.h"

26 #include "libavutil/opt.h"

27 #include "libavutil/imgutils.h"

28 #include "avfilter.h"

29 #include "internal.h"

31 #include "vidstabutils.h"

33 typedef struct {

34 const AVClass *class;

36 VSTransformData td;

37 VSTransformConfig conf;

39 VSTransformations trans; // transformations

40 char *input; // name of transform file

41 int tripod;

42 int debug;

43 } TransformContext;

45 #define OFFSET(x) offsetof(TransformContext, x)

46 #define OFFSETC(x) (offsetof(TransformContext, conf)+offsetof(VSTransformConfig, x))

47 #define FLAGS AV_OPT_FLAG_FILTERING_PARAM|AV_OPT_FLAG_VIDEO_PARAM

49 static const AVOption vidstabtransform_options[] = {

50 {"input", "set path to the file storing the transforms", OFFSET(input),

51 AV_OPT_TYPE_STRING, {.str = DEFAULT_INPUT_NAME}, .flags = FLAGS },

52 {"smoothing", "set number of frames*2 + 1 used for lowpass filtering", OFFSETC(smoothing),

53 AV_OPT_TYPE_INT, {.i64 = 15}, 0, 1000, FLAGS},

55 {"optalgo", "set camera path optimization algo", OFFSETC(camPathAlgo),

56 AV_OPT_TYPE_INT, {.i64 = VSOptimalL1}, VSOptimalL1, VSAvg, FLAGS, "optalgo"},

57 { "opt", "global optimization", 0, // from version 1.0 on

58 AV_OPT_TYPE_CONST, {.i64 = VSOptimalL1 }, 0, 0, FLAGS, "optalgo"},

59 { "gauss", "gaussian kernel", 0,

60 AV_OPT_TYPE_CONST, {.i64 = VSGaussian }, 0, 0, FLAGS, "optalgo"},

61 { "avg", "simple averaging on motion", 0,

62 AV_OPT_TYPE_CONST, {.i64 = VSAvg }, 0, 0, FLAGS, "optalgo"},

64 {"maxshift", "set maximal number of pixels to translate image", OFFSETC(maxShift),

65 AV_OPT_TYPE_INT, {.i64 = -1}, -1, 500, FLAGS},

66 {"maxangle", "set maximal angle in rad to rotate image", OFFSETC(maxAngle),

67 AV_OPT_TYPE_DOUBLE, {.dbl = -1.0}, -1.0, 3.14, FLAGS},

69 {"crop", "set cropping mode", OFFSETC(crop),

70 AV_OPT_TYPE_INT, {.i64 = 0}, 0, 1, FLAGS, "crop"},

71 { "keep", "keep border", 0,

72 AV_OPT_TYPE_CONST, {.i64 = VSKeepBorder }, 0, 0, FLAGS, "crop"},

73 { "black", "black border", 0,

74 AV_OPT_TYPE_CONST, {.i64 = VSCropBorder }, 0, 0, FLAGS, "crop"},

76 {"invert", "invert transforms", OFFSETC(invert),

77 AV_OPT_TYPE_INT, {.i64 = 0}, 0, 1, FLAGS},

78 {"relative", "consider transforms as relative", OFFSETC(relative),

79 AV_OPT_TYPE_INT, {.i64 = 1}, 0, 1, FLAGS},

80 {"zoom", "set percentage to zoom (>0: zoom in, <0: zoom out", OFFSETC(zoom),

81 AV_OPT_TYPE_DOUBLE, {.dbl = 0}, -100, 100, FLAGS},

82 {"optzoom", "set optimal zoom (0: nothing, 1: optimal static zoom, 2: optimal dynamic zoom)", OFFSETC(optZoom),

83 AV_OPT_TYPE_INT, {.i64 = 1}, 0, 2, FLAGS},

84 {"zoomspeed", "for adative zoom: percent to zoom maximally each frame", OFFSETC(zoomSpeed),

85 AV_OPT_TYPE_DOUBLE, {.dbl = 0.25}, 0, 5, FLAGS},

87 {"interpol", "set type of interpolation", OFFSETC(interpolType),

88 AV_OPT_TYPE_INT, {.i64 = 2}, 0, 3, FLAGS, "interpol"},

89 { "no", "no interpolation", 0,

90 AV_OPT_TYPE_CONST, {.i64 = VS_Zero }, 0, 0, FLAGS, "interpol"},

91 { "linear", "linear (horizontal)", 0,

92 AV_OPT_TYPE_CONST, {.i64 = VS_Linear }, 0, 0, FLAGS, "interpol"},

93 { "bilinear","bi-linear", 0,

94 AV_OPT_TYPE_CONST, {.i64 = VS_BiLinear},0, 0, FLAGS, "interpol"},

95 { "bicubic", "bi-cubic", 0,

96 AV_OPT_TYPE_CONST, {.i64 = VS_BiCubic },0, 0, FLAGS, "interpol"},

98 {"tripod", "enable virtual tripod mode (same as relative=0:smoothing=0)", OFFSET(tripod),

99 AV_OPT_TYPE_INT, {.i64 = 0}, 0, 1, FLAGS},

100 {"debug", "enable debug mode and writer global motions information to file", OFFSET(debug),

101 AV_OPT_TYPE_INT, {.i64 = 0}, 0, 1, FLAGS},

102 {NULL}

103 };

104

105 AVFILTER_DEFINE_CLASS(vidstabtransform);

106

107 static av_cold int init(AVFilterContext *ctx)

108 {

109 TransformContext *tc = ctx->priv;

110 ff_vs_init();

111 tc->class = &vidstabtransform_class;

112 av_log(ctx, AV_LOG_VERBOSE, "vidstabtransform filter: init %s\n", LIBVIDSTAB_VERSION);

113 return 0;

114 }

115

116 static av_cold void uninit(AVFilterContext *ctx)

117 {

118 TransformContext *tc = ctx->priv;

119

120 vsTransformDataCleanup(&tc->td);

121 vsTransformationsCleanup(&tc->trans);

122 }

123

124 static int query_formats(AVFilterContext *ctx)

125 {

126 // If you add something here also add it in vidstabutils.c

127 static const enum AVPixelFormat pix_fmts[] = {

128 AV_PIX_FMT_YUV444P, AV_PIX_FMT_YUV422P, AV_PIX_FMT_YUV420P,

129 AV_PIX_FMT_YUV411P, AV_PIX_FMT_YUV410P, AV_PIX_FMT_YUVA420P,

130 AV_PIX_FMT_YUV440P, AV_PIX_FMT_GRAY8,

131 AV_PIX_FMT_RGB24, AV_PIX_FMT_BGR24, AV_PIX_FMT_RGBA,

132 AV_PIX_FMT_NONE

133 };

134

135 ff_set_common_formats(ctx, ff_make_format_list(pix_fmts));

136 return 0;

137 }

138

139

140 static int config_input(AVFilterLink *inlink)

141 {

142 AVFilterContext *ctx = inlink->dst;

143 TransformContext *tc = ctx->priv;

144 FILE *f;

145

146 const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(inlink->format);

147

148 VSTransformData *td = &(tc->td);

149

150 VSFrameInfo fi_src;

151 VSFrameInfo fi_dest;

152

153 if (!vsFrameInfoInit(&fi_src, inlink->w, inlink->h,

154 ff_av2vs_pixfmt(ctx, inlink->format)) ||

155 !vsFrameInfoInit(&fi_dest, inlink->w, inlink->h,

156 ff_av2vs_pixfmt(ctx, inlink->format))) {

157 av_log(ctx, AV_LOG_ERROR, "unknown pixel format: %i (%s)",

158 inlink->format, desc->name);

159 return AVERROR(EINVAL);

160 }

161

162 if (fi_src.bytesPerPixel != av_get_bits_per_pixel(desc)/8 ||

163 fi_src.log2ChromaW != desc->log2_chroma_w ||

164 fi_src.log2ChromaH != desc->log2_chroma_h) {

165 av_log(ctx, AV_LOG_ERROR, "pixel-format error: bpp %i<>%i ",

166 fi_src.bytesPerPixel, av_get_bits_per_pixel(desc)/8);

167 av_log(ctx, AV_LOG_ERROR, "chroma_subsampl: w: %i<>%i h: %i<>%i\n",

168 fi_src.log2ChromaW, desc->log2_chroma_w,

169 fi_src.log2ChromaH, desc->log2_chroma_h);

170 return AVERROR(EINVAL);

171 }

172

173 // set values that are not initializes by the options

174 tc->conf.modName = "vidstabtransform";

175 tc->conf.verbose = 1 + tc->debug;

176 if (tc->tripod) {

177 av_log(ctx, AV_LOG_INFO, "Virtual tripod mode: relative=0, smoothing=0\n");

178 tc->conf.relative = 0;

179 tc->conf.smoothing = 0;

180 }

181 tc->conf.simpleMotionCalculation = 0;

182 tc->conf.storeTransforms = tc->debug;

183 tc->conf.smoothZoom = 0;

184

185 if (vsTransformDataInit(td, &tc->conf, &fi_src, &fi_dest) != VS_OK) {

186 av_log(ctx, AV_LOG_ERROR, "initialization of vid.stab transform failed, please report a BUG\n");

187 return AVERROR(EINVAL);

188 }

189

190 vsTransformGetConfig(&tc->conf, td);

191 av_log(ctx, AV_LOG_INFO, "Video transformation/stabilization settings (pass 2/2):\n");

192 av_log(ctx, AV_LOG_INFO, " input = %s\n", tc->input);

193 av_log(ctx, AV_LOG_INFO, " smoothing = %d\n", tc->conf.smoothing);

194 av_log(ctx, AV_LOG_INFO, " optalgo = %s\n",

195 tc->conf.camPathAlgo == VSOptimalL1 ? "opt" :

196 (tc->conf.camPathAlgo == VSGaussian ? "gauss" : "avg"));

197 av_log(ctx, AV_LOG_INFO, " maxshift = %d\n", tc->conf.maxShift);

198 av_log(ctx, AV_LOG_INFO, " maxangle = %f\n", tc->conf.maxAngle);

199 av_log(ctx, AV_LOG_INFO, " crop = %s\n", tc->conf.crop ? "Black" : "Keep");

200 av_log(ctx, AV_LOG_INFO, " relative = %s\n", tc->conf.relative ? "True": "False");

201 av_log(ctx, AV_LOG_INFO, " invert = %s\n", tc->conf.invert ? "True" : "False");

202 av_log(ctx, AV_LOG_INFO, " zoom = %f\n", tc->conf.zoom);

203 av_log(ctx, AV_LOG_INFO, " optzoom = %s\n",

204 tc->conf.optZoom == 1 ? "Static (1)" : (tc->conf.optZoom == 2 ? "Dynamic (2)" : "Off (0)"));

205 if (tc->conf.optZoom == 2)

206 av_log(ctx, AV_LOG_INFO, " zoomspeed = %g\n", tc->conf.zoomSpeed);

207 av_log(ctx, AV_LOG_INFO, " interpol = %s\n", getInterpolationTypeName(tc->conf.interpolType));

208

209 f = fopen(tc->input, "r");

210 if (!f) {

211 av_log(ctx, AV_LOG_ERROR, "cannot open input file %s\n", tc->input);

212 return AVERROR(errno);

213 } else {

214 VSManyLocalMotions mlms;

215 if (vsReadLocalMotionsFile(f, &mlms) == VS_OK) {

216 // calculate the actual transforms from the local motions

217 if (vsLocalmotions2Transforms(td, &mlms, &tc->trans) != VS_OK) {

218 av_log(ctx, AV_LOG_ERROR, "calculating transformations failed\n");

219 return AVERROR(EINVAL);

220 }

221 } else { // try to read old format

222 if (!vsReadOldTransforms(td, f, &tc->trans)) { /* read input file */

223 av_log(ctx, AV_LOG_ERROR, "error parsing input file %s\n", tc->input);

224 return AVERROR(EINVAL);

225 }

226 }

227 }

228 fclose(f);

229

230 if (vsPreprocessTransforms(td, &tc->trans) != VS_OK) {

231 av_log(ctx, AV_LOG_ERROR, "error while preprocessing transforms\n");

232 return AVERROR(EINVAL);

233 }

234

235 // TODO: add sharpening, so far the user needs to call the unsharp filter manually

236 return 0;

237 }

238

239

240 static int filter_frame(AVFilterLink *inlink, AVFrame *in)

241 {

242 AVFilterContext *ctx = inlink->dst;

243 TransformContext *tc = ctx->priv;

244 VSTransformData* td = &(tc->td);

245

246 AVFilterLink *outlink = inlink->dst->outputs[0];

247 int direct = 0;

248 AVFrame *out;

249 VSFrame inframe;

250 int plane;

251

252 if (av_frame_is_writable(in)) {

253 direct = 1;

254 out = in;

255 } else {

256 out = ff_get_video_buffer(outlink, outlink->w, outlink->h);

257 if (!out) {

258 av_frame_free(&in);

259 return AVERROR(ENOMEM);

260 }

261 av_frame_copy_props(out, in);

262 }

263

264 for (plane = 0; plane < vsTransformGetSrcFrameInfo(td)->planes; plane++) {

265 inframe.data[plane] = in->data[plane];

266 inframe.linesize[plane] = in->linesize[plane];

267 }

268 if (direct) {

269 vsTransformPrepare(td, &inframe, &inframe);

270 } else { // separate frames

271 VSFrame outframe;

272 for (plane = 0; plane < vsTransformGetDestFrameInfo(td)->planes; plane++) {

273 outframe.data[plane] = out->data[plane];

274 outframe.linesize[plane] = out->linesize[plane];

275 }

276 vsTransformPrepare(td, &inframe, &outframe);

277 }

278

279 vsDoTransform(td, vsGetNextTransform(td, &tc->trans));

280

281 vsTransformFinish(td);

282

283 if (!direct)

284 av_frame_free(&in);

285

286 return ff_filter_frame(outlink, out);

287 }

288

289 static const AVFilterPad avfilter_vf_vidstabtransform_inputs[] = {

290 {

291 .name = "default",

292 .type = AVMEDIA_TYPE_VIDEO,

293 .filter_frame = filter_frame,

294 .config_props = config_input,

295 },

296 { NULL }

297 };

298

299 static const AVFilterPad avfilter_vf_vidstabtransform_outputs[] = {

300 {

301 .name = "default",

302 .type = AVMEDIA_TYPE_VIDEO,

303 },

304 { NULL }

305 };

306

307 AVFilter ff_vf_vidstabtransform = {

308 .name = "vidstabtransform",

309 .description = NULL_IF_CONFIG_SMALL("Transform the frames, "

310 "pass 2 of 2 for stabilization "

311 "(see vidstabdetect for pass 1)."),

312 .priv_size = sizeof(TransformContext),

313 .init = init,

314 .uninit = uninit,

315 .query_formats = query_formats,

316 .inputs = avfilter_vf_vidstabtransform_inputs,

317 .outputs = avfilter_vf_vidstabtransform_outputs,

318 .priv_class = &vidstabtransform_class,

319 };

Generated on Sun Sep 14 2014 18:56:11 for FFmpeg by doxygen 1.8.2