[FFmpeg-cvslog] libavfi: added option to vf_perspective to specify transformation by giving destinations of corners of source.

Nicholas Robbins git at videolan.org
Sun Oct 19 18:18:58 CEST 2014


ffmpeg | branch: master | Nicholas Robbins <nickrobbins-at-yahoo.com at ffmpeg.org> | Sun Oct 19 09:20:22 2014 -0400| [22cfa1f759ac5e3b7a62f3b5d0cd88f5fd1e399f] | committer: Michael Niedermayer

libavfi: added option to vf_perspective to specify transformation by giving destinations of corners of source.

Signed-off-by: Nicholas Robbins <nickrobbins at yahoo.com>
Signed-off-by: Michael Niedermayer <michaelni at gmx.at>

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=22cfa1f759ac5e3b7a62f3b5d0cd88f5fd1e399f
---

 doc/filters.texi             |   21 +++++++++++
 libavfilter/vf_perspective.c |   85 ++++++++++++++++++++++++++++++++----------
 2 files changed, 86 insertions(+), 20 deletions(-)

diff --git a/doc/filters.texi b/doc/filters.texi
index b847635..c612052 100644
--- a/doc/filters.texi
+++ b/doc/filters.texi
@@ -6718,6 +6718,9 @@ A description of the accepted parameters follows.
 @item y3
 Set coordinates expression for top left, top right, bottom left and bottom right corners.
 Default values are @code{0:0:W:0:0:H:W:H} with which perspective will remain unchanged.
+If the @code{sense} option is set to @code{source}, then the specified points will be sent
+to the corners of the destination. If the @code{sense} option is set to @code{destination},
+then the corners of the source will be sent to the specified coordinates.
 
 The expressions can use the following variables:
 
@@ -6737,6 +6740,24 @@ It accepts the following values:
 @end table
 
 Default value is @samp{linear}.
+
+ at item sense
+Set interpretation of coordinate options.
+
+It accepts the following values:
+ at table @samp
+ at item 0, source
+
+Send point in the source specified by the given coordinates to
+the corners of the destination.
+
+ at item 1, destination
+
+Send the corners of the source to the point in the destination specified
+by the given coordinates.
+
+Default value is @samp{source}.
+ at end table
 @end table
 
 @section phase
diff --git a/libavfilter/vf_perspective.c b/libavfilter/vf_perspective.c
index a796bd4..bf06d02 100644
--- a/libavfilter/vf_perspective.c
+++ b/libavfilter/vf_perspective.c
@@ -46,6 +46,7 @@ typedef struct PerspectiveContext {
     int height[4];
     int hsub, vsub;
     int nb_planes;
+    int sense;
 
     int (*perspective)(AVFilterContext *ctx,
                        void *arg, int job, int nb_jobs);
@@ -54,6 +55,11 @@ typedef struct PerspectiveContext {
 #define OFFSET(x) offsetof(PerspectiveContext, x)
 #define FLAGS AV_OPT_FLAG_FILTERING_PARAM|AV_OPT_FLAG_VIDEO_PARAM
 
+enum PERSPECTIVESense {
+    PERSPECTIVE_SENSE_SOURCE      = 0, ///< coordinates give locations in source of corners of destination.
+    PERSPECTIVE_SENSE_DESTINATION = 1, ///< coordinates give locations in destination of corners of source.
+};
+
 static const AVOption perspective_options[] = {
     { "x0", "set top left x coordinate",     OFFSET(expr_str[0][0]), AV_OPT_TYPE_STRING, {.str="0"}, 0, 0, FLAGS },
     { "y0", "set top left y coordinate",     OFFSET(expr_str[0][1]), AV_OPT_TYPE_STRING, {.str="0"}, 0, 0, FLAGS },
@@ -66,6 +72,12 @@ static const AVOption perspective_options[] = {
     { "interpolation", "set interpolation", OFFSET(interpolation), AV_OPT_TYPE_INT, {.i64=LINEAR}, 0, 1, FLAGS, "interpolation" },
     {      "linear", "", 0, AV_OPT_TYPE_CONST, {.i64=LINEAR}, 0, 0, FLAGS, "interpolation" },
     {       "cubic", "", 0, AV_OPT_TYPE_CONST, {.i64=CUBIC},  0, 0, FLAGS, "interpolation" },
+    { "sense",   "specify the sense of the coordinates", OFFSET(sense), AV_OPT_TYPE_INT, {.i64=PERSPECTIVE_SENSE_SOURCE}, 0, 1, FLAGS, "sense"},
+    {       "source", "specify locations in source to send to corners in destination",
+                0, AV_OPT_TYPE_CONST, {.i64=PERSPECTIVE_SENSE_SOURCE}, 0, 0, FLAGS, "sense"},
+    {       "destination", "specify locations in destination to send corners of source",
+                0, AV_OPT_TYPE_CONST, {.i64=PERSPECTIVE_SENSE_DESTINATION}, 0, 0, FLAGS, "sense"},
+
     { NULL }
 };
 
@@ -105,7 +117,8 @@ enum                                   { VAR_W, VAR_H, VAR_VARS_NB };
 
 static int config_input(AVFilterLink *inlink)
 {
-    double x0, x1, x2, x3, x4, x5, x6, x7, q;
+    double x0, x1, x2, x3, x4, x5, x6, x7, x8, q;
+    double t0, t1, t2, t3;
     AVFilterContext *ctx = inlink->dst;
     PerspectiveContext *s = ctx->priv;
     double (*ref)[2] = s->ref;
@@ -141,32 +154,64 @@ static int config_input(AVFilterLink *inlink)
     if (!s->pv)
         return AVERROR(ENOMEM);
 
-    x6 = ((ref[0][0] - ref[1][0] - ref[2][0] + ref[3][0]) *
-          (ref[2][1] - ref[3][1]) -
-         ( ref[0][1] - ref[1][1] - ref[2][1] + ref[3][1]) *
-          (ref[2][0] - ref[3][0])) * h;
-    x7 = ((ref[0][1] - ref[1][1] - ref[2][1] + ref[3][1]) *
-          (ref[1][0] - ref[3][0]) -
-         ( ref[0][0] - ref[1][0] - ref[2][0] + ref[3][0]) *
-          (ref[1][1] - ref[3][1])) * w;
-    q =  ( ref[1][0] - ref[3][0]) * (ref[2][1] - ref[3][1]) -
-         ( ref[2][0] - ref[3][0]) * (ref[1][1] - ref[3][1]);
-
-    x0 = q * (ref[1][0] - ref[0][0]) * h + x6 * ref[1][0];
-    x1 = q * (ref[2][0] - ref[0][0]) * w + x7 * ref[2][0];
-    x2 = q *  ref[0][0] * w * h;
-    x3 = q * (ref[1][1] - ref[0][1]) * h + x6 * ref[1][1];
-    x4 = q * (ref[2][1] - ref[0][1]) * w + x7 * ref[2][1];
-    x5 = q *  ref[0][1] * w * h;
+    switch (s->sense) {
+    case PERSPECTIVE_SENSE_SOURCE:
+        x6 = ((ref[0][0] - ref[1][0] - ref[2][0] + ref[3][0]) *
+              (ref[2][1] - ref[3][1]) -
+             ( ref[0][1] - ref[1][1] - ref[2][1] + ref[3][1]) *
+              (ref[2][0] - ref[3][0])) * h;
+        x7 = ((ref[0][1] - ref[1][1] - ref[2][1] + ref[3][1]) *
+              (ref[1][0] - ref[3][0]) -
+             ( ref[0][0] - ref[1][0] - ref[2][0] + ref[3][0]) *
+              (ref[1][1] - ref[3][1])) * w;
+        q =  ( ref[1][0] - ref[3][0]) * (ref[2][1] - ref[3][1]) -
+             ( ref[2][0] - ref[3][0]) * (ref[1][1] - ref[3][1]);
+
+        x0 = q * (ref[1][0] - ref[0][0]) * h + x6 * ref[1][0];
+        x1 = q * (ref[2][0] - ref[0][0]) * w + x7 * ref[2][0];
+        x2 = q *  ref[0][0] * w * h;
+        x3 = q * (ref[1][1] - ref[0][1]) * h + x6 * ref[1][1];
+        x4 = q * (ref[2][1] - ref[0][1]) * w + x7 * ref[2][1];
+        x5 = q *  ref[0][1] * w * h;
+        x8 = q * w * h;
+        break;
+    case PERSPECTIVE_SENSE_DESTINATION:
+        t0 = ref[0][0] * (ref[3][1] - ref[1][1]) +
+             ref[1][0] * (ref[0][1] - ref[3][1]) +
+             ref[3][0] * (ref[1][1] - ref[0][1]);
+        t1 = ref[1][0] * (ref[2][1] - ref[3][1]) +
+             ref[2][0] * (ref[3][1] - ref[1][1]) +
+             ref[3][0] * (ref[1][1] - ref[2][1]);
+        t2 = ref[0][0] * (ref[3][1] - ref[2][1]) +
+             ref[2][0] * (ref[0][1] - ref[3][1]) +
+             ref[3][0] * (ref[2][1] - ref[0][1]);
+        t3 = ref[0][0] * (ref[1][1] - ref[2][1]) +
+             ref[1][0] * (ref[2][1] - ref[0][1]) +
+             ref[2][0] * (ref[0][1] - ref[1][1]);
+
+        x0 = t0 * t1 * w * (ref[2][1] - ref[0][1]);
+        x1 = t0 * t1 * w * (ref[0][0] - ref[2][0]);
+        x2 = t0 * t1 * w * (ref[0][1] * ref[2][0] - ref[0][0] * ref[2][1]);
+        x3 = t1 * t2 * h * (ref[1][1] - ref[0][1]);
+        x4 = t1 * t2 * h * (ref[0][0] - ref[1][0]);
+        x5 = t1 * t2 * h * (ref[0][1] * ref[1][0] - ref[0][0] * ref[1][1]);
+        x6 = t1 * t2 * (ref[1][1] - ref[0][1]) +
+             t0 * t3 * (ref[2][1] - ref[3][1]);
+        x7 = t1 * t2 * (ref[0][0] - ref[1][0]) +
+             t0 * t3 * (ref[3][0] - ref[2][0]);
+        x8 = t1 * t2 * (ref[0][1] * ref[1][0] - ref[0][0] * ref[1][1]) +
+             t0 * t3 * (ref[2][0] * ref[3][1] - ref[2][1] * ref[3][0]);
+        break;
+    }
 
     for (y = 0; y < h; y++){
         for (x = 0; x < w; x++){
             int u, v;
 
             u = (int)floor(SUB_PIXELS * (x0 * x + x1 * y + x2) /
-                                        (x6 * x + x7 * y + q * w * h) + 0.5);
+                                        (x6 * x + x7 * y + x8) + 0.5);
             v = (int)floor(SUB_PIXELS * (x3 * x + x4 * y + x5) /
-                                        (x6 * x + x7 * y + q * w * h) + 0.5);
+                                        (x6 * x + x7 * y + x8) + 0.5);
 
             s->pv[x + y * w][0] = u;
             s->pv[x + y * w][1] = v;



More information about the ffmpeg-cvslog mailing list