[FFmpeg-devel] delogo filter: new "uglarm" interpolation mode added

Submitted by Uwe Freese on Dec. 26, 2018, 5:21 p.m.

Details

Message ID e58c282e-0524-2501-a495-07e63c94d2a9@gmx.de
State New
Headers show

Commit Message

Uwe Freese Dec. 26, 2018, 5:21 p.m.
Hello,

attached you can find a new patch, with no trailing spaces and avoiding 
additional indentation in existing code.

Regards,
Uwe

Am 26.12.18 um 16:48 schrieb Uwe Freese:
> Hello,
>>> so now I've taken the time to integrate the alternative 
>>> interpolation algorithm 'uglarm' into the delogo filter.
>> Please do not re-indent existing code in this patch as this makes 
>> reviewing the changes more difficult
>
> Parts of the previous code are now in an "if" statement block 
> (function apply_delogo), so indentation is correct. Even it would 
> maybe be better to read the diff, it wouldn't be correctly indented.
>
> In the parameter lists, spaces are added to have the same layout of 
> the descriptions in the right part for all lines.
>
> So what should I do in this case?
>
> I could create a diff of course with "wrong" indentation (not 
> correctly indented and not good to read in the final file, but the 
> diff is better to read...). Would this help for the first review?
>
>>   and please do not add trailing white space as it cannot be 
>> committed to our git repository.
>
> OK, I'll remove them, no problem. (I'll send a new patch to this list 
> after I know how to handle also the first point.)
>
>> (I did not check if you are possibly changing the license of code you 
>> did not write yourself, please be extra careful to make sure this 
>> does not happen.)
>
> The TimgFilterLogoaway.cpp from ffdshow also has GPL 2 and up, the 
> same as vf_delogo.c from ffmpeg. -> OK.
>
> https://sourceforge.net/p/ffdshow-tryout/code/HEAD/tree/trunk/src/imgFilters/TimgFilterLogoaway.cpp 
>
>
> Regards,
> Uwe
>
> _______________________________________________
> ffmpeg-devel mailing list
> ffmpeg-devel@ffmpeg.org
> http://ffmpeg.org/mailman/listinfo/ffmpeg-devel

Patch hide | download patch | download mbox

From 221ecf222eb855303055a32bdc27ca8885217a2c Mon Sep 17 00:00:00 2001
From: breaker27 <mail@uwe-freese.de>
Date: Wed, 26 Dec 2018 18:16:48 +0100
Subject: [PATCH] Add new delogo interpolation mode uglarm.

---
 libavfilter/vf_delogo.c | 182 +++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 173 insertions(+), 9 deletions(-)

diff --git a/libavfilter/vf_delogo.c b/libavfilter/vf_delogo.c
index 065d093641..608cff2e4d 100644
--- a/libavfilter/vf_delogo.c
+++ b/libavfilter/vf_delogo.c
@@ -2,6 +2,7 @@ 
  * Copyright (c) 2002 Jindrich Makovicka <makovick@gmail.com>
  * Copyright (c) 2011 Stefano Sabatini
  * Copyright (c) 2013, 2015 Jean Delvare <jdelvare@suse.com>
+ * Copyright (c) 2019 Uwe Freese <mail@uwe-freese.de>
  *
  * This file is part of FFmpeg.
  *
@@ -25,6 +26,9 @@ 
  * A very simple tv station logo remover
  * Originally imported from MPlayer libmpcodecs/vf_delogo.c,
  * the algorithm was later improved.
+ * The "UGLARM" mode was first implemented 2001 by Uwe Freese for Virtual
+ * Dub's LogoAway filter (by Krzysztof Wojdon), taken over into ffdshow's
+ * logoaway filter (by Milan Cutka), from where it was ported to ffmpeg.
  */
 
 #include "libavutil/common.h"
@@ -50,6 +54,10 @@ 
  * @param logo_w width of the logo
  * @param logo_h height of the logo
  * @param band   the size of the band around the processed area
+ * @param *uglarmtable      pointer to weight table in UGLARM interpolation mode,
+ *                          zero when x-y mode is used
+ * @param *uglarmweightsum  pointer to weight sum table in UGLARM interpolation mode,
+ *                          zero when x-y mode is used
  * @param show   show a rectangle around the processed area, useful for
  *               parameters tweaking
  * @param direct if non-zero perform in-place processing
@@ -58,7 +66,8 @@  static void apply_delogo(uint8_t *dst, int dst_linesize,
                          uint8_t *src, int src_linesize,
                          int w, int h, AVRational sar,
                          int logo_x, int logo_y, int logo_w, int logo_h,
-                         unsigned int band, int show, int direct)
+                         unsigned int band, double *uglarmtable,
+                         double *uglarmweightsum, int show, int direct)
 {
     int x, y;
     uint64_t interp, weightl, weightr, weightt, weightb, weight;
@@ -89,6 +98,7 @@  static void apply_delogo(uint8_t *dst, int dst_linesize,
     dst += (logo_y1 + 1) * dst_linesize;
     src += (logo_y1 + 1) * src_linesize;
 
+    if (!uglarmtable) {
     for (y = logo_y1+1; y < logo_y2; y++) {
         left_sample = topleft[src_linesize*(y-logo_y1)]   +
                       topleft[src_linesize*(y-logo_y1-1)] +
@@ -151,12 +161,121 @@  static void apply_delogo(uint8_t *dst, int dst_linesize,
         dst += dst_linesize;
         src += src_linesize;
     }
+    } else {
+        int bx, by;
+        double interpd;
+
+        for (y = logo_y1 + 1; y < logo_y2; y++) {
+            for (x = logo_x1 + 1,
+                xdst = dst + logo_x1 + 1,
+                xsrc = src + logo_x1 + 1; x < logo_x2; x++, xdst++, xsrc++) {
+
+                if (show && (y == logo_y1 + 1 || y == logo_y2 - 1 ||
+                            x == logo_x1 + 1 || x == logo_x2 - 1)) {
+                    *xdst = 0;
+                    continue;
+                }
+
+                interpd = 0;
+
+                for (bx = 0; bx < logo_w; bx++) {
+                    interpd += topleft[bx] *
+                        uglarmtable[abs(bx - (x - logo_x1)) + (y - logo_y1) * (logo_w - 1)];
+                    interpd += botleft[bx] *
+                        uglarmtable[abs(bx - (x - logo_x1)) + (logo_h - (y - logo_y1) - 1) * (logo_w - 1)];
+                }
+
+                for (by = 1; by < logo_h - 1; by++) {
+                    interpd += topleft[by * src_linesize] *
+                        uglarmtable[(x - logo_x1) + abs(by - (y - logo_y1)) * (logo_w - 1)];
+                    interpd += topleft[by * src_linesize + (logo_w - 1)] *
+                        uglarmtable[logo_w - (x - logo_x1) - 1 + abs(by - (y - logo_y1)) * (logo_w - 1)];
+                }
+
+                interp = (uint64_t)(interpd /
+                    uglarmweightsum[(x - logo_x1) - 1 + (y - logo_y1 - 1) * (logo_w - 2)]);
+                *xdst = interp;
+            }
+
+            dst += dst_linesize;
+            src += src_linesize;
+        }
+    }
+}
+
+/**
+ * Calculate the lookup tables to be used in UGLARM interpolation mode.
+ *
+ * @param *uglarmtable      Pointer to table containing weigths for each possible
+ *                          diagonal distance between a border pixel and an inner
+ *                          logo pixel.
+ * @param *uglarmweightsum  Pointer to a table containing the weight sum to divide
+ *                          by for each pixel within the logo area.
+ * @param sar               The sar to take into account when calculating lookup
+ *                          tables.
+ * @param logo_w            width of the logo
+ * @param logo_h            height of the logo
+ * @param power             power of uglarm interpolation
+ */
+static void calcUGLARMTables(double *uglarmtable, double *uglarmweightsum,
+                             AVRational sar, int logo_w, int logo_h, int power)
+{
+    double e = 0.2 * power;
+    double aspect = (double)sar.num / sar.den;
+    int x, y;
+
+    /* uglarmtable will contain a weigth for each possible diagonal distance
+     * between a border pixel and an inner logo pixel. The maximum distance in
+     * each direction between border and an inner pixel can be logo_w - 1. The
+     * weight of a border pixel which is x,y pixels away is stored at position
+     * x + y * (logo_w - 1). */
+    for (y = 0; y < logo_h - 1; y++)
+        for (x = 0; x < logo_w - 1; x++) {
+            if (x + y != 0) {
+                double d = pow(sqrt((double)(x * x * aspect * aspect + y * y)), e);
+                uglarmtable[x + y * (logo_w - 1)] = 1.0 / d;
+            } else {
+                uglarmtable[x + y * (logo_w - 1)] = 1.0;
+            }
+        }
+
+    /* uglarmweithsum will conatain the sum of all weigths which is used when
+     * an inner pixel of the logo at position x,y is calculated out of the
+     * border pixels. The aggregated value has to be divided by that. The value
+     * to use for the inner 1-based logo position x,y is stored at
+     * (x - 1) + (y - 1) * (logo_w - 2). */
+    for (y = 1; y < logo_h - 1; y++)
+        for (x = 1; x < logo_w - 1; x++) {
+            double weightsum = 0;
+
+            for (int bx = 0; bx < logo_w; bx++) {
+                /* top border */
+                weightsum += uglarmtable[abs(bx - x) + y * (logo_w - 1)];
+                /* bottom border */
+                weightsum += uglarmtable[abs(bx - x) + (logo_h - y - 1) * (logo_w - 1)];
+            }
+
+            for (int by = 1; by < logo_h - 1; by++) {
+                /* left border */
+                weightsum += uglarmtable[x + abs(by - y) * (logo_w - 1)];
+                /* right border */
+                weightsum += uglarmtable[(logo_w - x - 1) + abs(by - y) * (logo_w - 1)];
+            }
+
+            uglarmweightsum[(x - 1) + (y - 1) * (logo_w - 2)] = weightsum;
+        }
 }
 
+enum mode {
+    MODE_XY,
+    MODE_UGLARM
+};
+
 typedef struct DelogoContext {
     const AVClass *class;
-    int x, y, w, h, band, show;
-}  DelogoContext;
+    int x, y, w, h, band, mode, power, show;
+    double *uglarmtable[10], *uglarmweightsum[10];
+} DelogoContext;
 
 #define OFFSET(x) offsetof(DelogoContext, x)
 #define FLAGS AV_OPT_FLAG_FILTERING_PARAM|AV_OPT_FLAG_VIDEO_PARAM
@@ -171,6 +290,10 @@  static const AVOption delogo_options[]= {
     { "band", "set delogo area band size", OFFSET(band), AV_OPT_TYPE_INT, { .i64 =  0 },  0, INT_MAX, FLAGS },
     { "t",    "set delogo area band size", OFFSET(band), AV_OPT_TYPE_INT, { .i64 =  0 },  0, INT_MAX, FLAGS },
 #endif
+    {"mode",    "set the interpolation mode",               OFFSET(mode), AV_OPT_TYPE_INT, { .i64 = MODE_XY},      0, 1, FLAGS, "mode"},
+        {"xy",     "use pixels in straight x any y direction",  OFFSET(mode), AV_OPT_TYPE_CONST, { .i64 = MODE_XY},     0, 0, FLAGS, "mode"},
+        {"uglarm", "UGLARM mode, use full border",              OFFSET(mode), AV_OPT_TYPE_CONST, { .i64 = MODE_UGLARM}, 0, 0, FLAGS, "mode"},
+    { "power",  "power of UGLARM interpolation",            OFFSET(power),  AV_OPT_TYPE_INT, { .i64 = 15 },  0,      30, FLAGS },
     { "show", "show delogo area",          OFFSET(show), AV_OPT_TYPE_BOOL,{ .i64 =  0 },  0, 1,       FLAGS },
     { NULL }
 };
@@ -215,8 +338,8 @@  static av_cold int init(AVFilterContext *ctx)
 #else
     s->band = 1;
 #endif
-    av_log(ctx, AV_LOG_VERBOSE, "x:%d y:%d, w:%d h:%d band:%d show:%d\n",
-           s->x, s->y, s->w, s->h, s->band, s->show);
+    av_log(ctx, AV_LOG_VERBOSE, "x:%d y:%d, w:%d h:%d band:%d mode:%d power:%d show:%d\n",
+           s->x, s->y, s->w, s->h, s->band, s->mode, s->power, s->show);
 
     s->w += s->band*2;
     s->h += s->band*2;
@@ -226,6 +349,21 @@  static av_cold int init(AVFilterContext *ctx)
     return 0;
 }
 
+static av_cold void uninit(AVFilterContext *ctx)
+{
+    DelogoContext *s = ctx->priv;
+
+    if (s->mode == MODE_UGLARM)
+    {
+        for (int plane = 0; plane < 10; plane++) {
+            if (s->uglarmtable[plane])
+                av_free(s->uglarmtable[plane]);
+            if (s->uglarmweightsum[plane])
+                av_free(s->uglarmweightsum[plane]);
+        }
+    }
+}
+
 static int config_input(AVFilterLink *inlink)
 {
     DelogoContext *s = inlink->dst->priv;
@@ -274,16 +412,41 @@  static int filter_frame(AVFilterLink *inlink, AVFrame *in)
         int hsub = plane == 1 || plane == 2 ? hsub0 : 0;
         int vsub = plane == 1 || plane == 2 ? vsub0 : 0;
 
+        /* Up and left borders were rounded down, inject lost bits
+        * into width and height to avoid error accumulation */
+        int logo_w = AV_CEIL_RSHIFT(s->w + (s->x & ((1<<hsub)-1)), hsub);
+        int logo_h = AV_CEIL_RSHIFT(s->h + (s->y & ((1<<vsub)-1)), vsub);
+
+        /* Init lookup tables once */
+        if ((s->mode == MODE_UGLARM) && (!s->uglarmtable[plane])) {
+            s->uglarmtable[plane] =
+                (double*)av_malloc((logo_w - 1) * (logo_h - 1) * sizeof(double));
+
+            if (!s->uglarmtable[plane]) {
+                return AVERROR(ENOMEM);
+            }
+
+            s->uglarmweightsum[plane] =
+                (double*)av_malloc((logo_w - 2) * (logo_h - 2) * sizeof(double));
+
+            if (!s->uglarmweightsum[plane]) {
+                return AVERROR(ENOMEM);
+            }
+
+            calcUGLARMTables(s->uglarmtable[plane],
+                             s->uglarmweightsum[plane],
+                             sar, logo_w, logo_h, s->power);
+        }
+
         apply_delogo(out->data[plane], out->linesize[plane],
                      in ->data[plane], in ->linesize[plane],
                      AV_CEIL_RSHIFT(inlink->w, hsub),
                      AV_CEIL_RSHIFT(inlink->h, vsub),
                      sar, s->x>>hsub, s->y>>vsub,
-                     /* Up and left borders were rounded down, inject lost bits
-                      * into width and height to avoid error accumulation */
-                     AV_CEIL_RSHIFT(s->w + (s->x & ((1<<hsub)-1)), hsub),
-                     AV_CEIL_RSHIFT(s->h + (s->y & ((1<<vsub)-1)), vsub),
+                     logo_w, logo_h,
                      s->band>>FFMIN(hsub, vsub),
+                     s->uglarmtable[plane],
+                     s->uglarmweightsum[plane],
                      s->show, direct);
     }
 
@@ -317,6 +480,7 @@  AVFilter ff_vf_delogo = {
     .priv_size     = sizeof(DelogoContext),
     .priv_class    = &delogo_class,
     .init          = init,
+    .uninit        = uninit,
     .query_formats = query_formats,
     .inputs        = avfilter_vf_delogo_inputs,
     .outputs       = avfilter_vf_delogo_outputs,
-- 
2.11.0