[FFmpeg-devel,v2,1/3] lavf/f_select: support scenecut with more pixel formats

Submitted by lance.lmwang@gmail.com on July 19, 2019, 11:18 a.m.

Details

Message ID 20190719111848.9009-1-lance.lmwang@gmail.com
State New
Headers show

Commit Message

lance.lmwang@gmail.com July 19, 2019, 11:18 a.m.
From: Limin Wang <lance.lmwang@gmail.com>

This patch haven't make other pixel format usable yet to make sure the test
result is same with rgb32 format.

Signed-off-by: Limin Wang <lance.lmwang@gmail.com>
---
 libavfilter/f_select.c | 34 ++++++++++++++++++++++++++++++----
 1 file changed, 30 insertions(+), 4 deletions(-)

Comments

Marton Balint July 19, 2019, 7:26 p.m.
On Fri, 19 Jul 2019, lance.lmwang@gmail.com wrote:

> From: Limin Wang <lance.lmwang@gmail.com>
>
> This patch haven't make other pixel format usable yet to make sure the test
> result is same with rgb32 format.
>
> Signed-off-by: Limin Wang <lance.lmwang@gmail.com>
> ---
> libavfilter/f_select.c | 34 ++++++++++++++++++++++++++++++----
> 1 file changed, 30 insertions(+), 4 deletions(-)
>
> diff --git a/libavfilter/f_select.c b/libavfilter/f_select.c
> index 1132375758..eed8df34cb 100644
> --- a/libavfilter/f_select.c
> +++ b/libavfilter/f_select.c
> @@ -28,6 +28,8 @@
> #include "libavutil/fifo.h"
> #include "libavutil/internal.h"
> #include "libavutil/opt.h"
> +#include "libavutil/imgutils.h"
> +#include "libavutil/pixdesc.h"
> #include "avfilter.h"
> #include "audio.h"
> #include "formats.h"
> @@ -144,6 +146,10 @@ typedef struct SelectContext {
>     char *expr_str;
>     AVExpr *expr;
>     double var_values[VAR_VARS_NB];
> +    int bitdepth;
> +    int nb_planes;
> +    ptrdiff_t width[4];
> +    ptrdiff_t height[4];
>     int do_scene_detect;            ///< 1 if the expression requires scene detection variables, 0 otherwise
>     ff_scene_sad_fn sad;            ///< Sum of the absolute difference function (scene detect only)
>     double prev_mafd;               ///< previous MAFD                           (scene detect only)
> @@ -202,6 +208,17 @@ static av_cold int init(AVFilterContext *ctx)
> static int config_input(AVFilterLink *inlink)
> {
>     SelectContext *select = inlink->dst->priv;
> +    const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(inlink->format);
> +
> +    select->bitdepth = desc->comp[0].depth;
> +    select->nb_planes = av_pix_fmt_count_planes(inlink->format);
> +    for (int plane = 0; plane < select->nb_planes; plane++) {
> +        ptrdiff_t line_size = av_image_get_linesize(inlink->format, inlink->w, plane);
> +        int vsub = desc->log2_chroma_h;
> +
> +        select->width[plane] = line_size >> (select->bitdepth > 8);
> +        select->height[plane] = plane == 1 || plane == 2 ?  AV_CEIL_RSHIFT(inlink->h, vsub) : inlink->h;
> +    }
>
>     select->var_values[VAR_N]          = 0.0;
>     select->var_values[VAR_SELECTED_N] = 0.0;
> @@ -242,7 +259,7 @@ static int config_input(AVFilterLink *inlink)
>         inlink->type == AVMEDIA_TYPE_AUDIO ? inlink->sample_rate : NAN;
>
>     if (CONFIG_SELECT_FILTER && select->do_scene_detect) {
> -        select->sad = ff_scene_sad_get_fn(8);
> +        select->sad = ff_scene_sad_get_fn(select->bitdepth == 8 ? 8 : 16);
>         if (!select->sad)
>             return AVERROR(EINVAL);
>     }
> @@ -258,12 +275,21 @@ static double get_scene_score(AVFilterContext *ctx, AVFrame *frame)
>     if (prev_picref &&
>         frame->height == prev_picref->height &&
>         frame->width  == prev_picref->width) {
> -        uint64_t sad;
> +        uint64_t sad = 0;
>         double mafd, diff;
> +        int count = 0;
> +
> +        for (int plane = 0; plane < select->nb_planes; plane++) {
> +            uint64_t plane_sad;
> +            select->sad(prev_picref->data[plane], prev_picref->linesize[plane],
> +                    frame->data[plane], frame->linesize[plane],
> +                    select->width[plane], select->height[plane], &plane_sad);
> +            sad += plane_sad;
> +            count += select->width[plane] * select->height[plane];
> +        }
> 
> -        select->sad(prev_picref->data[0], prev_picref->linesize[0], frame->data[0], frame->linesize[0], frame->width * 3, frame->height, &sad);
>         emms_c();
> -        mafd = (double)sad / (frame->width * 3 * frame->height);
> +        mafd = (double)sad / count;

Still missing normalization to [0..255] here for >8 bitdepth.

Regards,
Marton
lance.lmwang@gmail.com July 19, 2019, 10:27 p.m.
On Fri, Jul 19, 2019 at 09:26:06PM +0200, Marton Balint wrote:
> 
> 
> On Fri, 19 Jul 2019, lance.lmwang@gmail.com wrote:
> 
> >From: Limin Wang <lance.lmwang@gmail.com>
> >
> >This patch haven't make other pixel format usable yet to make sure the test
> >result is same with rgb32 format.
> >
> >Signed-off-by: Limin Wang <lance.lmwang@gmail.com>
> >---
> >libavfilter/f_select.c | 34 ++++++++++++++++++++++++++++++----
> >1 file changed, 30 insertions(+), 4 deletions(-)
> >
> >diff --git a/libavfilter/f_select.c b/libavfilter/f_select.c
> >index 1132375758..eed8df34cb 100644
> >--- a/libavfilter/f_select.c
> >+++ b/libavfilter/f_select.c
> >@@ -28,6 +28,8 @@
> >#include "libavutil/fifo.h"
> >#include "libavutil/internal.h"
> >#include "libavutil/opt.h"
> >+#include "libavutil/imgutils.h"
> >+#include "libavutil/pixdesc.h"
> >#include "avfilter.h"
> >#include "audio.h"
> >#include "formats.h"
> >@@ -144,6 +146,10 @@ typedef struct SelectContext {
> >    char *expr_str;
> >    AVExpr *expr;
> >    double var_values[VAR_VARS_NB];
> >+    int bitdepth;
> >+    int nb_planes;
> >+    ptrdiff_t width[4];
> >+    ptrdiff_t height[4];
> >    int do_scene_detect;            ///< 1 if the expression requires scene detection variables, 0 otherwise
> >    ff_scene_sad_fn sad;            ///< Sum of the absolute difference function (scene detect only)
> >    double prev_mafd;               ///< previous MAFD                           (scene detect only)
> >@@ -202,6 +208,17 @@ static av_cold int init(AVFilterContext *ctx)
> >static int config_input(AVFilterLink *inlink)
> >{
> >    SelectContext *select = inlink->dst->priv;
> >+    const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(inlink->format);
> >+
> >+    select->bitdepth = desc->comp[0].depth;
> >+    select->nb_planes = av_pix_fmt_count_planes(inlink->format);
> >+    for (int plane = 0; plane < select->nb_planes; plane++) {
> >+        ptrdiff_t line_size = av_image_get_linesize(inlink->format, inlink->w, plane);
> >+        int vsub = desc->log2_chroma_h;
> >+
> >+        select->width[plane] = line_size >> (select->bitdepth > 8);
> >+        select->height[plane] = plane == 1 || plane == 2 ?  AV_CEIL_RSHIFT(inlink->h, vsub) : inlink->h;
> >+    }
> >
> >    select->var_values[VAR_N]          = 0.0;
> >    select->var_values[VAR_SELECTED_N] = 0.0;
> >@@ -242,7 +259,7 @@ static int config_input(AVFilterLink *inlink)
> >        inlink->type == AVMEDIA_TYPE_AUDIO ? inlink->sample_rate : NAN;
> >
> >    if (CONFIG_SELECT_FILTER && select->do_scene_detect) {
> >-        select->sad = ff_scene_sad_get_fn(8);
> >+        select->sad = ff_scene_sad_get_fn(select->bitdepth == 8 ? 8 : 16);
> >        if (!select->sad)
> >            return AVERROR(EINVAL);
> >    }
> >@@ -258,12 +275,21 @@ static double get_scene_score(AVFilterContext *ctx, AVFrame *frame)
> >    if (prev_picref &&
> >        frame->height == prev_picref->height &&
> >        frame->width  == prev_picref->width) {
> >-        uint64_t sad;
> >+        uint64_t sad = 0;
> >        double mafd, diff;
> >+        int count = 0;
> >+
> >+        for (int plane = 0; plane < select->nb_planes; plane++) {
> >+            uint64_t plane_sad;
> >+            select->sad(prev_picref->data[plane], prev_picref->linesize[plane],
> >+                    frame->data[plane], frame->linesize[plane],
> >+                    select->width[plane], select->height[plane], &plane_sad);
> >+            sad += plane_sad;
> >+            count += select->width[plane] * select->height[plane];
> >+        }
> >
> >-        select->sad(prev_picref->data[0], prev_picref->linesize[0], frame->data[0], frame->linesize[0], frame->width * 3, frame->height, &sad);
> >        emms_c();
> >-        mafd = (double)sad / (frame->width * 3 * frame->height);
> >+        mafd = (double)sad / count;
> 
> Still missing normalization to [0..255] here for >8 bitdepth.
By the testing, Passengers_Breakfast_4K.mkv is 10bits sample, it can't detect the scenecut if using 1<<bitdepth, 
Or just remove yuv420p10 support, it's the only 10bit enable pixel format in the 3/3 patch?
After get more sample for testing it's OK, then change for bitdepth > 8. 



> 
> Regards,
> Marton
> _______________________________________________
> ffmpeg-devel mailing list
> ffmpeg-devel@ffmpeg.org
> https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
> 
> To unsubscribe, visit link above, or email
> ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
Marton Balint July 20, 2019, 7:36 p.m.
On Sat, 20 Jul 2019, Limin Wang wrote:

> On Fri, Jul 19, 2019 at 09:26:06PM +0200, Marton Balint wrote:
>> 
>> 
>> On Fri, 19 Jul 2019, lance.lmwang@gmail.com wrote:
>> 
>> >From: Limin Wang <lance.lmwang@gmail.com>
>> >
>> >This patch haven't make other pixel format usable yet to make sure the test
>> >result is same with rgb32 format.
>> >
>> >Signed-off-by: Limin Wang <lance.lmwang@gmail.com>
>> >---
>> >libavfilter/f_select.c | 34 ++++++++++++++++++++++++++++++----
>> >1 file changed, 30 insertions(+), 4 deletions(-)
>> >
>> >diff --git a/libavfilter/f_select.c b/libavfilter/f_select.c
>> >index 1132375758..eed8df34cb 100644
>> >--- a/libavfilter/f_select.c
>> >+++ b/libavfilter/f_select.c
>> >@@ -28,6 +28,8 @@
>> >#include "libavutil/fifo.h"
>> >#include "libavutil/internal.h"
>> >#include "libavutil/opt.h"
>> >+#include "libavutil/imgutils.h"
>> >+#include "libavutil/pixdesc.h"
>> >#include "avfilter.h"
>> >#include "audio.h"
>> >#include "formats.h"
>> >@@ -144,6 +146,10 @@ typedef struct SelectContext {
>> >    char *expr_str;
>> >    AVExpr *expr;
>> >    double var_values[VAR_VARS_NB];
>> >+    int bitdepth;
>> >+    int nb_planes;
>> >+    ptrdiff_t width[4];
>> >+    ptrdiff_t height[4];
>> >    int do_scene_detect;            ///< 1 if the expression requires scene detection variables, 0 otherwise
>> >    ff_scene_sad_fn sad;            ///< Sum of the absolute difference function (scene detect only)
>> >    double prev_mafd;               ///< previous MAFD                           (scene detect only)
>> >@@ -202,6 +208,17 @@ static av_cold int init(AVFilterContext *ctx)
>> >static int config_input(AVFilterLink *inlink)
>> >{
>> >    SelectContext *select = inlink->dst->priv;
>> >+    const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(inlink->format);
>> >+
>> >+    select->bitdepth = desc->comp[0].depth;
>> >+    select->nb_planes = av_pix_fmt_count_planes(inlink->format);
>> >+    for (int plane = 0; plane < select->nb_planes; plane++) {
>> >+        ptrdiff_t line_size = av_image_get_linesize(inlink->format, inlink->w, plane);
>> >+        int vsub = desc->log2_chroma_h;
>> >+
>> >+        select->width[plane] = line_size >> (select->bitdepth > 8);
>> >+        select->height[plane] = plane == 1 || plane == 2 ?  AV_CEIL_RSHIFT(inlink->h, vsub) : inlink->h;
>> >+    }
>> >
>> >    select->var_values[VAR_N]          = 0.0;
>> >    select->var_values[VAR_SELECTED_N] = 0.0;
>> >@@ -242,7 +259,7 @@ static int config_input(AVFilterLink *inlink)
>> >        inlink->type == AVMEDIA_TYPE_AUDIO ? inlink->sample_rate : NAN;
>> >
>> >    if (CONFIG_SELECT_FILTER && select->do_scene_detect) {
>> >-        select->sad = ff_scene_sad_get_fn(8);
>> >+        select->sad = ff_scene_sad_get_fn(select->bitdepth == 8 ? 8 : 16);
>> >        if (!select->sad)
>> >            return AVERROR(EINVAL);
>> >    }
>> >@@ -258,12 +275,21 @@ static double get_scene_score(AVFilterContext *ctx, AVFrame *frame)
>> >    if (prev_picref &&
>> >        frame->height == prev_picref->height &&
>> >        frame->width  == prev_picref->width) {
>> >-        uint64_t sad;
>> >+        uint64_t sad = 0;
>> >        double mafd, diff;
>> >+        int count = 0;
>> >+
>> >+        for (int plane = 0; plane < select->nb_planes; plane++) {
>> >+            uint64_t plane_sad;
>> >+            select->sad(prev_picref->data[plane], prev_picref->linesize[plane],
>> >+                    frame->data[plane], frame->linesize[plane],
>> >+                    select->width[plane], select->height[plane], &plane_sad);
>> >+            sad += plane_sad;
>> >+            count += select->width[plane] * select->height[plane];
>> >+        }
>> >
>> >-        select->sad(prev_picref->data[0], prev_picref->linesize[0], frame->data[0], frame->linesize[0], frame->width * 3, frame->height, &sad);
>> >        emms_c();
>> >-        mafd = (double)sad / (frame->width * 3 * frame->height);
>> >+        mafd = (double)sad / count;
>> 
>> Still missing normalization to [0..255] here for >8 bitdepth.
> By the testing, Passengers_Breakfast_4K.mkv is 10bits sample, it can't detect the scenecut if using 1<<bitdepth,

You should divide by (1 << (bitdepth - 8)), since you should be 
normalizing to 0..255 here.

> Or just remove yuv420p10 support, it's the only 10bit enable pixel format in the 3/3 patch?
> After get more sample for testing it's OK, then change for bitdepth > 8

You should get the same scores for 10bit and 8bit. (e.g. YUV420P and 
YUV420P10).

Regards,
Marton
lance.lmwang@gmail.com July 20, 2019, 11:31 p.m.
On Sat, Jul 20, 2019 at 09:36:37PM +0200, Marton Balint wrote:
> 
> 
> On Sat, 20 Jul 2019, Limin Wang wrote:
> 
> >On Fri, Jul 19, 2019 at 09:26:06PM +0200, Marton Balint wrote:
> >>
> >>
> >>On Fri, 19 Jul 2019, lance.lmwang@gmail.com wrote:
> >>
> >>>From: Limin Wang <lance.lmwang@gmail.com>
> >>>
> >>>This patch haven't make other pixel format usable yet to make sure the test
> >>>result is same with rgb32 format.
> >>>
> >>>Signed-off-by: Limin Wang <lance.lmwang@gmail.com>
> >>>---
> >>>libavfilter/f_select.c | 34 ++++++++++++++++++++++++++++++----
> >>>1 file changed, 30 insertions(+), 4 deletions(-)
> >>>
> >>>diff --git a/libavfilter/f_select.c b/libavfilter/f_select.c
> >>>index 1132375758..eed8df34cb 100644
> >>>--- a/libavfilter/f_select.c
> >>>+++ b/libavfilter/f_select.c
> >>>@@ -28,6 +28,8 @@
> >>>#include "libavutil/fifo.h"
> >>>#include "libavutil/internal.h"
> >>>#include "libavutil/opt.h"
> >>>+#include "libavutil/imgutils.h"
> >>>+#include "libavutil/pixdesc.h"
> >>>#include "avfilter.h"
> >>>#include "audio.h"
> >>>#include "formats.h"
> >>>@@ -144,6 +146,10 @@ typedef struct SelectContext {
> >>>    char *expr_str;
> >>>    AVExpr *expr;
> >>>    double var_values[VAR_VARS_NB];
> >>>+    int bitdepth;
> >>>+    int nb_planes;
> >>>+    ptrdiff_t width[4];
> >>>+    ptrdiff_t height[4];
> >>>    int do_scene_detect;            ///< 1 if the expression requires scene detection variables, 0 otherwise
> >>>    ff_scene_sad_fn sad;            ///< Sum of the absolute difference function (scene detect only)
> >>>    double prev_mafd;               ///< previous MAFD                           (scene detect only)
> >>>@@ -202,6 +208,17 @@ static av_cold int init(AVFilterContext *ctx)
> >>>static int config_input(AVFilterLink *inlink)
> >>>{
> >>>    SelectContext *select = inlink->dst->priv;
> >>>+    const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(inlink->format);
> >>>+
> >>>+    select->bitdepth = desc->comp[0].depth;
> >>>+    select->nb_planes = av_pix_fmt_count_planes(inlink->format);
> >>>+    for (int plane = 0; plane < select->nb_planes; plane++) {
> >>>+        ptrdiff_t line_size = av_image_get_linesize(inlink->format, inlink->w, plane);
> >>>+        int vsub = desc->log2_chroma_h;
> >>>+
> >>>+        select->width[plane] = line_size >> (select->bitdepth > 8);
> >>>+        select->height[plane] = plane == 1 || plane == 2 ?  AV_CEIL_RSHIFT(inlink->h, vsub) : inlink->h;
> >>>+    }
> >>>
> >>>    select->var_values[VAR_N]          = 0.0;
> >>>    select->var_values[VAR_SELECTED_N] = 0.0;
> >>>@@ -242,7 +259,7 @@ static int config_input(AVFilterLink *inlink)
> >>>        inlink->type == AVMEDIA_TYPE_AUDIO ? inlink->sample_rate : NAN;
> >>>
> >>>    if (CONFIG_SELECT_FILTER && select->do_scene_detect) {
> >>>-        select->sad = ff_scene_sad_get_fn(8);
> >>>+        select->sad = ff_scene_sad_get_fn(select->bitdepth == 8 ? 8 : 16);
> >>>        if (!select->sad)
> >>>            return AVERROR(EINVAL);
> >>>    }
> >>>@@ -258,12 +275,21 @@ static double get_scene_score(AVFilterContext *ctx, AVFrame *frame)
> >>>    if (prev_picref &&
> >>>        frame->height == prev_picref->height &&
> >>>        frame->width  == prev_picref->width) {
> >>>-        uint64_t sad;
> >>>+        uint64_t sad = 0;
> >>>        double mafd, diff;
> >>>+        int count = 0;
> >>>+
> >>>+        for (int plane = 0; plane < select->nb_planes; plane++) {
> >>>+            uint64_t plane_sad;
> >>>+            select->sad(prev_picref->data[plane], prev_picref->linesize[plane],
> >>>+                    frame->data[plane], frame->linesize[plane],
> >>>+                    select->width[plane], select->height[plane], &plane_sad);
> >>>+            sad += plane_sad;
> >>>+            count += select->width[plane] * select->height[plane];
> >>>+        }
> >>>
> >>>-        select->sad(prev_picref->data[0], prev_picref->linesize[0], frame->data[0], frame->linesize[0], frame->width * 3, frame->height, &sad);
> >>>        emms_c();
> >>>-        mafd = (double)sad / (frame->width * 3 * frame->height);
> >>>+        mafd = (double)sad / count;
> >>
> >>Still missing normalization to [0..255] here for >8 bitdepth.
> >By the testing, Passengers_Breakfast_4K.mkv is 10bits sample, it can't detect the scenecut if using 1<<bitdepth,
> 
> You should divide by (1 << (bitdepth - 8)), since you should be
> normalizing to 0..255 here.
> 
Yes, Now I have check the result, it's expected. I have updated the patch. 

> >Or just remove yuv420p10 support, it's the only 10bit enable pixel format in the 3/3 patch?
> >After get more sample for testing it's OK, then change for bitdepth > 8
> 
> You should get the same scores for 10bit and 8bit. (e.g. YUV420P and
> YUV420P10).
> 
> Regards,
> Marton
> _______________________________________________
> ffmpeg-devel mailing list
> ffmpeg-devel@ffmpeg.org
> https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
> 
> To unsubscribe, visit link above, or email
> ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".

Patch hide | download patch | download mbox

diff --git a/libavfilter/f_select.c b/libavfilter/f_select.c
index 1132375758..eed8df34cb 100644
--- a/libavfilter/f_select.c
+++ b/libavfilter/f_select.c
@@ -28,6 +28,8 @@ 
 #include "libavutil/fifo.h"
 #include "libavutil/internal.h"
 #include "libavutil/opt.h"
+#include "libavutil/imgutils.h"
+#include "libavutil/pixdesc.h"
 #include "avfilter.h"
 #include "audio.h"
 #include "formats.h"
@@ -144,6 +146,10 @@  typedef struct SelectContext {
     char *expr_str;
     AVExpr *expr;
     double var_values[VAR_VARS_NB];
+    int bitdepth;
+    int nb_planes;
+    ptrdiff_t width[4];
+    ptrdiff_t height[4];
     int do_scene_detect;            ///< 1 if the expression requires scene detection variables, 0 otherwise
     ff_scene_sad_fn sad;            ///< Sum of the absolute difference function (scene detect only)
     double prev_mafd;               ///< previous MAFD                           (scene detect only)
@@ -202,6 +208,17 @@  static av_cold int init(AVFilterContext *ctx)
 static int config_input(AVFilterLink *inlink)
 {
     SelectContext *select = inlink->dst->priv;
+    const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(inlink->format);
+
+    select->bitdepth = desc->comp[0].depth;
+    select->nb_planes = av_pix_fmt_count_planes(inlink->format);
+    for (int plane = 0; plane < select->nb_planes; plane++) {
+        ptrdiff_t line_size = av_image_get_linesize(inlink->format, inlink->w, plane);
+        int vsub = desc->log2_chroma_h;
+
+        select->width[plane] = line_size >> (select->bitdepth > 8);
+        select->height[plane] = plane == 1 || plane == 2 ?  AV_CEIL_RSHIFT(inlink->h, vsub) : inlink->h;
+    }
 
     select->var_values[VAR_N]          = 0.0;
     select->var_values[VAR_SELECTED_N] = 0.0;
@@ -242,7 +259,7 @@  static int config_input(AVFilterLink *inlink)
         inlink->type == AVMEDIA_TYPE_AUDIO ? inlink->sample_rate : NAN;
 
     if (CONFIG_SELECT_FILTER && select->do_scene_detect) {
-        select->sad = ff_scene_sad_get_fn(8);
+        select->sad = ff_scene_sad_get_fn(select->bitdepth == 8 ? 8 : 16);
         if (!select->sad)
             return AVERROR(EINVAL);
     }
@@ -258,12 +275,21 @@  static double get_scene_score(AVFilterContext *ctx, AVFrame *frame)
     if (prev_picref &&
         frame->height == prev_picref->height &&
         frame->width  == prev_picref->width) {
-        uint64_t sad;
+        uint64_t sad = 0;
         double mafd, diff;
+        int count = 0;
+
+        for (int plane = 0; plane < select->nb_planes; plane++) {
+            uint64_t plane_sad;
+            select->sad(prev_picref->data[plane], prev_picref->linesize[plane],
+                    frame->data[plane], frame->linesize[plane],
+                    select->width[plane], select->height[plane], &plane_sad);
+            sad += plane_sad;
+            count += select->width[plane] * select->height[plane];
+        }
 
-        select->sad(prev_picref->data[0], prev_picref->linesize[0], frame->data[0], frame->linesize[0], frame->width * 3, frame->height, &sad);
         emms_c();
-        mafd = (double)sad / (frame->width * 3 * frame->height);
+        mafd = (double)sad / count;
         diff = fabs(mafd - select->prev_mafd);
         ret  = av_clipf(FFMIN(mafd, diff) / 100., 0, 1);
         select->prev_mafd = mafd;