[FFmpeg-devel,v6] libavfilter/vf_find_rect: convert the object image to gray8 format instead of failed directly

Submitted by lance.lmwang@gmail.com on June 15, 2019, 11:26 p.m.

Details

Message ID 1560641215-64931-1-git-send-email-lance.lmwang@gmail.com
State New
Headers show

Commit Message

lance.lmwang@gmail.com June 15, 2019, 11:26 p.m.
From: Limin Wang <lance.lmwang@gmail.com>

Signed-off-by: Limin Wang <lance.lmwang@gmail.com>
---
 doc/filters.texi           |  2 +-
 libavfilter/vf_find_rect.c | 39 ++++++++++++++++++++++++++++-----------
 2 files changed, 29 insertions(+), 12 deletions(-)

Patch hide | download patch | download mbox

diff --git a/doc/filters.texi b/doc/filters.texi
index ec1c7c7..4ee6a57 100644
--- a/doc/filters.texi
+++ b/doc/filters.texi
@@ -10150,7 +10150,7 @@  It accepts the following options:
 
 @table @option
 @item object
-Filepath of the object image, needs to be in gray8.
+Filepath of the object image, it will be converted to GRAY8 automatically.
 
 @item threshold
 Detection threshold, default is 0.5.
diff --git a/libavfilter/vf_find_rect.c b/libavfilter/vf_find_rect.c
index d7e6579..ee6c3f4 100644
--- a/libavfilter/vf_find_rect.c
+++ b/libavfilter/vf_find_rect.c
@@ -28,6 +28,7 @@ 
 #include "internal.h"
 
 #include "lavfutils.h"
+#include "lswsutils.h"
 
 #define MAX_MIPMAPS 5
 
@@ -244,6 +245,9 @@  static av_cold int init(AVFilterContext *ctx)
 {
     FOCContext *foc = ctx->priv;
     int ret, i;
+    uint8_t *tmp_data[4] = { NULL };
+    int tmp_linesize[4], width, height;
+    enum AVPixelFormat pix_fmt;
 
     if (!foc->obj_filename) {
         av_log(ctx, AV_LOG_ERROR, "object filename not set\n");
@@ -254,24 +258,37 @@  static av_cold int init(AVFilterContext *ctx)
     if (!foc->obj_frame)
         return AVERROR(ENOMEM);
 
-    if ((ret = ff_load_image(foc->obj_frame->data, foc->obj_frame->linesize,
-                             &foc->obj_frame->width, &foc->obj_frame->height,
-                             &foc->obj_frame->format, foc->obj_filename, ctx)) < 0)
-        return ret;
-
-    if (foc->obj_frame->format != AV_PIX_FMT_GRAY8) {
-        av_log(ctx, AV_LOG_ERROR, "object image is not a grayscale image\n");
-        return AVERROR(EINVAL);
-    }
+    if ((ret = ff_load_image(tmp_data, tmp_linesize,
+                             &width, &height,
+                             &pix_fmt, foc->obj_filename, ctx)) < 0)
+        goto error;
+
+    /* convert object image to gray8 format with same width and height */
+    foc->obj_frame->format = AV_PIX_FMT_GRAY8;
+    foc->obj_frame->width  = width;
+    foc->obj_frame->height = height;
+    if ((ret = ff_scale_image(foc->obj_frame->data, foc->obj_frame->linesize,
+                    foc->obj_frame->width, foc->obj_frame->height, foc->obj_frame->format,
+                    tmp_data, tmp_linesize, width, height, pix_fmt, ctx)) < 0)
+        goto error;
+    av_freep(&tmp_data[0]);
 
     foc->needle_frame[0] = av_frame_clone(foc->obj_frame);
     for (i = 1; i < foc->mipmaps; i++) {
         foc->needle_frame[i] = downscale(foc->needle_frame[i-1]);
-        if (!foc->needle_frame[i])
-            return AVERROR(ENOMEM);
+        if (!foc->needle_frame[i]) {
+            ret = AVERROR(ENOMEM);
+            goto error;
+        }
     }
 
     return 0;
+error:
+    av_freep(&tmp_data[0]);
+    if (foc->obj_frame)
+        av_freep(&foc->obj_frame->data[0]);
+    av_frame_free(&foc->obj_frame);
+    return ret;
 }
 
 static const AVFilterPad foc_inputs[] = {