1.1.3

app.py

@@ -53,7 +53,7 @@ class DepthEstimator:
     def estimate_depth(self, image_path):
         try:
             # Load image
-
+            image = Image.open(image_path)
             
             # Resize image for processing
             resized_image, new_size = self.resize_image(image_path)
@@ -118,9 +118,11 @@ def find_bottommost_footpath_pixel(mask, topmost_pixel):
     top_y, top_x = topmost_pixel
     
     # Find all mask pixels in the same x-column as the topmost pixel
-    column_pixels = np.where((mask > 0) & (np.arange(mask.shape[1])[None, :] == top_x))
+    mask_y_coords, mask_x_coords = np.where(mask > 0)
+    column_mask = mask_x_coords == top_x
+    column_y_coords = mask_y_coords[column_mask]
     
-    if len(column_pixels[0]) == 0:
+    if len(column_y_coords) == 0:
         # If no pixels in the same column, find the bottommost pixel in the entire mask
         footpath_pixels = np.where(mask > 0)
         if len(footpath_pixels[0]) == 0:
@@ -132,7 +134,7 @@ def find_bottommost_footpath_pixel(mask, topmost_pixel):
         return (max_y, bottom_x_coords[center_idx])
     
     # Find the bottommost pixel in the same x-column
-    max_y_in_column = np.max(column_pixels[0])
+    max_y_in_column = np.max(column_y_coords)
     return (max_y_in_column, top_x)
 
 
@@ -235,7 +237,9 @@ async def estimate_depth_endpoint(file: UploadFile = File(...), mask: UploadFile
         resized_image = cv2.resize(image, new_size)
         resized_mask = cv2.resize(mask, new_size)
         
-
+        # Convert mask to grayscale if it's not already
+        if len(resized_mask.shape) == 3:
+            resized_mask = cv2.cvtColor(resized_mask, cv2.COLOR_BGR2GRAY)
         
         # Find key pixels from the mask
         topmost_pixel = find_topmost_pixel(resized_mask)