remove self loops and bi-directional non unique edges. edge_th=60

handcrafted_solution.py

@@ -138,7 +138,7 @@ def get_vertices_and_edges_from_segmentation(gest_seg_np, edge_th=50.0):
             theta = np.pi / 180  # angular resolution in radians of the Hough grid
             threshold = 15  # minimum number of votes (intersections in Hough grid cell)
             min_line_length = 40  # minimum number of pixels making up a line
-            max_line_gap = 30  # maximum gap in pixels between connectable line segments
+            max_line_gap = 40  # maximum gap in pixels between connectable line segments
 
             # Run Hough on edge detected image
             # Output "lines" is an array containing endpoints of detected line segments
@@ -165,19 +165,27 @@ def get_vertices_and_edges_from_segmentation(gest_seg_np, edge_th=50.0):
             begin_closest_point_distances = begin_distances[begin_closest_points, np.arange(len(begin_closest_points))]
             end_closest_point_distances = end_distances[end_closest_points, np.arange(len(end_closest_points))]
 
-            begin_in_range_mask = begin_closest_point_distances < edge_th
-            end_in_range_mask = end_closest_point_distances < edge_th
+            begin_in_range_mask = begin_closest_point_distances <= edge_th
+            end_in_range_mask = end_closest_point_distances <= edge_th
 
             # where both ends are in range
             in_range_connected_mask = np.logical_and(begin_in_range_mask, end_in_range_mask)
 
             edge_idxs = np.where(in_range_connected_mask)[0]
 
-            unique_edges = np.unique(np.array([begin_closest_points[edge_idxs], end_closest_points[edge_idxs]]).T,
-                                     axis=0)
+            edges = np.array([begin_closest_points[edge_idxs], end_closest_points[edge_idxs]]).T
+            if len(edges) < 1:
+                continue
+            edges = np.sort(edges, axis=1)
+            unique_edges = np.unique(edges, axis=0)
+
+            unique_edges = unique_edges[unique_edges[:, 0] != unique_edges[:, 1]] # remove self loops
 
+            if len(unique_edges) < 1:
+                continue
             connections.extend(unique_edges)
 
+
     vertices = [{"xy": v, "type": "apex"} for v in apex_centroids]
     vertices += [{"xy": v, "type": "eave_end_point"} for v in eave_end_point_centroids]
     return vertices, connections
@@ -288,7 +296,7 @@ def predict(entry, visualize=False) -> Tuple[np.ndarray, List[int]]:
         gest_seg_np = np.array(gest_seg).astype(np.uint8)
         # Metric3D
         depth_np = np.array(depth) / 2.5  # 2.5 is the scale estimation coefficient
-        vertices, connections = get_vertices_and_edges_from_segmentation(gest_seg_np, edge_th=70.)
+        vertices, connections = get_vertices_and_edges_from_segmentation(gest_seg_np, edge_th=60.)
         if (len(vertices) < 2) or (len(connections) < 1):
             print(f'Not enough vertices or connections in image {i}')
             vert_edge_per_image[i] = np.empty((0, 2)), [], np.empty((0, 3))