hofee/nbv_reconstruction
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add scan points check

Browse Source
This commit is contained in:
hofee 2024-09-30 00:55:34 +08:00
parent 2f6d156abd
commit cef7ab4429
3 changed files with 52 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
configs/local/view_generate_config.yaml
View File

@ -24,12 +24,6 @@ runner:
max_height: 0.15
min_radius: 0.3
max_radius: 0.5
min_R: 0.05
max_R: 0.3
min_G: 0.05
max_G: 0.3
min_B: 0.05
max_B: 0.3
display_object:
min_x: 0
max_x: 0.03

10
core/global_pts_n_num_pipeline.py
View File

@ -76,16 +76,16 @@ class NBVReconstructionGlobalPointsPipeline(nn.Module):
device = next(self.parameters()).device
pose_feat_seq_list = []
pts_num_feat_seq_list = []
embedding_list_batch = []
for scanned_n_to_world_pose_9d,scanned_target_pts_num in zip(scanned_n_to_world_pose_9d_batch,scanned_target_pts_num_batch):
scanned_n_to_world_pose_9d = scanned_n_to_world_pose_9d.to(device)
scanned_target_pts_num = scanned_target_pts_num.to(device)
pose_feat_seq_list.append(self.pose_encoder.encode_pose(scanned_n_to_world_pose_9d))
pts_num_feat_seq_list.append(self.pts_num_encoder.encode_pts_num(scanned_target_pts_num))
pose_feat_seq = self.pose_encoder.encode_pose(scanned_n_to_world_pose_9d)
pts_num_feat_seq = self.pts_num_encoder.encode_pts_num(scanned_target_pts_num)
embedding_list_batch.append(torch.cat([pose_feat_seq, pts_num_feat_seq], dim=-1))
main_feat = self.pose_n_num_seq_encoder.encode_sequence(pts_num_feat_seq_list, pose_feat_seq_list)
main_feat = self.pose_n_num_seq_encoder.encode_sequence(embedding_list_batch)
combined_scanned_pts_batch = data['combined_scanned_pts']

41
utils/reconstruction.py
View File

@ -45,9 +45,10 @@ class ReconstructionUtil:
@staticmethod
def compute_next_best_view_sequence_with_overlap(target_point_cloud, point_cloud_list,threshold=0.01, overlap_threshold=0.3, init_view = 0, status_info=None):
def compute_next_best_view_sequence_with_overlap(target_point_cloud, point_cloud_list, scan_points_indices_list, threshold=0.01, overlap_threshold=0.3, init_view = 0, status_info=None):
selected_views = [point_cloud_list[init_view]]
combined_point_cloud = np.vstack(selected_views)
combined_scan_points_indices = scan_points_indices_list[init_view]
down_sampled_combined_point_cloud = PtsUtil.voxel_downsample_point_cloud(combined_point_cloud,threshold)
new_coverage = ReconstructionUtil.compute_coverage_rate(target_point_cloud, down_sampled_combined_point_cloud, threshold)
current_coverage = new_coverage
@ -63,6 +64,8 @@ class ReconstructionUtil:
for view_index in remaining_views:
if selected_views:
new_scan_points_indices = scan_points_indices_list[view_index]
if not ReconstructionUtil.check_scan_points_overlap(combined_scan_points_indices, new_scan_points_indices):
combined_old_point_cloud = np.vstack(selected_views)
down_sampled_old_point_cloud = PtsUtil.voxel_downsample_point_cloud(combined_old_point_cloud,threshold)
down_sampled_new_view_point_cloud = PtsUtil.voxel_downsample_point_cloud(point_cloud_list[view_index],threshold)
@ -85,6 +88,7 @@ class ReconstructionUtil:
break
selected_views.append(point_cloud_list[best_view])
remaining_views.remove(best_view)
combined_scan_points_indices = ReconstructionUtil.combine_scan_points_indices(combined_scan_points_indices, scan_points_indices_list[best_view])
current_coverage += best_coverage_increase
cnt_processed_view += 1
if status_info is not None:
@ -121,3 +125,38 @@ class ReconstructionUtil:
return filtered_sampled_points[:, :3]
@staticmethod
def generate_scan_points(display_table_top, display_table_radius, min_distance=0.03, max_points_num = 100, max_attempts = 1000):
points = []
attempts = 0
while len(points) < max_points_num and attempts < max_attempts:
angle = np.random.uniform(0, 2 * np.pi)
r = np.random.uniform(0, display_table_radius)
x = r * np.cos(angle)
y = r * np.sin(angle)
z = display_table_top
new_point = (x, y, z)
if all(np.linalg.norm(np.array(new_point) - np.array(existing_point)) >= min_distance for existing_point in points):
points.append(new_point)
attempts += 1
return points
@staticmethod
def compute_covered_scan_points(scan_points, point_cloud, threshold=0.01):
tree = cKDTree(point_cloud)
covered_points = []
indices = []
for i, scan_point in enumerate(scan_points):
if tree.query_ball_point(scan_point, threshold):
covered_points.append(scan_point)
indices.append(i)
return covered_points, indices
@staticmethod
def check_scan_points_overlap(indices1, indices2, threshold=5):
return len(set(indices1).intersection(set(indices2))) > threshold
@staticmethod
def combine_scan_points_indices(indices1, indices2):
combined_indices = set(indices1) | set(indices2)
return sorted(combined_indices)