def main():
"""This demo visualizes box 8C format predicted by MLOD, before
getting converted to Box 3D.
Keys:
F1: Toggle predictions
F2: Toggle easy ground truth objects (Green)
F3: Toggle medium ground truth objects (Orange)
F4: Toggle hard ground truth objects (Red)
F5: Toggle all ground truth objects (default off)
F6: Toggle 3D voxel grid
F7: Toggle point cloud
"""
##############################
# Options
##############################
mlod_score_threshold = 0.1
show_orientations = True
checkpoint_name = 'mlod_exp_8c'
global_step = None
sample_name = None
dataset_config = DatasetBuilder.copy_config(DatasetBuilder.KITTI_VAL_HALF)
dataset = DatasetBuilder.build_kitti_dataset(dataset_config)
##############################
# Setup Paths
##############################
# # # Cars # # #
# sample_name = '000050'
# sample_name = '000104'
# sample_name = '000169'
# sample_name = '000191'
# sample_name = '000360'
# sample_name = '001783'
# sample_name = '001820'
# sample_name = '006338'
# # # People # # #
# val_half split
# sample_name = '000001'
sample_name = '000005' # Easy, 1 ped
# sample_name = '000122' # Easy, 1 cyc
# sample_name = '000134' # Hard, lots of people
# sample_name = '000167' # Medium, 1 ped, 2 cycs
# sample_name = '000187' # Medium, 1 ped on left
# sample_name = '000381' # Easy, 1 ped
# sample_name = '000398' # Easy, 1 ped
# sample_name = '000401' # Hard, obscured peds
# sample_name = '000407' # Easy, 1 ped
# sample_name = '000448' # Hard, several far people
# sample_name = '000486' # Hard 2 obscured peds
# sample_name = '000509' # Easy, 1 ped
# sample_name = '000718' # Hard, lots of people
# sample_name = '002216' # Easy, 1 cyc
# Random sample
if sample_name is None:
sample_idx = np.random.randint(0, dataset.num_samples)
sample_name = dataset.sample_list[sample_idx]
img_idx = int(sample_name)
# Text files directory
predictions_and_scores_dir = mlod.root_dir() + \
'/data/outputs/' + checkpoint_name + '/predictions' + \
'/final_boxes_8c_and_scores/' + dataset.data_split
# Get checkpoint step
steps = os.listdir(predictions_and_scores_dir)
steps.sort(key=int)
print('Available steps: {}'.format(steps))
# Use latest checkpoint if no index provided
if global_step is None:
global_step = steps[-1]
##############################
# predictions
##############################
# Load predictions from files
predictions_and_scores = np.loadtxt(
predictions_and_scores_dir +
"/{}/{}.txt".format(global_step, sample_name))
predictions_boxes_8c = predictions_and_scores[:, 0:24]
prediction_scores = predictions_and_scores[:, 24]
score_mask = prediction_scores >= mlod_score_threshold
predictions_boxes_8c = predictions_boxes_8c[score_mask]
all_vtk_box_corners = []
predictions_boxes_8c = np.reshape(predictions_boxes_8c, [-1, 3, 8])
for i in range(len(predictions_boxes_8c)):
box_8c = predictions_boxes_8c[i, :, :]
vtk_box_corners = VtkBox8c()
vtk_box_corners.set_objects(box_8c)
all_vtk_box_corners.append(vtk_box_corners)
##############################
# Ground Truth
##############################
if dataset.has_labels:
easy_gt_objs, medium_gt_objs, \
hard_gt_objs, all_gt_objs = \
demo_utils.get_gts_based_on_difficulty(dataset,
img_idx)
else:
easy_gt_objs = medium_gt_objs = hard_gt_objs = all_gt_objs = []
##############################
# Point Cloud
##############################
image_path = dataset.get_rgb_image_path(sample_name)
image = cv2.imread(image_path)
img_idx = int(sample_name)
points, point_colours = demo_utils.get_filtered_pc_and_colours(
dataset, image, img_idx)
# Voxelize the point cloud for visualization
voxel_grid = VoxelGrid()
voxel_grid.voxelize(points, voxel_size=0.1, create_leaf_layout=False)
##############################
# Visualization
##############################
# Create VtkVoxelGrid
vtk_voxel_grid = VtkVoxelGrid()
vtk_voxel_grid.set_voxels(voxel_grid)
vtk_point_cloud = VtkPointCloud()
vtk_point_cloud.set_points(points, point_colours)
# Create VtkAxes
axes = vtk.vtkAxesActor()
axes.SetTotalLength(5, 5, 5)
# Create VtkBoxes for ground truth
vtk_easy_gt_boxes, vtk_medium_gt_boxes, \
vtk_hard_gt_boxes, vtk_all_gt_boxes = \
demo_utils.create_gt_vtk_boxes(easy_gt_objs,
medium_gt_objs,
hard_gt_objs,
all_gt_objs,
show_orientations)
# Create Voxel Grid Renderer in bottom half
vtk_renderer = vtk.vtkRenderer()
vtk_renderer.AddActor(vtk_voxel_grid.vtk_actor)
vtk_renderer.AddActor(vtk_point_cloud.vtk_actor)
vtk_box_actors = vtk.vtkAssembly()
# Create VtkBoxes for prediction boxes
for i in range(len(all_vtk_box_corners)):
# Adding labels, slows down rendering
# vtk_renderer.AddActor(all_vtk_box_corners[i].
# vtk_text_labels.vtk_actor)
vtk_box_actors.AddPart(all_vtk_box_corners[i].vtk_actor)
vtk_renderer.AddActor(vtk_voxel_grid.vtk_actor)
vtk_renderer.AddActor(vtk_point_cloud.vtk_actor)
vtk_renderer.SetBackground(0.2, 0.3, 0.4)
vtk_renderer.AddActor(vtk_voxel_grid.vtk_actor)
vtk_renderer.AddActor(vtk_point_cloud.vtk_actor)
vtk_renderer.AddActor(vtk_hard_gt_boxes.vtk_actor)
vtk_renderer.AddActor(vtk_medium_gt_boxes.vtk_actor)
vtk_renderer.AddActor(vtk_easy_gt_boxes.vtk_actor)
vtk_renderer.AddActor(vtk_all_gt_boxes.vtk_actor)
vtk_renderer.AddActor(vtk_box_actors)
vtk_renderer.AddActor(axes)
# Set initial properties for some actors
vtk_point_cloud.vtk_actor.GetProperty().SetPointSize(2)
vtk_voxel_grid.vtk_actor.SetVisibility(0)
vtk_all_gt_boxes.vtk_actor.SetVisibility(0)
# Setup Camera
current_cam = vtk_renderer.GetActiveCamera()
current_cam.Pitch(160.0)
current_cam.Roll(180.0)
# Zooms out to fit all points on screen
vtk_renderer.ResetCamera()
# Zoom in slightly
current_cam.Zoom(2.5)
# Reset the clipping range to show all points
vtk_renderer.ResetCameraClippingRange()
# Setup Render Window
vtk_render_window = vtk.vtkRenderWindow()
vtk_render_window.SetWindowName(
"Predictions: Step {}, Sample {}, Min Score {}".format(
global_step,
sample_name,
mlod_score_threshold,
))
vtk_render_window.SetSize(900, 600)
vtk_render_window.AddRenderer(vtk_renderer)
# Setup custom interactor style, which handles mouse and key events
vtk_render_window_interactor = vtk.vtkRenderWindowInteractor()
vtk_render_window_interactor.SetRenderWindow(vtk_render_window)
vtk_render_window_interactor.SetInteractorStyle(
vis_utils.ToggleActorsInteractorStyle([
vtk_box_actors, vtk_easy_gt_boxes.vtk_actor,
vtk_medium_gt_boxes.vtk_actor, vtk_hard_gt_boxes.vtk_actor,
vtk_all_gt_boxes.vtk_actor, vtk_voxel_grid.vtk_actor,
vtk_point_cloud.vtk_actor
]))
vtk_render_window_interactor.Start()
def test_get_empty_anchor_filter_in_2d(self):
# create generic ground plane (normal vector is straight up)
area_extent = [(0., 2.), (-1., 0.), (0., 2.)]
# Creates a voxel grid in following format at y = bin (-1.5, -0.5]
# [ ][ ][ ][ ]
# [ ][ ][x][ ]
# [ ][ ][ ][ ]
# [ ][ ][x][ ]
pts = np.array([[0.51, -0.5, 1.1], [1.51, -0.5, 1.1]])
voxel_size = 0.5
voxel_grid = VoxelGrid()
voxel_grid.voxelize(pts, voxel_size, extents=area_extent)
# Define anchors to test
boxes_3d = np.array([
[0.51, 0, 0.51, 1, 1, 1, 0],
[0.51, 0, 0.51, 1, 1, 1, np.pi / 2.],
[0.51, 0, 1.1, 1, 1, 1, 0],
[0.51, 0, 1.1, 1, 1, 1, np.pi / 2.],
[1.51, 0, 0.51, 1, 1, 1, 0],
[1.51, 0, 0.51, 1, 1, 1, np.pi / 2.],
[1.51, 0, 1.1, 1, 1, 1, 0],
[1.51, 0, 1.1, 1, 1, 1, np.pi / 2.],
])
anchors = box_3d_encoder.box_3d_to_anchor(boxes_3d)
# test anchor locations, number indicates the anchors indices
# [ ][ ][ ][ ]
# [ ][1][3][ ]
# [ ][ ][ ][ ]
# [ ][5][7][ ]
gen_filter = anchor_filter.get_empty_anchor_filter(anchors,
voxel_grid,
density_threshold=1)
expected_filter = np.array(
[False, False, True, True, False, False, True, True])
self.assertTrue((gen_filter == expected_filter).all())
boxes_3d = np.array([
[0.5, 0, 0.5, 2, 1, 1, 0], # case 1
[0.5, 0, 0.5, 2, 1, 1, np.pi / 2.],
[0.5, 0, 1.5, 1, 2, 1, 0], # case 2
[0.5, 0, 1.5, 1, 2, 1, np.pi / 2.],
[1.5, 0, 0.5, 2, 1, 1, 0], # case 3
[1.5, 0, 0.5, 2, 1, 1, np.pi / 2.],
[1.5, 0, 1.5, 1, 2, 1, 0], # case 4
[1.5, 0, 1.5, 1, 2, 1, np.pi / 2.]
])
anchors = box_3d_encoder.box_3d_to_anchor(boxes_3d)
# case 1
# [ ][ ][ ][ ] [ ][ ][ ][ ]
# [ ][o][ ][ ] [ ][o][o][ ]
# [ ][o][ ][ ] [ ][ ][ ][ ]
# [ ][ ][ ][ ] [ ][ ][ ][ ]
# case 2
# [ ][ ][ ][ ] [ ][ ][ ][ ]
# [ ][ ][o][o] [ ][ ][o][ ]
# [ ][ ][ ][ ] [ ][ ][o][ ]
# [ ][ ][ ][ ] [ ][ ][ ][ ]
# case 3
# [ ][ ][ ][ ] [ ][ ][ ][ ]
# [ ][ ][ ][ ] [ ][ ][ ][ ]
# [ ][o][ ][ ] [ ][o][o][ ]
# [ ][o][ ][ ] [ ][ ][ ][ ]
# case 4
# [ ][ ][ ][ ] [ ][ ][ ][ ]
# [ ][ ][ ][ ] [ ][ ][ ][ ]
# [ ][ ][o][o] [ ][ ][o][ ]
# [ ][ ][ ][ ] [ ][ ][o][ ]
gen_filter = anchor_filter.get_empty_anchor_filter(anchors,
voxel_grid,
density_threshold=1)
expected_filter = np.array(
[False, True, True, True, False, True, True, True])
self.assertTrue((gen_filter == expected_filter).all())
def main():
"""This demo shows RPN proposals and AVOD predictions in the
3D point cloud.
Keys:
F1: Toggle proposals
F2: Toggle predictions
F3: Toggle 3D voxel grid
F4: Toggle point cloud
F5: Toggle easy ground truth objects (Green)
F6: Toggle medium ground truth objects (Orange)
F7: Toggle hard ground truth objects (Red)
F8: Toggle all ground truth objects (default off)
F9: Toggle ground slice filter (default off)
F10: Toggle offset slice filter (default off)
"""
##############################
# Options
##############################
rpn_score_threshold = 0.1
avod_score_threshold = 0.1
proposals_line_width = 1.0
predictions_line_width = 3.0
show_orientations = True
point_cloud_source = 'depth'
# Config file folder, default (<avod_root>/data/outputs/<checkpoint_name>)
config_dir = None
checkpoint_name = 'pyramid_cars_with_aug_example'
global_step = None # Latest checkpoint
global_step = 83000
#data_split = 'val_half'
data_split = 'val'
# data_split = 'test'
# Show 3D iou text
draw_ious_3d = True
name_list =[]
#name_file = '/media/wavelab/d3cd89ab-7705-4996-94f3-01da25ba8f50/moosey/val.txt'
#with open(name_file) as f:
#for line in f:
#newline = line.replace("\n","")
#name_list.append(newline)
#name_list =['0000000003','0000000009','0000000016','0000000233','0000000234','0000000236','0000000422','0000000473','0000000490','0000000494','0000000547','0000000655',\
#'0000000679','0000000690','0000000692','0000000781']
name_list =['0000000004']
for names in name_list:
sample_name = names
#sample_name = None
# # # Cars # # #
# sample_name = '000050'
# sample_name = '000104'
# sample_name = '000169'
# sample_name = '000191'
# sample_name = '000360'
# sample_name = '001783'
# sample_name = '001820'
# val split
# sample_name = '000181'
# sample_name = '000751'
# sample_name = '000843'
# sample_name = '000944'
# sample_name = '006338'
# # # People # # #
# val_half split
# sample_name = '000001' # Hard, 1 far cyc
# sample_name = '000005' # Easy, 1 ped
# sample_name = '000122' # Easy, 1 cyc
# sample_name = '000134' # Hard, lots of people
# sample_name = '000167' # Medium, 1 ped, 2 cycs
# sample_name = '000187' # Medium, 1 ped on left
# sample_name = '000381' # Easy, 1 ped
# sample_name = '000398' # Easy, 1 ped
# sample_name = '000401' # Hard, obscured peds
# sample_name = '000407' # Easy, 1 ped
# sample_name = '000448' # Hard, several far people
# sample_name = '000486' # Hard 2 obscured peds
# sample_name = '000509' # Easy, 1 ped
# sample_name = '000718' # Hard, lots of people
# sample_name = '002216' # Easy, 1 cyc
# val split
# sample_name = '000015'
# sample_name = '000048'
# sample_name = '000058'
# sample_name = '000076' # Medium, few ped, 1 cyc
# sample_name = '000108'
# sample_name = '000118'
# sample_name = '000145'
# sample_name = '000153'
# sample_name = '000186'
# sample_name = '000195'
# sample_name = '000199'
# sample_name = '000397'
# sample_name = '004425'
# sample_name = '004474' # Hard, many ped, 1 cyc
# sample_name = '004657' # Hard, Few cycl, few ped
# sample_name = '006071'
# sample_name = '006828' # Hard, Few cycl, few ped
# sample_name = '006908' # Hard, Few cycl, few ped
# sample_name = '007412'
# sample_name = '007318' # Hard, Few cycl, few ped
##############################
# End of Options
##############################
if data_split == 'test':
draw_ious_3d = False
if config_dir is None:
config_dir = avod.root_dir() + '/data/outputs/' + checkpoint_name
# Parse experiment config
pipeline_config_file = \
config_dir + '/' + checkpoint_name + '.config'
_, _, _, dataset_config = \
config_builder_util.get_configs_from_pipeline_file(
pipeline_config_file, is_training=False)
dataset_config.data_split = data_split
if data_split == 'test':
dataset_config.data_split_dir = 'testing'
dataset_config.has_labels = False
dataset = DatasetBuilder.build_kitti_dataset(dataset_config,
use_defaults=False)
# Random sample
if sample_name is None:
sample_idx = np.random.randint(0, dataset.num_samples)
sample_name = dataset.sample_names[sample_idx]
##############################
# Setup Paths
##############################
img_idx = int(sample_name)
# Text files directory
proposals_and_scores_dir = avod.root_dir() + \
'/data/outputs/' + checkpoint_name + '/predictions' + \
'/proposals_and_scores/' + dataset.data_split
predictions_and_scores_dir = avod.root_dir() + \
'/data/outputs/' + checkpoint_name + '/predictions' + \
'/final_predictions_and_scores/' + dataset.data_split
# Get checkpoint step
steps = os.listdir(proposals_and_scores_dir)
steps.sort(key=int)
print('Available steps: {}'.format(steps))
# Use latest checkpoint if no index provided
if global_step is None:
global_step = steps[-1]
# Output images directory
img_out_dir = avod.root_dir() + '/data/outputs/' + checkpoint_name + \
'/predictions/images_3d/{}/{}/{}'.format(dataset.data_split,
global_step,
rpn_score_threshold)
if not os.path.exists(img_out_dir):
os.makedirs(img_out_dir)
##############################
# Proposals
##############################
# Load proposals from files
proposals_and_scores = np.loadtxt(proposals_and_scores_dir +
"/{}/{}.txt".format(global_step,
sample_name))
proposals = proposals_and_scores[:, 0:7]
proposal_scores = proposals_and_scores[:, 7]
rpn_score_mask = proposal_scores > rpn_score_threshold
proposals = proposals[rpn_score_mask]
proposal_scores = proposal_scores[rpn_score_mask]
print('Proposals:', len(proposal_scores), proposal_scores)
proposal_objs = \
[box_3d_encoder.box_3d_to_object_label(proposal,
obj_type='Proposal')
for proposal in proposals]
##############################
# Predictions
##############################
# Load proposals from files
predictions_and_scores = np.loadtxt(predictions_and_scores_dir +
"/{}/{}.txt".format(
global_step,
sample_name)).reshape(-1, 9)
prediction_boxes_3d = predictions_and_scores[:, 0:7]
prediction_scores = predictions_and_scores[:, 7]
prediction_types = np.asarray(predictions_and_scores[:, 8], dtype=np.int32)
avod_score_mask = prediction_scores >= avod_score_threshold
prediction_boxes_3d = prediction_boxes_3d[avod_score_mask]
prediction_scores = prediction_scores[avod_score_mask]
print('Predictions: ', len(prediction_scores), prediction_scores)
final_predictions = np.copy(prediction_boxes_3d)
# # Swap l, w for predictions where w > l
# swapped_indices = predictions[:, 4] > predictions[:, 3]
# final_predictions[swapped_indices, 3] = predictions[swapped_indices, 4]
# final_predictions[swapped_indices, 4] = predictions[swapped_indices, 3]
prediction_objs = []
for pred_idx in range(len(final_predictions)):
prediction_box_3d = final_predictions[pred_idx]
prediction_type = dataset.classes[prediction_types[pred_idx]]
prediction_obj = box_3d_encoder.box_3d_to_object_label(
prediction_box_3d, obj_type=prediction_type)
prediction_objs.append(prediction_obj)
##############################
# Ground Truth
##############################
if dataset.has_labels:
# Get ground truth labels
easy_gt_objs, medium_gt_objs, \
hard_gt_objs, all_gt_objs = \
demo_utils.get_gts_based_on_difficulty(dataset, img_idx)
else:
easy_gt_objs = medium_gt_objs = hard_gt_objs = all_gt_objs = []
##############################
# 3D IoU
##############################
if draw_ious_3d:
# Convert to box_3d
all_gt_boxes_3d = [box_3d_encoder.object_label_to_box_3d(gt_obj)
for gt_obj in all_gt_objs]
pred_boxes_3d = [box_3d_encoder.object_label_to_box_3d(pred_obj)
for pred_obj in prediction_objs]
max_ious_3d = demo_utils.get_max_ious_3d(all_gt_boxes_3d,
pred_boxes_3d)
##############################
# Point Cloud
##############################
image_path = dataset.get_rgb_image_path(sample_name)
image = cv2.imread(image_path)
print("***************")
print(point_cloud_source)
print(img_idx)
print(image.shape)
point_cloud = dataset.kitti_utils.get_point_cloud(point_cloud_source,
img_idx,
image_shape=image.shape)
print("This is the shape of the point_cloud")
print(point_cloud.shape)
point_cloud = np.asarray(point_cloud)
# Filter point cloud to extents
area_extents = np.asarray([[-40, 40], [-5, 3], [0, 70]])
bev_extents = area_extents[[0, 2]]
points = point_cloud.T
point_filter = obj_utils.get_point_filter(point_cloud, area_extents)
points = points[point_filter]
point_colours = vis_utils.project_img_to_point_cloud(points,
image,
dataset.calib_dir,
img_idx)
# Voxelize the point cloud for visualization
voxel_grid = VoxelGrid()
voxel_grid.voxelize(points, voxel_size=0.1,
create_leaf_layout=False)
# Ground plane
ground_plane = obj_utils.get_road_plane(img_idx, dataset.planes_dir)
##############################
# Visualization
##############################
# Create VtkVoxelGrid
vtk_voxel_grid = VtkVoxelGrid()
vtk_voxel_grid.set_voxels(voxel_grid)
vtk_point_cloud = VtkPointCloud()
vtk_point_cloud.set_points(points, point_colours)
# Create VtkAxes
vtk_axes = vtk.vtkAxesActor()
vtk_axes.SetTotalLength(5, 5, 5)
# Create VtkBoxes for proposal boxes
vtk_proposal_boxes = VtkBoxes()
vtk_proposal_boxes.set_line_width(proposals_line_width)
vtk_proposal_boxes.set_objects(proposal_objs,
COLOUR_SCHEME_PREDICTIONS)
# Create VtkBoxes for prediction boxes
vtk_prediction_boxes = VtkPyramidBoxes()
vtk_prediction_boxes.set_line_width(predictions_line_width)
vtk_prediction_boxes.set_objects(prediction_objs,
COLOUR_SCHEME_PREDICTIONS,
show_orientations)
# Create VtkBoxes for ground truth
vtk_hard_gt_boxes = VtkBoxes()
vtk_medium_gt_boxes = VtkBoxes()
vtk_easy_gt_boxes = VtkBoxes()
vtk_all_gt_boxes = VtkBoxes()
vtk_hard_gt_boxes.set_objects(hard_gt_objs, COLOUR_SCHEME_PREDICTIONS,
show_orientations)
vtk_medium_gt_boxes.set_objects(medium_gt_objs, COLOUR_SCHEME_PREDICTIONS,
show_orientations)
vtk_easy_gt_boxes.set_objects(easy_gt_objs, COLOUR_SCHEME_PREDICTIONS,
show_orientations)
vtk_all_gt_boxes.set_objects(all_gt_objs, VtkBoxes.COLOUR_SCHEME_KITTI,
show_orientations)
# Create VtkTextLabels for 3D ious
vtk_text_labels = VtkTextLabels()
if draw_ious_3d and len(all_gt_boxes_3d) > 0:
gt_positions_3d = np.asarray(all_gt_boxes_3d)[:, 0:3]
vtk_text_labels.set_text_labels(
gt_positions_3d,
['{:0.3f}'.format(iou_3d) for iou_3d in max_ious_3d])
# Create VtkGroundPlane
vtk_ground_plane = VtkGroundPlane()
vtk_slice_bot_plane = VtkGroundPlane()
vtk_slice_top_plane = VtkGroundPlane()
vtk_ground_plane.set_plane(ground_plane, bev_extents)
vtk_slice_bot_plane.set_plane(ground_plane + [0, 0, 0, -0.2], bev_extents)
vtk_slice_top_plane.set_plane(ground_plane + [0, 0, 0, -2.0], bev_extents)
# Create Voxel Grid Renderer in bottom half
vtk_renderer = vtk.vtkRenderer()
vtk_renderer.AddActor(vtk_voxel_grid.vtk_actor)
vtk_renderer.AddActor(vtk_point_cloud.vtk_actor)
vtk_renderer.AddActor(vtk_proposal_boxes.vtk_actor)
vtk_renderer.AddActor(vtk_prediction_boxes.vtk_actor)
vtk_renderer.AddActor(vtk_hard_gt_boxes.vtk_actor)
vtk_renderer.AddActor(vtk_medium_gt_boxes.vtk_actor)
vtk_renderer.AddActor(vtk_easy_gt_boxes.vtk_actor)
vtk_renderer.AddActor(vtk_all_gt_boxes.vtk_actor)
vtk_renderer.AddActor(vtk_text_labels.vtk_actor)
# Add ground plane and slice planes
vtk_renderer.AddActor(vtk_ground_plane.vtk_actor)
vtk_renderer.AddActor(vtk_slice_bot_plane.vtk_actor)
vtk_renderer.AddActor(vtk_slice_top_plane.vtk_actor)
vtk_renderer.AddActor(vtk_axes)
vtk_renderer.SetBackground(0.2, 0.3, 0.4)
# Set initial properties for some actors
vtk_point_cloud.vtk_actor.GetProperty().SetPointSize(3)
vtk_proposal_boxes.vtk_actor.SetVisibility(0)
vtk_voxel_grid.vtk_actor.SetVisibility(0)
vtk_all_gt_boxes.vtk_actor.SetVisibility(0)
vtk_ground_plane.vtk_actor.SetVisibility(0)
vtk_slice_bot_plane.vtk_actor.SetVisibility(0)
vtk_slice_top_plane.vtk_actor.SetVisibility(0)
vtk_ground_plane.vtk_actor.GetProperty().SetOpacity(0.9)
vtk_slice_bot_plane.vtk_actor.GetProperty().SetOpacity(0.9)
vtk_slice_top_plane.vtk_actor.GetProperty().SetOpacity(0.9)
# Setup Camera
current_cam = vtk_renderer.GetActiveCamera()
current_cam.Pitch(140.0)
current_cam.Roll(180.0)
# Zooms out to fit all points on screen
vtk_renderer.ResetCamera()
# Zoom in slightly
current_cam.Zoom(2)
# Reset the clipping range to show all points
vtk_renderer.ResetCameraClippingRange()
# Setup Render Window
vtk_render_window = vtk.vtkRenderWindow()
vtk_render_window.SetWindowName(
"Predictions: Step {}, Sample {}, Min Score {}".format(
global_step,
sample_name,
avod_score_threshold,
))
vtk_render_window.SetSize(900, 600)
vtk_render_window.AddRenderer(vtk_renderer)
# Setup custom interactor style, which handles mouse and key events
vtk_render_window_interactor = vtk.vtkRenderWindowInteractor()
vtk_render_window_interactor.SetRenderWindow(vtk_render_window)
# Add custom interactor to toggle actor visibilities
custom_interactor = vis_utils.CameraInfoInteractorStyle([
vtk_proposal_boxes.vtk_actor,
vtk_prediction_boxes.vtk_actor,
vtk_voxel_grid.vtk_actor,
vtk_point_cloud.vtk_actor,
vtk_easy_gt_boxes.vtk_actor,
vtk_medium_gt_boxes.vtk_actor,
vtk_hard_gt_boxes.vtk_actor,
vtk_all_gt_boxes.vtk_actor,
vtk_ground_plane.vtk_actor,
vtk_slice_bot_plane.vtk_actor,
vtk_slice_top_plane.vtk_actor,
vtk_text_labels.vtk_actor,
])
vtk_render_window_interactor.SetInteractorStyle(custom_interactor)
# Render in VTK
vtk_render_window.Render()
# Take a screenshot
window_to_image_filter = vtk.vtkWindowToImageFilter()
window_to_image_filter.SetInput(vtk_render_window)
window_to_image_filter.Update()
png_writer = vtk.vtkPNGWriter()
file_name = img_out_dir + "/{}.png".format(sample_name)
png_writer.SetFileName(file_name)
png_writer.SetInputData(window_to_image_filter.GetOutput())
png_writer.Write()
print('Screenshot saved to ', file_name)
#vtk_render_window_interactor.Start() # Blocking
vtk_render_window_interactor.Initialize() # Non-Blocking
def main():
# Setting Paths
cam = 2
# dataset_dir = '/media/bradenhurl/hd/gta/object/'
data_set = 'training'
dataset_dir = os.path.expanduser('~') + '/wavedata-dev/demos/gta'
#dataset_dir = os.path.expanduser('~') + '/Kitti/object/'
dataset_dir = os.path.expanduser(
'~') + '/GTAData/TruPercept/object_tru_percept8/'
#Set to true to see predictions (results) from all perspectives
use_results = True
altPerspective = False
perspID = 48133
perspStr = '%07d' % perspID
altPerspect_dir = os.path.join(dataset_dir, data_set + '/alt_perspective/')
if altPerspective:
data_set = data_set + '/alt_perspective/' + perspStr
fromWiseWindows = False
useEVE = False
if fromWiseWindows:
data_set = 'object'
if useEVE:
dataset_dir = '/media/bradenhurl/hd/data/eve/'
else:
dataset_dir = '/media/bradenhurl/hd/data/'
image_dir = os.path.join(dataset_dir, data_set) + '/image_2'
velo_dir = os.path.join(dataset_dir, data_set) + '/velodyne'
calib_dir = os.path.join(dataset_dir, data_set) + '/calib'
if use_results:
label_dir = os.path.join(dataset_dir, data_set) + '/predictions'
else:
label_dir = os.path.join(dataset_dir, data_set) + '/label_2'
base_dir = os.path.join(dataset_dir, data_set)
comparePCs = False
if comparePCs:
velo_dir2 = os.path.join(dataset_dir, data_set) + '/velodyne'
tracking = False
if tracking:
seq_idx = 1
data_set = '%04d' % seq_idx
dataset_dir = '/media/bradenhurl/hd/GTAData/August-01/tracking'
image_dir = os.path.join(dataset_dir, 'images', data_set)
label_dir = os.path.join(dataset_dir, 'labels', data_set)
velo_dir = os.path.join(dataset_dir, 'velodyne', data_set)
calib_dir = os.path.join(dataset_dir, 'training', 'calib', '0000')
#Used for visualizing inferences
#label_dir = '/media/bradenhurl/hd/avod/avod/data/outputs/pyramid_people_gta_40k'
#label_dir = label_dir + '/predictions/kitti_predictions_3d/test/0.02/154000/data/'
closeView = False
pitch = 170
pointSize = 3
zoom = 1
if closeView:
pitch = 180.5
pointSize = 3
zoom = 35
image_list = os.listdir(image_dir)
fulcrum_of_points = True
use_intensity = False
img_idx = 2
print('=== Loading image: {:06d}.png ==='.format(img_idx))
print(image_dir)
image = cv2.imread(image_dir + '/{:06d}.png'.format(img_idx))
image_shape = (image.shape[1], image.shape[0])
if use_intensity:
point_cloud, intensity = obj_utils.get_lidar_point_cloud(
img_idx, calib_dir, velo_dir, ret_i=use_intensity)
else:
point_cloud = obj_utils.get_lidar_point_cloud(img_idx,
calib_dir,
velo_dir,
im_size=image_shape)
if comparePCs:
point_cloud2 = obj_utils.get_lidar_point_cloud(img_idx,
calib_dir,
velo_dir2,
im_size=image_shape)
point_cloud = np.hstack((point_cloud, point_cloud2))
# Reshape points into N x [x, y, z]
all_points = np.array(point_cloud).transpose().reshape((-1, 3))
# Define Fixed Sizes for the voxel grid
x_min = -85
x_max = 85
y_min = -5
y_max = 5
z_min = 3
z_max = 85
x_min = min(point_cloud[0])
x_max = max(point_cloud[0])
y_min = min(point_cloud[1])
y_max = max(point_cloud[1])
#z_min = min(point_cloud[2])
z_max = max(point_cloud[2])
# Filter points within certain xyz range
area_filter = (point_cloud[0] > x_min) & (point_cloud[0] < x_max) & \
(point_cloud[1] > y_min) & (point_cloud[1] < y_max) & \
(point_cloud[2] > z_min) & (point_cloud[2] < z_max)
all_points = all_points[area_filter]
#point_colours = np.zeros(point_cloud.shape[1],0)
#print(point_colours.shape)
if fulcrum_of_points:
# Get point colours
point_colours = vis_utils.project_img_to_point_cloud(
all_points, image, calib_dir, img_idx)
print("Point colours shape: ", point_colours.shape)
print("Sample 0 of colour: ", point_colours[0])
elif use_intensity:
adjusted = intensity == 65535
intensity = intensity > 0
intensity = np.expand_dims(intensity, -1)
point_colours = np.hstack(
(intensity * 255, intensity * 255 - adjusted * 255,
intensity * 255 - adjusted * 255))
print("Intensity shape:", point_colours.shape)
print("Intensity sample: ", point_colours[0])
# Create Voxel Grid
voxel_grid = VoxelGrid()
voxel_grid_extents = [[x_min, x_max], [y_min, y_max], [z_min, z_max]]
print(voxel_grid_extents)
start_time = time.time()
voxel_grid.voxelize(all_points, 0.2, voxel_grid_extents)
end_time = time.time()
print("Voxelized in {} s".format(end_time - start_time))
# Get bounding boxes
gt_detections = obj_utils.read_labels(label_dir,
img_idx,
results=use_results)
if gt_detections is None:
gt_detections = []
#perspective_utils.to_world(gt_detections, base_dir, img_idx)
#perspective_utils.to_perspective(gt_detections, base_dir, img_idx)
for entity_str in os.listdir(altPerspect_dir):
if os.path.isdir(os.path.join(altPerspect_dir, entity_str)):
perspect_detections = perspective_utils.get_detections(
base_dir,
altPerspect_dir,
img_idx,
perspID,
entity_str,
results=use_results)
if perspect_detections != None:
if use_results:
stripped_detections = trust_utils.strip_objs(
perspect_detections)
gt_detections = gt_detections + stripped_detections
else:
gt_detections = gt_detections + perspect_detections
# Create VtkPointCloud for visualization
vtk_point_cloud = VtkPointCloud()
if fulcrum_of_points or use_intensity:
vtk_point_cloud.set_points(all_points, point_colours)
else:
vtk_point_cloud.set_points(all_points)
vtk_point_cloud.vtk_actor.GetProperty().SetPointSize(pointSize)
# Create VtkVoxelGrid for visualization
vtk_voxel_grid = VtkVoxelGrid()
vtk_voxel_grid.set_voxels(voxel_grid)
COLOUR_SCHEME_PAPER = {
"Car": (0, 0, 255), # Blue
"Pedestrian": (255, 0, 0), # Red
"Bus": (0, 0, 255), #Blue
"Cyclist": (150, 50, 100), # Purple
"Van": (255, 150, 150), # Peach
"Person_sitting": (150, 200, 255), # Sky Blue
"Truck": (0, 0, 255), # Light Grey
"Tram": (150, 150, 150), # Grey
"Misc": (100, 100, 100), # Dark Grey
"DontCare": (255, 255, 255), # White
}
# Create VtkBoxes for boxes
vtk_boxes = VtkBoxes()
vtk_boxes.set_objects(gt_detections,
COLOUR_SCHEME_PAPER) #vtk_boxes.COLOUR_SCHEME_KITTI)
# Create Axes
axes = vtk.vtkAxesActor()
axes.SetTotalLength(5, 5, 5)
# Create Voxel Grid Renderer in bottom half
vtk_renderer = vtk.vtkRenderer()
vtk_renderer.AddActor(vtk_point_cloud.vtk_actor)
vtk_renderer.AddActor(vtk_voxel_grid.vtk_actor)
vtk_renderer.AddActor(vtk_boxes.vtk_actor)
#vtk_renderer.AddActor(axes)
vtk_renderer.SetBackground(0.2, 0.3, 0.4)
# Setup Camera
current_cam = vtk_renderer.GetActiveCamera()
current_cam.Pitch(pitch)
current_cam.Roll(180.0)
# Zooms out to fit all points on screen
vtk_renderer.ResetCamera()
# Zoom in slightly
current_cam.Zoom(zoom)
# Reset the clipping range to show all points
vtk_renderer.ResetCameraClippingRange()
# Setup Render Window
vtk_render_window = vtk.vtkRenderWindow()
vtk_render_window.SetWindowName(
"Point Cloud and Voxel Grid, Image {}".format(img_idx))
vtk_render_window.SetSize(1920, 1080)
vtk_render_window.AddRenderer(vtk_renderer)
# Setup custom interactor style, which handles mouse and key events
vtk_render_window_interactor = vtk.vtkRenderWindowInteractor()
vtk_render_window_interactor.SetRenderWindow(vtk_render_window)
# Add custom interactor to toggle actor visibilities
vtk_render_window_interactor.SetInteractorStyle(
vis_utils.ToggleActorsInteractorStyle([
vtk_point_cloud.vtk_actor,
vtk_voxel_grid.vtk_actor,
vtk_boxes.vtk_actor,
]))
# Show image
image = cv2.imread(image_dir + "/%06d.png" % img_idx)
cv2.imshow("Press any key to continue", image)
cv2.waitKey()
# Render in VTK
vtk_render_window.Render()
vtk_render_window_interactor.Start() # Blocking
def vis_pc(pc, obj_list, frustum_points=None):
# Define Fixed Sizes for the voxel grid
x_min = -85
x_max = 85
y_min = -5
y_max = 5
z_min = 3
z_max = 85
# Comment these out to filter points by area
x_min = min(pc[0])
x_max = max(pc[0])
y_min = min(pc[1])
y_max = max(pc[1])
z_min = min(pc[2])
z_max = max(pc[2])
# Reshape points into N x [x, y, z]
all_points = np.array(pc).transpose().reshape((-1, 3))
# Filter points within certain xyz range
area_filter = (pc[0] > x_min) & (pc[0] < x_max) & \
(pc[1] > y_min) & (pc[1] < y_max) & \
(pc[2] > z_min) & (pc[2] < z_max)
all_points = all_points[area_filter]
# Create Voxel Grid
voxel_grid = VoxelGrid()
voxel_grid_extents = [[x_min, x_max], [y_min, y_max], [z_min, z_max]]
print(voxel_grid_extents)
start_time = time.time()
voxel_grid.voxelize(all_points, 0.2, voxel_grid_extents)
end_time = time.time()
print("Voxelized in {} s".format(end_time - start_time))
# Some settings for the initial camera view and point size
closeView = False
pitch = 170
pointSize = 4
zoom = 1
if closeView:
pitch = 180.5
pointSize = 3
zoom = 35
# Create VtkPointCloud for visualization
vtk_point_cloud = VtkPointCloud()
vtk_point_cloud.set_points(all_points)
vtk_point_cloud.vtk_actor.GetProperty().SetPointSize(pointSize)
# Create VtkVoxelGrid for visualization
vtk_voxel_grid = VtkVoxelGrid()
vtk_voxel_grid.set_voxels(voxel_grid)
# Create VtkBoxes for boxes
vtk_boxes = VtkBoxes()
vtk_boxes.set_objects(obj_list, COLOUR_SCHEME, False)
# Create Axes
axes = vtk.vtkAxesActor()
axes.SetTotalLength(2, 2, 2)
# Create Voxel Grid Renderer in bottom half
vtk_renderer = vtk.vtkRenderer()
vtk_renderer.AddActor(vtk_point_cloud.vtk_actor)
vtk_renderer.AddActor(vtk_voxel_grid.vtk_actor)
vtk_renderer.AddActor(vtk_boxes.vtk_actor)
vtk_renderer.AddActor(axes)
vtk_renderer.SetBackground(0.2, 0.3, 0.4)
# Add lines for frustum
if frustum_points is not None:
frustum_actor = get_frustum_actor(frustum_points)
vtk_renderer.AddActor(frustum_actor)
# Setup Camera
current_cam = vtk_renderer.GetActiveCamera()
current_cam.Pitch(pitch)
current_cam.Roll(180.0)
# Zooms out to fit all points on screen
vtk_renderer.ResetCamera()
# Zoom in slightly
current_cam.Zoom(zoom)
# Zoom/navigate to the desired camera view then exit
# Three lines will be output. Paste these here
# Above forward view
current_cam.SetPosition(7.512679241328601, -312.20497623371926, -130.38469206536766)
current_cam.SetViewUp(-0.01952407393317445, -0.44874501090739727, 0.893446543293314)
current_cam.SetFocalPoint(11.624950999358777, 14.835920755080867, 33.965665867613836)
# Reset the clipping range to show all points
vtk_renderer.ResetCameraClippingRange()
# Setup Render Window
vtk_render_window = vtk.vtkRenderWindow()
vtk_render_window.SetWindowName(
"Point Cloud and Voxel Grid")
vtk_render_window.SetSize(1920, 1080)
vtk_render_window.AddRenderer(vtk_renderer)
# Setup custom interactor style, which handles mouse and key events
vtk_render_window_interactor = vtk.vtkRenderWindowInteractor()
vtk_render_window_interactor.SetRenderWindow(vtk_render_window)
# Add custom interactor to toggle actor visibilities
vtk_render_window_interactor.SetInteractorStyle(
vis_utils.ToggleActorsInteractorStyle([
vtk_point_cloud.vtk_actor,
vtk_voxel_grid.vtk_actor,
vtk_boxes.vtk_actor,
]))
# Render in VTK
vtk_render_window.Render()
vtk_render_window_interactor.Start() # Blocking
def visualize_objects_in_pointcloud(objects, COLOUR_SCHEME, dataset_dir,
img_idx, fulcrum_of_points, use_intensity,
receive_from_perspective, compare_pcs=False,
show_3d_point_count=False, show_orientation=cfg.VISUALIZE_ORIENTATION,
final_results=False, show_score=False,
compare_with_gt=False, show_image=True,
_text_positions=None, _text_labels=None):
image_dir = os.path.join(dataset_dir, 'image_2')
velo_dir = os.path.join(dataset_dir, 'velodyne')
calib_dir = os.path.join(dataset_dir, 'calib')
if compare_pcs:
fulcrum_of_points = False
print('=== Loading image: {:06d}.png ==='.format(img_idx))
print(image_dir)
image = cv2.imread(image_dir + '/{:06d}.png'.format(img_idx))
image_shape = (image.shape[1], image.shape[0])
if use_intensity:
point_cloud,intensity = obj_utils.get_lidar_point_cloud(img_idx, calib_dir, velo_dir,
ret_i=use_intensity)
else:
point_cloud = obj_utils.get_lidar_point_cloud(img_idx, calib_dir, velo_dir,
im_size=image_shape)
if compare_pcs:
receive_persp_dir = os.path.join(altPerspect_dir, '{:07d}'.format(receive_from_perspective))
velo_dir2 = os.path.join(receive_persp_dir, 'velodyne')
print(velo_dir2)
if not os.path.isdir(velo_dir2):
print("Error: cannot find velo_dir2: ", velo_dir2)
exit()
point_cloud2 = obj_utils.get_lidar_point_cloud(img_idx, calib_dir, velo_dir2,
im_size=image_shape)
#Set to true to display point clouds in world coordinates (for debugging)
display_in_world=False
if display_in_world:
point_cloud = perspective_utils.pc_to_world(point_cloud.T, receive_persp_dir, img_idx)
point_cloud2 = perspective_utils.pc_to_world(point_cloud2.T, dataset_dir, img_idx)
point_cloud = np.hstack((point_cloud.T, point_cloud2.T))
else:
point_cloud2 = perspective_utils.pc_persp_transform(point_cloud2.T, receive_persp_dir, dataset_dir, img_idx)
point_cloud = np.hstack((point_cloud, point_cloud2.T))
# Reshape points into N x [x, y, z]
all_points = np.array(point_cloud).transpose().reshape((-1, 3))
# Define Fixed Sizes for the voxel grid
x_min = -85
x_max = 85
y_min = -5
y_max = 5
z_min = 3
z_max = 85
# Comment these out to filter points by area
x_min = min(point_cloud[0])
x_max = max(point_cloud[0])
y_min = min(point_cloud[1])
y_max = max(point_cloud[1])
z_min = min(point_cloud[2])
z_max = max(point_cloud[2])
# Filter points within certain xyz range
area_filter = (point_cloud[0] > x_min) & (point_cloud[0] < x_max) & \
(point_cloud[1] > y_min) & (point_cloud[1] < y_max) & \
(point_cloud[2] > z_min) & (point_cloud[2] < z_max)
all_points = all_points[area_filter]
point_colours = None
if fulcrum_of_points:
# Get point colours
point_colours = vis_utils.project_img_to_point_cloud(all_points, image,
calib_dir, img_idx)
elif use_intensity:
adjusted = intensity == 65535
intensity = intensity > 0
intensity = np.expand_dims(intensity,-1)
point_colours = np.hstack((intensity*255,intensity*255-adjusted*255,intensity*255-adjusted*255))
# Create Voxel Grid
voxel_grid = VoxelGrid()
voxel_grid_extents = [[x_min, x_max], [y_min, y_max], [z_min, z_max]]
print(voxel_grid_extents)
start_time = time.time()
voxel_grid.voxelize(all_points, 0.2, voxel_grid_extents)
end_time = time.time()
print("Voxelized in {} s".format(end_time - start_time))
# Some settings for the initial camera view and point size
closeView = False
pitch = 170
pointSize = 2
zoom = 1
if closeView:
pitch = 180.5
pointSize = 3
zoom = 35
# Create VtkPointCloud for visualization
vtk_point_cloud = VtkPointCloud()
if point_colours is not None:
vtk_point_cloud.set_points(all_points, point_colours)
else:
vtk_point_cloud.set_points(all_points)
vtk_point_cloud.vtk_actor.GetProperty().SetPointSize(pointSize)
# Create VtkVoxelGrid for visualization
vtk_voxel_grid = VtkVoxelGrid()
vtk_voxel_grid.set_voxels(voxel_grid)
# Create VtkBoxes for boxes
vtk_boxes = VtkBoxes()
vtk_boxes.set_objects(objects, COLOUR_SCHEME, show_orientation)#vtk_boxes.COLOUR_SCHEME_KITTI)
# Create Axes
axes = vtk.vtkAxesActor()
axes.SetTotalLength(5, 5, 5)
# Create Voxel Grid Renderer in bottom half
vtk_renderer = vtk.vtkRenderer()
vtk_renderer.AddActor(vtk_point_cloud.vtk_actor)
vtk_renderer.AddActor(vtk_voxel_grid.vtk_actor)
vtk_renderer.AddActor(vtk_boxes.vtk_actor)
vtk_renderer.AddActor(axes)
if _text_positions is not None:
vtk_text_labels = VtkTextLabels()
vtk_text_labels.set_text_labels(_text_positions, _text_labels)
vtk_renderer.AddActor(vtk_text_labels.vtk_actor)
vtk_renderer.SetBackground(0.2, 0.3, 0.4)
# Setup Camera
current_cam = vtk_renderer.GetActiveCamera()
current_cam.Pitch(pitch)
current_cam.Roll(180.0)
# Zooms out to fit all points on screen
vtk_renderer.ResetCamera()
# Zoom in slightly
current_cam.Zoom(zoom)
# Zoom/navigate to the desired camera view then exit
# Three lines will be output. Paste these here
# Above forward view
current_cam.SetPosition(7.512679241328601, -312.20497623371926, -130.38469206536766)
current_cam.SetViewUp(-0.01952407393317445, -0.44874501090739727, 0.893446543293314)
current_cam.SetFocalPoint(11.624950999358777, 14.835920755080867, 33.965665867613836)
# Top down view of synchronization
current_cam.SetPosition(28.384757950371405, -125.46190537888288, 63.60263366961189)
current_cam.SetViewUp(-0.02456679343399302, 0.0030507437719906913, 0.9996935358512673)
current_cam.SetFocalPoint(27.042134804730317, 15.654378427929846, 63.13899801247614)
current_cam.SetPosition(30.3869590224831, -50.28910856489952, 60.097631136698965)
current_cam.SetViewUp(-0.0237472244952177, -0.06015048799392083, 0.997906803325274)
current_cam.SetFocalPoint(27.06695416156647, 15.347824332314035, 63.97499987548391)
# current_cam.SetPosition(14.391008769593322, -120.06549828061613, -1.567028749253062)
# current_cam.SetViewUp(-0.02238762832327178, -0.1049057307562059, 0.9942301452644481)
# current_cam.SetFocalPoint(10.601112314728102, 20.237110061924664, 13.151596441968126)
# # Top down view of whole detection area
# current_cam.SetPosition(11.168659642537031, -151.97163016078756, 17.590894639193227)
# current_cam.SetViewUp(-0.02238762832327178, -0.1049057307562059, 0.9942301452644481)
# current_cam.SetFocalPoint(6.5828849321501055, 17.79452593368671, 35.400431120570865)
# Top down view of scenario
current_cam.SetPosition(2.075612197299923, -76.19063612245675, 5.948366424752178)
current_cam.SetViewUp(-0.02238762832327178, -0.1049057307562059, 0.9942301452644481)
current_cam.SetFocalPoint(-0.5129380758134061, 19.637933198314016, 16.00138547483155)
# Reset the clipping range to show all points
vtk_renderer.ResetCameraClippingRange()
# Setup Render Window
vtk_render_window = vtk.vtkRenderWindow()
vtk_render_window.SetWindowName(
"Point Cloud and Voxel Grid, Image {}".format(img_idx))
vtk_render_window.SetSize(1920, 1080)
vtk_render_window.AddRenderer(vtk_renderer)
# Setup custom interactor style, which handles mouse and key events
vtk_render_window_interactor = vtk.vtkRenderWindowInteractor()
vtk_render_window_interactor.SetRenderWindow(vtk_render_window)
# Add custom interactor to toggle actor visibilities
vtk_render_window_interactor.SetInteractorStyle(
vis_utils.ToggleActorsInteractorStyle([
vtk_point_cloud.vtk_actor,
vtk_voxel_grid.vtk_actor,
vtk_boxes.vtk_actor,
]))
# Show image
if show_image:
image = cv2.imread(image_dir + "/%06d.png" % img_idx)
cv2.imshow("Press any key to continue", image)
cv2.waitKey()
# Render in VTK
vtk_render_window.Render()
vtk_render_window_interactor.Start() # Blocking
# vtk_render_window_interactor.Initialize() # Non-Blocking
# Obtain camera positional information for repeatable views
print("current_cam.SetPosition{}".format(current_cam.GetPosition()))
print("current_cam.SetViewUp{}".format(current_cam.GetViewUp()))
print("current_cam.SetFocalPoint{}".format(current_cam.GetFocalPoint()))