if im_ids:
im_ids_curr = set(im_ids_curr).intersection(im_ids)
active_ratio = 0.6
for im_id in im_ids_curr:
start_time = time.time()
print('#' * 20)
print('scene: {}, im: {}'.format(scene_id, im_id))
K = scene_info[im_id]['cam_K']
# Load the images
rgb = inout.load_im(dp['test_rgb_mpath'].format(scene_id, im_id))
depth = inout.load_depth(dp['test_depth_mpath'].format(scene_id, im_id))
depth *= dp['cam']['depth_scale']
depth = depth.astype(np.uint16) # [mm]
im_size = (depth.shape[1], depth.shape[0])
match_ids = list()
for radius in dep_anchors:
match_ids.append('{:02d}_template_{}'.format(obj_id_in_scene, radius))
# srcs, score for one part, active ratio, may be too low for simple objects so too many candidates?
matches = detector.match([rgb, depth], 70, active_ratio,
match_ids, dep_anchors, dep_range, masks=[])
depth_edge = poseRefine.get_depth_edge(depth) # already dilute & distant transform
depth_edge = (depth_edge < 1.01).astype(np.uint8)*255 # dilute once more
misc.ensure_dir(
os.path.dirname(vis_mpath.format(dataset, delta, data_id, 0, 0)))
# Load scene info and gts
info = inout.load_info(dp[info_mpath_key].format(data_id))
gts = inout.load_gt(dp[gt_mpath_key].format(data_id))
im_ids = sorted(gts.keys())
gt_stats = {}
for im_id in im_ids:
print('dataset: {}, scene/obj: {}, im: {}'.format(
dataset, data_id, im_id))
K = info[im_id]['cam_K']
depth_path = dp[depth_mpath_key].format(data_id, im_id)
depth_im = inout.load_depth(depth_path)
depth_im *= dp['cam']['depth_scale'] # to [mm]
im_size = (depth_im.shape[1], depth_im.shape[0])
gt_stats[im_id] = []
for gt_id, gt in enumerate(gts[im_id]):
depth_gt = renderer.render(models[gt['obj_id']],
im_size,
K,
gt['cam_R_m2c'],
gt['cam_t_m2c'],
mode='depth')
# Get distance images
dist_gt = misc.depth_im_to_dist_im(depth_gt, K)
dist_im = misc.depth_im_to_dist_im(depth_im, K)
info = inout.load_info(dp[info_mpath_key].format(data_id))
gts = inout.load_gt(dp[gt_mpath_key].format(data_id))
# Considered subset of images for the current scene
if im_ids_sets is not None:
im_ids = im_ids_sets[data_id]
else:
im_ids = sorted(gts.keys())
gt_stats = {}
for im_id in im_ids:
print('dataset: {}, scene/obj: {}, im: {}'.format(dataset, data_id, im_id))
K = info[im_id]['cam_K']
depth_path = dp[depth_mpath_key].format(data_id, im_id)
depth_im = inout.load_depth(depth_path)
depth_im *= dp['cam']['depth_scale'] # to [mm]
im_size = (depth_im.shape[1], depth_im.shape[0])
gt_stats[im_id] = []
for gt_id, gt in enumerate(gts[im_id]):
depth_gt = renderer.render(models[gt['obj_id']], im_size, K,
gt['cam_R_m2c'], gt['cam_t_m2c'],
mode='depth')
# Get distance images
dist_gt = misc.depth_im_to_dist_im(depth_gt, K)
dist_im = misc.depth_im_to_dist_im(depth_im, K)
# Estimation of visibility mask
visib_gt = visibility.estimate_visib_mask_gt(dist_im, dist_gt, delta)
obj_id = scene_id # The object id is the same as scene id for this dataset
model = inout.load_ply(model_mpath.format(obj_id))
# Transformation which was applied to the object models (its inverse will
# be applied to the GT poses):
# 1) Translate the bounding box center to the origin
t_model = bbox_cens[obj_id - 1, :].reshape((3, 1))
im_id_out = 0
for im_id in im_ids:
# if im_id % 10 == 0:
print('scene,view: ' + str(scene_id) + ',' + str(im_id))
# Load the RGB and depth image
rgb = inout.load_im(rgb_in_mpath.format(scene_id, im_id))
depth = inout.load_depth(depth_in_mpath.format(scene_id, im_id))
depth *= 10.0 # Convert depth map to [100um]
# Save the RGB and depth image
inout.save_im(rgb_out_mpath.format(scene_id, im_id_out), rgb)
inout.save_depth(depth_out_mpath.format(scene_id, im_id_out), depth)
scene_info[im_id_out] = {'cam_K': par['cam']['K'].flatten().tolist()}
# Process the GT poses
poses = load_tejani_poses(pose_mpath.format(scene_id, im_id))
scene_gt[im_id_out] = []
for pose in poses:
R_m2c = pose['R']
t_m2c = pose['t']
if im_ids_sets is not None:
im_ids_curr = im_ids_sets[scene_id]
else:
im_ids_curr = sorted(scene_info.keys())
if im_ids:
im_ids_curr = set(im_ids_curr).intersection(im_ids)
for im_id in im_ids_curr:
print('scene: {}, im: {}'.format(scene_id, im_id))
K = scene_info[im_id]['cam_K']
render_K = K
# Load the images
rgb = inout.load_im(dp['test_rgb_mpath'].format(scene_id, im_id))
depth = inout.load_depth(dp['test_depth_mpath'].format(scene_id, im_id))
depth = depth.astype(np.uint16) # [mm]
# depth *= dp['cam']['depth_scale'] # to [mm]
im_size = (depth.shape[1], depth.shape[0])
match_ids = list()
match_ids.append('{:02d}_template'.format(scene_id))
start_time = time.time()
# result = cxx_3d_seg.convex_cloud_seg(rgb, depth, K.astype(np.float32))
result = cxx_3d_seg_pybind.convex_cloud_seg(rgb, depth, K.astype(np.float32))
indices = result.getIndices()
cloud = result.getCloud()
normal = result.getNormal()
# just test one seg result, may break because it's not guaranteed as an object mask
