Skip to content

Allow masking of images for dynamic objects #190

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Allow masking of images for dynamic objects #190

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 15 additions & 2 deletions hloc/extract_features.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -158,6 +158,7 @@ def __init__(self, root, conf, paths=None):
self.conf = conf = SimpleNamespace(**{**self.default_conf, **conf})
self.root = root


if paths is None:
paths = []
for g in conf.globs:
Expand All @@ -184,6 +185,7 @@ def __init__(self, root, conf, paths=None):
def __getitem__(self, idx):
name = self.names[idx]
image = read_image(self.root / name, self.conf.grayscale)

image = image.astype(np.float32)
size = image.shape[:2][::-1]

Expand Down Expand Up @@ -217,10 +219,12 @@ def main(conf: Dict,
as_half: bool = True,
image_list: Optional[Union[Path, List[str]]] = None,
feature_path: Optional[Path] = None,
overwrite: bool = False) -> Path:
overwrite: bool = False,
mask_dir: Optional[Path] = None,
) -> Path:
logger.info('Extracting local features with configuration:'
f'\n{pprint.pformat(conf)}')

loader = ImageDataset(image_dir, conf['preprocessing'], image_list)
loader = torch.utils.data.DataLoader(loader, num_workers=1)

Expand Down Expand Up @@ -250,9 +254,18 @@ def main(conf: Dict,
size = np.array(data['image'].shape[-2:][::-1])
scales = (original_size / size).astype(np.float32)
pred['keypoints'] = (pred['keypoints'] + .5) * scales[None] - .5
if mask_dir is not None:
mask = cv2.imread(str(mask_dir / name) + '.png')[:, :, 0]

valid_keypoint = mask[pred['keypoints'][:, 1].astype('int'), pred['keypoints'][:, 0].astype('int')]
pred['keypoints'] = pred['keypoints'][valid_keypoint > 0]
pred['descriptors'] = pred['descriptors'][:, valid_keypoint > 0]
pred['scores'] = pred['scores'][valid_keypoint > 0]
# add keypoint uncertainties scaled to the original resolution
uncertainty = getattr(model, 'detection_noise', 1) * scales.mean()



if as_half:
for k in pred:
dt = pred[k].dtype
Expand Down