def detect(self, image):
if self.model is None:
return {}
image = image.convert('RGB')
width, height = image.size
image.thumbnail((1024, 1024))
image = img_to_array(image)
result = self.model.detect([image])[0]
masks = result.get('masks')
class_ids = result.get('class_ids')
coco_image = im.Image(width=width, height=height)
for i in range(masks.shape[-1]):
mask = resize(masks[..., i], (height, width))
mask = im.Mask(mask)
class_id = class_ids[i]
class_name = CLASS_NAMES[class_id]
category = im.Category(class_name)
coco_image.add(mask, category=category)
return coco_image.coco()
def prepare_dataset(self, all_images=False):
dataset = imantics.Dataset('INbreast')
categories_names = list(self.annotations_df.category.unique())
colors = {name: imantics.Color.random() for name in categories_names}
categories = {
name: imantics.Category(name, id=i, color=colors[name])
for i, name in enumerate(categories_names)
}
total = len(self.annotations_df)
prepared = 0
for case_id, annotations_data in self.annotations_df.groupby(
'case_id'):
width = annotations_data['width'].unique()[0]
height = annotations_data['height'].unique()[0]
image = imantics.Image(id=case_id, width=width, height=height)
image.file_name = '%d.png' % case_id
annotations = []
for _, annotation_data in annotations_data.iterrows():
annotation_id = annotation_data['annotation_id']
category = categories[annotation_data['category']]
color = colors[annotation_data['category']]
points = annotation_data['points']
annotation = imantics.Annotation(id=annotation_id,
polygons=[points],
category=category,
color=color)
annotations.append(annotation)
image.add(annotations)
dataset.add(image)
prepared += 1
print('\r%d %d/%d' % (case_id, prepared, total), end="")
print('\rprepared %d images' % prepared)
print()
self.dataset = dataset
def __call__(self):
""" Generates imantics category object """
data = {
'name': self.name,
'color': self.color,
'parent': self.supercategory,
'metadata': self.metadata,
'id': self.id
}
return im.Category(**data)
def to_imantics_annotation(self):
"""
Returns imantics.annotation.Annotation representation of ObjectAnnotation.
"""
imantics_category = imantics.Category(
id=self.category.id, name=self.category.name
)
imantics_mask = imantics.Mask.create(self.mask.bool_mask)
imantics_annotation = imantics.annotation.Annotation.from_mask(
mask=imantics_mask, category=imantics_category
)
return imantics_annotation
def imageCallback(self, img_msg, info_msg):
try:
img = self.bridge.imgmsg_to_cv2(img_msg, "bgr8")
header = img_msg.header
except CvBridgeError as err:
rospy.logerr(err)
return
board_mask = np.zeros_like(img[:, :, 0])
if (self.image_roi is None):
board_mask[:, :] = 1
else:
board_mask[self.image_roi[0]:self.image_roi[1],
self.image_roi[2]:self.image_roi[3]] = 1
board_size = board_mask.sum()
all_markers = segmentImage(img, self.filter_size, self.filter_const)
markers_masked = (all_markers + 1) * board_mask
filtered_idxs, filtered_counts = filterMarkers(markers_masked,
board_size / 250,
board_size / 3)
markers_masked[np.isin(markers_masked, filtered_idxs, invert=True)] = 0
ann_img = imantics.Image(image_array=img)
colors = [(255, 0, 0), (0, 255, 0), (0, 0, 255), (0, 255, 255),
(255, 0, 255), (255, 255, 0)]
for j, idx in enumerate(filtered_idxs):
mask = imantics.Mask((markers_masked == idx).astype(np.uint8))
ann = imantics.Annotation(image=ann_img,
category=imantics.Category(
'obj_{}'.format(j),
color=imantics.Color(rgb=colors[j])),
mask=mask,
bbox=imantics.BBox.from_mask(mask))
ann_img.add(ann)
display_img = ann_img.draw(thickness=1, color_by_category=True)
try:
display_msg = self.bridge.cv2_to_imgmsg(display_img.astype(
np.uint8),
encoding="bgr8")
except CvBridgeError as err:
rospy.logerr(err)
return
display_msg.header = img_msg.header
self.image_pub.publish(display_msg)
def to_imantics_annotation(self):
"""
Returns imantics.annotation.Annotation representation of ObjectAnnotation.
"""
try:
import imantics
except ImportError:
raise ImportError(
'Please run "pip install -U imantics" '
"to install imantics first for imantics conversion.")
imantics_category = imantics.Category(id=self.category.id,
name=self.category.name)
if self.mask is not None:
imantics_mask = imantics.Mask.create(self.mask.bool_mask)
imantics_annotation = imantics.annotation.Annotation.from_mask(
mask=imantics_mask, category=imantics_category)
else:
imantics_bbox = imantics.BBox.create(self.bbox.to_voc_bbox())
imantics_annotation = imantics.annotation.Annotation.from_bbox(
bbox=imantics_bbox, category=imantics_category)
return imantics_annotation
import imantics
import scipy as sp
import cv2
import os
from tqdm import tqdm
import json
from joblib import Parallel, delayed
image_id = 1
annotation_id = 1
coco_dataset = {'images': [], 'categories': [], 'annotations': []}
basedir = '/home/spadmin/data/lostandfound_processing/testset'
categories = {1: imantics.Category('void'), 2: imantics.Category('object')}
i = 0
# loads ego-vehicle mask
with open(
'/home/spadmin/Downloads/0000_02_Hanns_Klemm_Str_44_000000_000020_leftImg8bit_rgb (1).json',
'r') as f:
coco_vehicle = json.load(f)
ego_mask = coco_vehicle['annotations'][0]['segmentation'][0]
ego_points = np.array(ego_mask).reshape((-1, 2)).round().astype('int')
vehicle_mask = np.zeros((1024, 2048, 1))
cv2.fillPoly(vehicle_mask, [ego_points], color=(100, 100, 100))
vehicle_mask = vehicle_mask[..., 0]
def process_image(file, image_id):
""" Assumes that prediction and image file have similar prefix, see below"""
prediction = cv2.imread(os.path.join(basedir, file), cv2.IMREAD_ANYDEPTH)
# reduce noise (makes it easier to edit predictions)
in_dicoms_dir = osp.join(inbreast_dir, 'AllDICOMs')
in_images_dir = images_dir
out_images_dir = osp.join(output_dir, 'images')
out_annotations_dir = osp.join(out_images_dir, 'annotations')
# cases_ids = [20586960]
cases_ids = sorted([
int(osp.basename(x).split('_')[0])
for x in glob(osp.join(in_xmls_dir, '*.xml'))
])
os.makedirs(out_images_dir, exist_ok=True)
os.makedirs(out_annotations_dir, exist_ok=True)
dataset = imantics.Dataset('INbreast - prectoral muscle')
category_breast = imantics.Category('breast')
category_pectoral_muscle = imantics.Category('pectoral_muscle')
index_breast = 0
index_pectoral_muscle = 1
total = len(cases_ids)
processed = 0
for case_id in cases_ids:
# check annotation
anns_fns = glob(osp.join(in_xmls_dir, '*%d*.xml' % case_id))
assert len(anns_fns) == 1
ann_fn = anns_fns[0]
# check dicom
dcms_fns = glob(osp.join(in_dicoms_dir, '*%d*.dcm' % case_id))
assert len(dcms_fns) == 1
dcm_fn = dcms_fns[0]