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 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)
prediction = (prediction == 19).astype('int32')
for _ in range(2):
prediction = sp.ndimage.median_filter(prediction, size=12)
# remove part where there is obvious street and ego-vehicle
prediction[700:, 500:1750] = 0
prediction[vehicle_mask != 0] = 1
annotation = imantics.Image(width=2048, height=1024)
for c in categories:
annotation.add(imantics.Mask(prediction == c), category=categories[c])
coco_dataset['images'].append({
'id':
image_id,
'dataset_id':
1,
'path':
"/datasets/lostandfound/{}".format(file[:-10] + 'rgb.png'),
'width':
2048,
'height':
1024,
'file_name':
file[:-10] + 'rgb.png'
})
coco_annotations = annotation.coco()['annotations']
for coco_annotation in coco_annotations:
coco_annotation['id'] = 0
coco_annotation['image_id'] = image_id
coco_annotation['dataset_id'] = 1
return coco_annotations
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 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)
# resize
breast_mask_gray = cv2.resize(breast_mask_gray, scaled_dim)
pm_mask_gray = cv2.resize(pm_mask_gray, scaled_dim)
# save images
img_rescaled_fn = osp.join(out_images_dir, '%d.png' % case_id)
img_breat_mask_fn = osp.join(out_annotations_dir,
'%d_pixels%d.png' % (case_id, index_breast))
pm_mask_fn = osp.join(out_annotations_dir,
'%d_pixels%d.png' % (case_id, index_pectoral_muscle))
img_rescaled = cv2.resize(img, scaled_dim)
cv2.imwrite(img_rescaled_fn, img_rescaled)
cv2.imwrite(img_breat_mask_fn, breast_mask_gray)
cv2.imwrite(pm_mask_fn, pm_mask_gray)
# add to coco
coco_image = imantics.Image(id=case_id,
width=scaled_dim[1],
height=scaled_dim[0])
coco_image.file_name = '%d.png' % case_id
breast_mask_mask = imantics.Mask.create(breast_mask_gray)
pm_mask_mask = imantics.Mask.create(pm_mask_gray)
breast_annotation = imantics.Annotation(mask=breast_mask_mask,
category=category_breast,
color=category_breast.color)
pectoral_muscle_annotation = imantics.Annotation(
mask=pm_mask_mask,
category=category_pectoral_muscle,
color=category_pectoral_muscle.color)
coco_image.add(breast_annotation)
coco_image.add(pectoral_muscle_annotation)
dataset.add(coco_image)
# show debug