Spaces:
Build error
Build error
File size: 56,167 Bytes
1865436 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 |
# Edit by Yao Lu
#
# Copyright (c) Facebook, Inc. and its affiliates.
import colorsys
import logging
import math
import numpy as np
from enum import Enum, unique
import cv2
import matplotlib as mpl
import matplotlib.colors as mplc
import matplotlib.figure as mplfigure
import pycocotools.mask as mask_util
import torch
from matplotlib.backends.backend_agg import FigureCanvasAgg
from PIL import Image
from detectron2.data import MetadataCatalog
from detectron2.structures import BitMasks, Boxes, BoxMode, Keypoints, PolygonMasks, RotatedBoxes
from detectron2.utils.file_io import PathManager
from .colormap import random_color
from shapely.geometry import *
import pickle
import matplotlib.font_manager as mfm
logger = logging.getLogger(__name__)
__all__ = ["ColorMode", "VisImage", "Visualizer"]
_SMALL_OBJECT_AREA_THRESH = 1000
_LARGE_MASK_AREA_THRESH = 120000
_OFF_WHITE = (1.0, 1.0, 240.0 / 255)
_BLACK = (0, 0, 0)
_RED = (1.0, 0, 0)
_KEYPOINT_THRESHOLD = 0.05
def py_cpu_pnms(dets, scores, thresh):
pts = dets
# for i in xrange(dets.shape[0]):
# pts.append([[int(bbox[i, 0]) + info_bbox[i, j], int(bbox[i, 1]) + info_bbox[i, j+1]] for j in xrange(0,28,2)])
scores = np.array(scores)
order = scores.argsort()[::-1]
areas = np.zeros(scores.shape)
order = scores.argsort()[::-1]
inter_areas = np.zeros((scores.shape[0], scores.shape[0]))
for il in range(len(pts)):
poly = Polygon(pts[il]).buffer(0.001)
areas[il] = poly.area
for jl in range(il, len(pts)):
polyj = Polygon(pts[jl].tolist()).buffer(0.001)
inS = poly.intersection(polyj)
try:
inter_areas[il][jl] = inS.area
except:
import pdb;pdb.set_trace()
inter_areas[jl][il] = inS.area
keep = []
while order.size > 0:
i = order[0]
keep.append(i)
ovr = inter_areas[i][order[1:]] / ((areas[i]) + areas[order[1:]] - inter_areas[i][order[1:]])
inds = np.where(ovr <= thresh)[0]
order = order[inds + 1]
return keep
@unique
class ColorMode(Enum):
"""
Enum of different color modes to use for instance visualizations.
"""
IMAGE = 0
"""
Picks a random color for every instance and overlay segmentations with low opacity.
"""
SEGMENTATION = 1
"""
Let instances of the same category have similar colors
(from metadata.thing_colors), and overlay them with
high opacity. This provides more attention on the quality of segmentation.
"""
IMAGE_BW = 2
"""
Same as IMAGE, but convert all areas without masks to gray-scale.
Only available for drawing per-instance mask predictions.
"""
class GenericMask:
"""
Attribute:
polygons (list[ndarray]): list[ndarray]: polygons for this mask.
Each ndarray has format [x, y, x, y, ...]
mask (ndarray): a binary mask
"""
def __init__(self, mask_or_polygons, height, width):
self._mask = self._polygons = self._has_holes = None
self.height = height
self.width = width
m = mask_or_polygons
if isinstance(m, dict):
# RLEs
assert "counts" in m and "size" in m
if isinstance(m["counts"], list): # uncompressed RLEs
h, w = m["size"]
assert h == height and w == width
m = mask_util.frPyObjects(m, h, w)
self._mask = mask_util.decode(m)[:, :]
return
if isinstance(m, list): # list[ndarray]
self._polygons = [np.asarray(x).reshape(-1) for x in m]
return
if isinstance(m, np.ndarray): # assumed to be a binary mask
assert m.shape[1] != 2, m.shape
assert m.shape == (height, width), m.shape
self._mask = m.astype("uint8")
return
raise ValueError("GenericMask cannot handle object {} of type '{}'".format(m, type(m)))
@property
def mask(self):
if self._mask is None:
self._mask = self.polygons_to_mask(self._polygons)
return self._mask
@property
def polygons(self):
if self._polygons is None:
self._polygons, self._has_holes = self.mask_to_polygons(self._mask)
return self._polygons
@property
def has_holes(self):
if self._has_holes is None:
if self._mask is not None:
self._polygons, self._has_holes = self.mask_to_polygons(self._mask)
else:
self._has_holes = False # if original format is polygon, does not have holes
return self._has_holes
def mask_to_polygons(self, mask):
# cv2.RETR_CCOMP flag retrieves all the contours and arranges them to a 2-level
# hierarchy. External contours (boundary) of the object are placed in hierarchy-1.
# Internal contours (holes) are placed in hierarchy-2.
# cv2.CHAIN_APPROX_NONE flag gets vertices of polygons from contours.
mask = np.ascontiguousarray(mask) # some versions of cv2 does not support incontiguous arr
#res = cv2.findContours(mask.astype("uint8"), cv2.RETR_CCOMP, cv2.CHAIN_APPROX_NONE)
res = cv2.findContours(mask.astype("uint8"), cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE)
hierarchy = res[-1]
if hierarchy is None: # empty mask
return [], False
has_holes = (hierarchy.reshape(-1, 4)[:, 3] >= 0).sum() > 0
res = res[-2]
res = [x.flatten() for x in res]
# These coordinates from OpenCV are integers in range [0, W-1 or H-1].
# We add 0.5 to turn them into real-value coordinate space. A better solution
# would be to first +0.5 and then dilate the returned polygon by 0.5.
res = [x + 0.5 for x in res if len(x) >= 6]
return res, has_holes
def polygons_to_mask(self, polygons):
rle = mask_util.frPyObjects(polygons, self.height, self.width)
rle = mask_util.merge(rle)
return mask_util.decode(rle)[:, :]
def area(self):
return self.mask.sum()
def bbox(self):
p = mask_util.frPyObjects(self.polygons, self.height, self.width)
p = mask_util.merge(p)
bbox = mask_util.toBbox(p)
bbox[2] += bbox[0]
bbox[3] += bbox[1]
return bbox
class _PanopticPrediction:
def __init__(self, panoptic_seg, segments_info, metadata=None):
if segments_info is None:
assert metadata is not None
# If "segments_info" is None, we assume "panoptic_img" is a
# H*W int32 image storing the panoptic_id in the format of
# category_id * label_divisor + instance_id. We reserve -1 for
# VOID label.
label_divisor = metadata.label_divisor
segments_info = []
for panoptic_label in np.unique(panoptic_seg.numpy()):
if panoptic_label == -1:
# VOID region.
continue
pred_class = panoptic_label // label_divisor
isthing = pred_class in metadata.thing_dataset_id_to_contiguous_id.values()
segments_info.append(
{
"id": int(panoptic_label),
"category_id": int(pred_class),
"isthing": bool(isthing),
}
)
del metadata
self._seg = panoptic_seg
self._sinfo = {s["id"]: s for s in segments_info} # seg id -> seg info
segment_ids, areas = torch.unique(panoptic_seg, sorted=True, return_counts=True)
areas = areas.numpy()
sorted_idxs = np.argsort(-areas)
self._seg_ids, self._seg_areas = segment_ids[sorted_idxs], areas[sorted_idxs]
self._seg_ids = self._seg_ids.tolist()
for sid, area in zip(self._seg_ids, self._seg_areas):
if sid in self._sinfo:
self._sinfo[sid]["area"] = float(area)
def non_empty_mask(self):
"""
Returns:
(H, W) array, a mask for all pixels that have a prediction
"""
empty_ids = []
for id in self._seg_ids:
if id not in self._sinfo:
empty_ids.append(id)
if len(empty_ids) == 0:
return np.zeros(self._seg.shape, dtype=np.uint8)
assert (
len(empty_ids) == 1
), ">1 ids corresponds to no labels. This is currently not supported"
return (self._seg != empty_ids[0]).numpy().astype(np.bool)
def semantic_masks(self):
for sid in self._seg_ids:
sinfo = self._sinfo.get(sid)
if sinfo is None or sinfo["isthing"]:
# Some pixels (e.g. id 0 in PanopticFPN) have no instance or semantic predictions.
continue
yield (self._seg == sid).numpy().astype(np.bool), sinfo
def instance_masks(self):
for sid in self._seg_ids:
sinfo = self._sinfo.get(sid)
if sinfo is None or not sinfo["isthing"]:
continue
mask = (self._seg == sid).numpy().astype(np.bool)
if mask.sum() > 0:
yield mask, sinfo
def _create_text_labels(classes, scores, class_names):
"""
Args:
classes (list[int] or None):
scores (list[float] or None):
class_names (list[str] or None):
Returns:
list[str] or None
"""
labels = None
if classes is not None and class_names is not None and len(class_names) > 0:
labels = [class_names[i] for i in classes]
if scores is not None:
if labels is None:
labels = ["{:.0f}%".format(s * 100) for s in scores]
else:
# labels = ["{} {:.0f}%".format(l, s * 100) for l, s in zip(labels, scores)]
#luyao
labels = ["{}.{:.0f}".format(l, s * 100) for l, s in zip(labels, scores)]
return labels
class VisImage:
def __init__(self, img, scale=1.0):
"""
Args:
img (ndarray): an RGB image of shape (H, W, 3).
scale (float): scale the input image
"""
self.img = img
self.scale = scale
self.width, self.height = img.shape[1], img.shape[0]
self._setup_figure(img)
def _setup_figure(self, img):
"""
Args:
Same as in :meth:`__init__()`.
Returns:
fig (matplotlib.pyplot.figure): top level container for all the image plot elements.
ax (matplotlib.pyplot.Axes): contains figure elements and sets the coordinate system.
"""
fig = mplfigure.Figure(frameon=False)
self.dpi = fig.get_dpi()
# add a small 1e-2 to avoid precision lost due to matplotlib's truncation
# (https://github.com/matplotlib/matplotlib/issues/15363)
fig.set_size_inches(
(self.width * self.scale + 1e-2) / self.dpi,
(self.height * self.scale + 1e-2) / self.dpi,
)
self.canvas = FigureCanvasAgg(fig)
# self.canvas = mpl.backends.backend_cairo.FigureCanvasCairo(fig)
ax = fig.add_axes([0.0, 0.0, 1.0, 1.0])
ax.axis("off")
# Need to imshow this first so that other patches can be drawn on top
ax.imshow(img, extent=(0, self.width, self.height, 0), interpolation="nearest")
self.fig = fig
self.ax = ax
def save(self, filepath):
"""
Args:
filepath (str): a string that contains the absolute path, including the file name, where
the visualized image will be saved.
"""
self.fig.savefig(filepath)
# self.fig.savefig(filepath[:-4]+'.svg', format='svg')
def get_image(self):
"""
Returns:
ndarray:
the visualized image of shape (H, W, 3) (RGB) in uint8 type.
The shape is scaled w.r.t the input image using the given `scale` argument.
"""
canvas = self.canvas
s, (width, height) = canvas.print_to_buffer()
# buf = io.BytesIO() # works for cairo backend
# canvas.print_rgba(buf)
# width, height = self.width, self.height
# s = buf.getvalue()
buffer = np.frombuffer(s, dtype="uint8")
img_rgba = buffer.reshape(height, width, 4)
rgb, alpha = np.split(img_rgba, [3], axis=2)
return rgb.astype("uint8")
class Visualizer:
"""
Visualizer that draws data about detection/segmentation on images.
It contains methods like `draw_{text,box,circle,line,binary_mask,polygon}`
that draw primitive objects to images, as well as high-level wrappers like
`draw_{instance_predictions,sem_seg,panoptic_seg_predictions,dataset_dict}`
that draw composite data in some pre-defined style.
Note that the exact visualization style for the high-level wrappers are subject to change.
Style such as color, opacity, label contents, visibility of labels, or even the visibility
of objects themselves (e.g. when the object is too small) may change according
to different heuristics, as long as the results still look visually reasonable.
To obtain a consistent style, implement custom drawing functions with the primitive
methods instead.
This visualizer focuses on high rendering quality rather than performance. It is not
designed to be used for real-time applications.
"""
# TODO implement a fast, rasterized version using OpenCV
def __init__(self, img_rgb, metadata=None, scale=1.0, instance_mode=ColorMode.IMAGE):
"""
Args:
img_rgb: a numpy array of shape (H, W, C), where H and W correspond to
the height and width of the image respectively. C is the number of
color channels. The image is required to be in RGB format since that
is a requirement of the Matplotlib library. The image is also expected
to be in the range [0, 255].
metadata (Metadata): image metadata.
instance_mode (ColorMode): defines one of the pre-defined style for drawing
instances on an image.
"""
self.img = np.asarray(img_rgb).clip(0, 255).astype(np.uint8)
if metadata is None:
metadata = MetadataCatalog.get("__nonexist__")
self.metadata = metadata
self.output = VisImage(self.img, scale=scale)
self.cpu_device = torch.device("cpu")
# too small texts are useless, therefore clamp to 9
self._default_font_size = max(
np.sqrt(self.output.height * self.output.width) // 90, 10 // scale
)
self._instance_mode = instance_mode
with open('chn_cls_list.txt', 'rb') as fp:
self.CTLABELS = pickle.load(fp)
def draw_instance_predictions(self, predictions, path):
"""
Draw instance-level prediction results on an image.
Args:
predictions (Instances): the output of an instance detection/segmentation
model. Following fields will be used to draw:
"pred_boxes", "pred_classes", "scores", "pred_masks" (or "pred_masks_rle").
Returns:
output (VisImage): image object with visualizations.
"""
boxes = predictions.pred_boxes if predictions.has("pred_boxes") else None
scores = predictions.scores if predictions.has("scores") else None
classes = predictions.pred_classes if predictions.has("pred_classes") else None
labels = _create_text_labels(classes, scores, self.metadata.get("thing_classes", None))
#luyao#
# labels = _create_text_labels(classes, scores, self.metadata.get("thing_classes", None))
keypoints = predictions.pred_keypoints if predictions.has("pred_keypoints") else None
rec = predictions.pred_rec if predictions.has("pred_rec") else None
rec_score = predictions.pred_rec_score if predictions.has("pred_rec_score") else None
#luyao#
if predictions.has("pred_masks"):
masks = np.asarray(predictions.pred_masks)
masks = [GenericMask(x, self.output.height, self.output.width) for x in masks]
else:
masks = None
# masks = None
if self._instance_mode == ColorMode.SEGMENTATION and self.metadata.get("thing_colors"):
colors = [
self._jitter([x / 255 for x in self.metadata.thing_colors[c]]) for c in classes
]
#luyao#
alpha = 0.8
else:
colors = None
alpha = 0.77
if self._instance_mode == ColorMode.IMAGE_BW:
self.output.img = self._create_grayscale_image(
(predictions.pred_masks.any(dim=0) > 0).numpy()
if predictions.has("pred_masks")
else None
)
alpha = 0.3
self.overlay_instances(
rec=rec,
masks=masks,
boxes=boxes,
labels=labels,
keypoints=keypoints,
assigned_colors=colors,
alpha=alpha,
scores=scores,
path=path,
rec_score = rec_score
)
return self.output
def draw_sem_seg(self, sem_seg, area_threshold=None, alpha=0.8):
"""
Draw semantic segmentation predictions/labels.
Args:
sem_seg (Tensor or ndarray): the segmentation of shape (H, W).
Each value is the integer label of the pixel.
area_threshold (int): segments with less than `area_threshold` are not drawn.
alpha (float): the larger it is, the more opaque the segmentations are.
Returns:
output (VisImage): image object with visualizations.
"""
if isinstance(sem_seg, torch.Tensor):
sem_seg = sem_seg.numpy()
labels, areas = np.unique(sem_seg, return_counts=True)
sorted_idxs = np.argsort(-areas).tolist()
labels = labels[sorted_idxs]
for label in filter(lambda l: l < len(self.metadata.stuff_classes), labels):
try:
mask_color = [x / 255 for x in self.metadata.stuff_colors[label]]
except (AttributeError, IndexError):
mask_color = None
binary_mask = (sem_seg == label).astype(np.uint8)
text = self.metadata.stuff_classes[label]
self.draw_binary_mask(
binary_mask,
color=mask_color,
edge_color=_OFF_WHITE,
text=text,
alpha=alpha,
area_threshold=area_threshold,
)
return self.output
def draw_panoptic_seg_predictions(
self, panoptic_seg, segments_info, area_threshold=None, alpha=0.7
):
"""
Draw panoptic prediction results on an image.
Args:
panoptic_seg (Tensor): of shape (height, width) where the values are ids for each
segment.
segments_info (list[dict]): Describe each segment in `panoptic_seg`.
Each dict contains keys "id", "category_id", "isthing".
area_threshold (int): stuff segments with less than `area_threshold` are not drawn.
Returns:
output (VisImage): image object with visualizations.
"""
pred = _PanopticPrediction(panoptic_seg, segments_info, self.metadata)
if self._instance_mode == ColorMode.IMAGE_BW:
self.output.img = self._create_grayscale_image(pred.non_empty_mask())
# draw mask for all semantic segments first i.e. "stuff"
for mask, sinfo in pred.semantic_masks():
category_idx = sinfo["category_id"]
try:
mask_color = [x / 255 for x in self.metadata.stuff_colors[category_idx]]
except AttributeError:
mask_color = None
text = self.metadata.stuff_classes[category_idx]
self.draw_binary_mask(
mask,
color=mask_color,
edge_color=_OFF_WHITE,
text=text,
alpha=alpha,
area_threshold=area_threshold,
)
# draw mask for all instances second
all_instances = list(pred.instance_masks())
if len(all_instances) == 0:
return self.output
masks, sinfo = list(zip(*all_instances))
category_ids = [x["category_id"] for x in sinfo]
try:
scores = [x["score"] for x in sinfo]
except KeyError:
scores = None
labels = _create_text_labels(category_ids, scores, self.metadata.thing_classes)
try:
colors = [
self._jitter([x / 255 for x in self.metadata.thing_colors[c]]) for c in category_ids
]
except AttributeError:
colors = None
self.overlay_instances(masks=masks, labels=labels, assigned_colors=colors, alpha=alpha)
return self.output
def draw_dataset_dict(self, dic):
"""
Draw annotations/segmentaions in Detectron2 Dataset format.
Args:
dic (dict): annotation/segmentation data of one image, in Detectron2 Dataset format.
Returns:
output (VisImage): image object with visualizations.
"""
annos = dic.get("annotations", None)
if annos:
if "segmentation" in annos[0]:
masks = [x["segmentation"] for x in annos]
else:
masks = None
if "keypoints" in annos[0]:
keypts = [x["keypoints"] for x in annos]
keypts = np.array(keypts).reshape(len(annos), -1, 3)
else:
keypts = None
boxes = [
BoxMode.convert(x["bbox"], x["bbox_mode"], BoxMode.XYXY_ABS)
if len(x["bbox"]) == 4
else x["bbox"]
for x in annos
]
labels = [x["category_id"] for x in annos]
colors = None
if self._instance_mode == ColorMode.SEGMENTATION and self.metadata.get("thing_colors"):
colors = [
self._jitter([x / 255 for x in self.metadata.thing_colors[c]]) for c in labels
]
names = self.metadata.get("thing_classes", None)
if names:
labels = [names[i] for i in labels]
labels = [
"{}".format(i) + ("|crowd" if a.get("iscrowd", 0) else "")
for i, a in zip(labels, annos)
]
self.overlay_instances(
labels=labels, boxes=boxes, masks=masks, keypoints=keypts, assigned_colors=colors
)
sem_seg = dic.get("sem_seg", None)
if sem_seg is None and "sem_seg_file_name" in dic:
with PathManager.open(dic["sem_seg_file_name"], "rb") as f:
sem_seg = Image.open(f)
sem_seg = np.asarray(sem_seg, dtype="uint8")
if sem_seg is not None:
self.draw_sem_seg(sem_seg, area_threshold=0, alpha=0.5)
pan_seg = dic.get("pan_seg", None)
if pan_seg is None and "pan_seg_file_name" in dic:
assert "segments_info" in dic
with PathManager.open(dic["pan_seg_file_name"], "rb") as f:
pan_seg = Image.open(f)
pan_seg = np.asarray(pan_seg)
from panopticapi.utils import rgb2id
pan_seg = rgb2id(pan_seg)
segments_info = dic["segments_info"]
if pan_seg is not None:
pan_seg = torch.Tensor(pan_seg)
self.draw_panoptic_seg_predictions(pan_seg, segments_info, area_threshold=0, alpha=0.5)
return self.output
def overlay_instances(
self,
*,
rec=None,
boxes=None,
labels=None,
masks=None,
keypoints=None,
assigned_colors=None,
alpha=0.5,
scores,
path,
rec_score,
):
"""
Args:
boxes (Boxes, RotatedBoxes or ndarray): either a :class:`Boxes`,
or an Nx4 numpy array of XYXY_ABS format for the N objects in a single image,
or a :class:`RotatedBoxes`,
or an Nx5 numpy array of (x_center, y_center, width, height, angle_degrees) format
for the N objects in a single image,
labels (list[str]): the text to be displayed for each instance.
masks (masks-like object): Supported types are:
* :class:`detectron2.structures.PolygonMasks`,
:class:`detectron2.structures.BitMasks`.
* list[list[ndarray]]: contains the segmentation masks for all objects in one image.
The first level of the list corresponds to individual instances. The second
level to all the polygon that compose the instance, and the third level
to the polygon coordinates. The third level should have the format of
[x0, y0, x1, y1, ..., xn, yn] (n >= 3).
* list[ndarray]: each ndarray is a binary mask of shape (H, W).
* list[dict]: each dict is a COCO-style RLE.
keypoints (Keypoint or array like): an array-like object of shape (N, K, 3),
where the N is the number of instances and K is the number of keypoints.
The last dimension corresponds to (x, y, visibility or score).
assigned_colors (list[matplotlib.colors]): a list of colors, where each color
corresponds to each mask or box in the image. Refer to 'matplotlib.colors'
for full list of formats that the colors are accepted in.
Returns:
output (VisImage): image object with visualizations.
"""
rec = rec
def _ctc_decode_recognition(rec):
#CTLABELS = "_0123456789abcdefghijklmnopqrstuvwxyz"
# CTLABELS = [' ','!','"','#','$','%','&','\'','(',')','*','+',',','-','.','/','0','1','2','3','4','5','6','7','8','9',':',';','<','=','>','?','@','A','B','C','D','E','F','G','H','I','J','K','L','M','N','O','P','Q','R','S','T','U','V','W','X','Y','Z','[','\\',']','^','_','`','a','b','c','d','e','f','g','h','i','j','k','l','m','n','o','p','q','r','s','t','u','v','w','x','y','z','{','|','}','~']
# ctc decoding
s = ''
for c in rec:
c = int(c)
if c < 5461:
s += str(chr(self.CTLABELS[c]))
elif c == 5462:
s += u''
return s
num_instances = None
if boxes is not None:
boxes = self._convert_boxes(boxes)
num_instances = len(boxes)
if masks is not None:
masks = self._convert_masks(masks)
if num_instances:
assert len(masks) == num_instances
else:
num_instances = len(masks)
if keypoints is not None:
if num_instances:
assert len(keypoints) == num_instances
else:
num_instances = len(keypoints)
keypoints = self._convert_keypoints(keypoints)
if labels is not None:
assert len(labels) == num_instances
if assigned_colors is None:
assigned_colors = [random_color(rgb=True, maximum=1) for _ in range(num_instances)]
if num_instances == 0:
return self.output
if boxes is not None and boxes.shape[1] == 5:
return self.overlay_rotated_instances(
boxes=boxes, labels=labels, assigned_colors=assigned_colors
)
# Display in largest to smallest order to reduce occlusion.
areas = None
if boxes is not None:
areas = np.prod(boxes[:, 2:] - boxes[:, :2], axis=1)
elif masks is not None:
areas = np.asarray([x.area() for x in masks])
if areas is not None:
sorted_idxs = np.argsort(-areas).tolist()
# Re-order overlapped instances in descending order.
boxes = boxes[sorted_idxs] if boxes is not None else None
labels = [labels[k] for k in sorted_idxs] if labels is not None else None
masks = [masks[idx] for idx in sorted_idxs] if masks is not None else None
rec = [rec[idx] for idx in sorted_idxs] if rec is not None else None
# rec_score = [rec_score[idx] for idx in sorted_idxs] if rec is not None else None
scores = [scores[idx] for idx in sorted_idxs] if scores is not None else None
# assigned_colors = [assigned_colors[idx] for idx in sorted_idxs]
keypoints = keypoints[sorted_idxs] if keypoints is not None else None
#luyao#
assigned_colors = [[0,113.985,118.955],[216.75,82.875,24.99],[236.895, 176.97, 31.875],[125.97, 46.92, 141.78],[118.83, 171.87, 47.94],[76.755, 189.975, 237.915],[161.925, 19.89, 46.92],\
[255,140,0 ],[70,130,180 ],[128,128,0 ],[205,92,92 ],[128,0,128 ],[255,182,193],[255,255,0],[105,105,105],[0,255,255],[0,255,0 ],\
[210,180,140],[255,0,0 ],[0,139,139],[255,0,255],[127,255,0],[75,0,130],[32,178,170],[255,215,0],[219,112,147],[148,0,211 ],\
[100,149,237],[175,238,238 ],[143,188,143],[255,255,224 ],[244,164,96],[188,143,143],[192,192,192 ],[220,20,60],[218,112,214],[147,112,219]]
rec = [_ctc_decode_recognition(rrec) for rrec in rec]
# assigned_colors = [[1,140/255,0],[30/255,144/255,1],[148/255,0,211/255],[0,1,1],[1,0,0],\
# [30/255,143/255,1],[0.94,0.5,0.5],[1,1,0],[0.5,0.5,0],[0.823,0.412,0.117],[0.58,0,0.827],[0.5,0,0]\
# ,[0.82,0.41,0.12],[0.41,0.41,0.41],[0,0.54,0.54],[0.75,0.25,0.65],[0.2,0.6,0.8],[0.74,0,0.3],[0,1.0,0.4],[1,0.5,0.5],[0.5,0.5,1]\
# ,[0.6,0,1],[0.56,0.56,0.3],[0,1,0],[1.0,0.0,0.4],[0.0,1.0,0.4],[0.0,0.5,1.0],[1,215/255,0]]
poly = []
alpha = 0.4
for i in range(num_instances):
if masks is not None:
poly.append(masks[i].polygons[0].astype(int).reshape(-1,2))
keep = py_cpu_pnms(poly,scores,0.5)
for i in range(num_instances):
# if rec[i] == ' ':
# continue
if i not in keep:
continue
# color = assigned_colors[i]
# print(i)
color_ = assigned_colors[i%len(assigned_colors)]
color = [x/255 for x in color_]
# if boxes is not None:
# self.draw_box(boxes[i], edge_color=color)
#luyao
# alpha = 0.6
H, W, _ = self.img.shape
if masks is not None:
for segment in masks[i].polygons:
segment = polygon2rbox(segment, H, W)
segment = np.array(segment)
self.draw_polygon(segment.reshape(-1, 2), color, alpha=alpha)
if labels is not None:
# first get a box
if boxes is not None:
#luyao#
x0, y0, x1, y1 = boxes[i]
text_pos = (x0, y0) # if drawing boxes, put text on the box corner.
horiz_align = "left"
elif masks is not None:
# skip small mask without polygon
if len(masks[i].polygons) == 0:
continue
x0, y0, x1, y1 = masks[i].bbox()
# draw text in the center (defined by median) when box is not drawn
# median is less sensitive to outliers.
text_pos = np.median(masks[i].mask.nonzero(), axis=1)[::-1]
horiz_align = "center"
else:
continue # drawing the box confidence for keypoints isn't very useful.
# for small objects, draw text at the side to avoid occlusion
instance_area = (y1 - y0) * (x1 - x0)
# print(x0,' ',x1,' ',y0,' ',y1,' ',self.output.height,' ', self.output.width)
#luyao#
if y0<5:
text_pos = ((x0+x1)//2,(y0+y1)//2)
#luyao#
# if (
# instance_area < _SMALL_OBJECT_AREA_THRESH * self.output.scale
# or y1 - y0 < 40 * self.output.scale
# ):
# if y1 >= self.output.height - 5:
# text_pos = (x1, y0)
# else:
# text_pos = (x0, y1)
height_ratio = (y1 - y0) / np.sqrt(self.output.height * self.output.width)
lighter_color = self._change_color_brightness(color, brightness_factor=0.7)
font_size = (
np.clip((height_ratio - 0.02) / 0.08 + 1, 1.2, 2)
* 1.0
* self._default_font_size
)
self.draw_text(
# labels[i],
# '',
rec[i],
text_pos,
color=lighter_color,
horizontal_alignment=horiz_align,
font_size=font_size,
)
# draw keypoints
if keypoints is not None:
for keypoints_per_instance in keypoints:
self.draw_and_connect_keypoints(keypoints_per_instance)
return self.output
def overlay_rotated_instances(self, boxes=None, labels=None, assigned_colors=None):
"""
Args:
boxes (ndarray): an Nx5 numpy array of
(x_center, y_center, width, height, angle_degrees) format
for the N objects in a single image.
labels (list[str]): the text to be displayed for each instance.
assigned_colors (list[matplotlib.colors]): a list of colors, where each color
corresponds to each mask or box in the image. Refer to 'matplotlib.colors'
for full list of formats that the colors are accepted in.
Returns:
output (VisImage): image object with visualizations.
"""
num_instances = len(boxes)
if assigned_colors is None:
assigned_colors = [random_color(rgb=True, maximum=1) for _ in range(num_instances)]
if num_instances == 0:
return self.output
# Display in largest to smallest order to reduce occlusion.
if boxes is not None:
areas = boxes[:, 2] * boxes[:, 3]
sorted_idxs = np.argsort(-areas).tolist()
# Re-order overlapped instances in descending order.
boxes = boxes[sorted_idxs]
labels = [labels[k] for k in sorted_idxs] if labels is not None else None
colors = [assigned_colors[idx] for idx in sorted_idxs]
for i in range(num_instances):
self.draw_rotated_box_with_label(
boxes[i], edge_color=colors[i], label=labels[i] if labels is not None else None
)
return self.output
def draw_and_connect_keypoints(self, keypoints):
"""
Draws keypoints of an instance and follows the rules for keypoint connections
to draw lines between appropriate keypoints. This follows color heuristics for
line color.
Args:
keypoints (Tensor): a tensor of shape (K, 3), where K is the number of keypoints
and the last dimension corresponds to (x, y, probability).
Returns:
output (VisImage): image object with visualizations.
"""
visible = {}
keypoint_names = self.metadata.get("keypoint_names")
for idx, keypoint in enumerate(keypoints):
# draw keypoint
x, y, prob = keypoint
if prob > _KEYPOINT_THRESHOLD:
self.draw_circle((x, y), color=_RED)
if keypoint_names:
keypoint_name = keypoint_names[idx]
visible[keypoint_name] = (x, y)
if self.metadata.get("keypoint_connection_rules"):
for kp0, kp1, color in self.metadata.keypoint_connection_rules:
if kp0 in visible and kp1 in visible:
x0, y0 = visible[kp0]
x1, y1 = visible[kp1]
color = tuple(x / 255.0 for x in color)
self.draw_line([x0, x1], [y0, y1], color=color)
# draw lines from nose to mid-shoulder and mid-shoulder to mid-hip
# Note that this strategy is specific to person keypoints.
# For other keypoints, it should just do nothing
try:
ls_x, ls_y = visible["left_shoulder"]
rs_x, rs_y = visible["right_shoulder"]
mid_shoulder_x, mid_shoulder_y = (ls_x + rs_x) / 2, (ls_y + rs_y) / 2
except KeyError:
pass
else:
# draw line from nose to mid-shoulder
nose_x, nose_y = visible.get("nose", (None, None))
if nose_x is not None:
self.draw_line([nose_x, mid_shoulder_x], [nose_y, mid_shoulder_y], color=_RED)
try:
# draw line from mid-shoulder to mid-hip
lh_x, lh_y = visible["left_hip"]
rh_x, rh_y = visible["right_hip"]
except KeyError:
pass
else:
mid_hip_x, mid_hip_y = (lh_x + rh_x) / 2, (lh_y + rh_y) / 2
self.draw_line([mid_hip_x, mid_shoulder_x], [mid_hip_y, mid_shoulder_y], color=_RED)
return self.output
"""
Primitive drawing functions:
"""
def draw_text(
self,
text,
position,
*,
font_size=None,
color="g",
horizontal_alignment="center",
rotation=0
):
"""
Args:
text (str): class label
position (tuple): a tuple of the x and y coordinates to place text on image.
font_size (int, optional): font of the text. If not provided, a font size
proportional to the image width is calculated and used.
color: color of the text. Refer to `matplotlib.colors` for full list
of formats that are accepted.
horizontal_alignment (str): see `matplotlib.text.Text`
rotation: rotation angle in degrees CCW
Returns:
output (VisImage): image object with text drawn.
"""
if not font_size:
font_size = self._default_font_size
# print(font_size, self.output.scale)
# since the text background is dark, we don't want the text to be dark
# color = np.maximum(list(mplc.to_rgb(color)), 0.2)
# color[np.argmax(color)] = max(0.8, np.max(color))
#luyao#
color = 'w'
# font_size = 7.0
x, y = position
font_path = "simsun.ttc"
prop = mfm.FontProperties(fname=font_path)
self.output.ax.text(
x,
y,
text,
size=font_size * self.output.scale,
# family="sans-serif",
family="monospace",
# family="serif",
#luyao#
bbox={"facecolor": "black", "alpha": 0.0, "pad": 0.0, "edgecolor": "none"},
# bbox={"facecolor": "black", "alpha": 0.8, "pad": 0.7, "edgecolor": "none"},
# verticalalignment="top",
verticalalignment="bottom",
horizontalalignment=horizontal_alignment,
color=color,
zorder=10,
rotation=rotation,
fontproperties=prop,
#luyao
# fontweight='light'
)
return self.output
def draw_box(self, box_coord, alpha=0.5, edge_color="g", line_style="-"):
"""
Args:
box_coord (tuple): a tuple containing x0, y0, x1, y1 coordinates, where x0 and y0
are the coordinates of the image's top left corner. x1 and y1 are the
coordinates of the image's bottom right corner.
alpha (float): blending efficient. Smaller values lead to more transparent masks.
edge_color: color of the outline of the box. Refer to `matplotlib.colors`
for full list of formats that are accepted.
line_style (string): the string to use to create the outline of the boxes.
Returns:
output (VisImage): image object with box drawn.
"""
x0, y0, x1, y1 = box_coord
width = x1 - x0
height = y1 - y0
# linewidth = max(self._default_font_size / 16, 1)
# linewidth = max(self._default_font_size / 4, 1)
#luyao#
edge_color=[0.196,0.80,0.196]
alpha = 1.0
linewidth = 0.7
self.output.ax.add_patch(
mpl.patches.Rectangle(
(x0, y0),
width,
height,
fill=False,
edgecolor=edge_color,
linewidth=linewidth * self.output.scale,
alpha=alpha,
linestyle=line_style,
)
)
return self.output
def draw_rotated_box_with_label(
self, rotated_box, alpha=0.5, edge_color="g", line_style="-", label=None
):
"""
Draw a rotated box with label on its top-left corner.
Args:
rotated_box (tuple): a tuple containing (cnt_x, cnt_y, w, h, angle),
where cnt_x and cnt_y are the center coordinates of the box.
w and h are the width and height of the box. angle represents how
many degrees the box is rotated CCW with regard to the 0-degree box.
alpha (float): blending efficient. Smaller values lead to more transparent masks.
edge_color: color of the outline of the box. Refer to `matplotlib.colors`
for full list of formats that are accepted.
line_style (string): the string to use to create the outline of the boxes.
label (string): label for rotated box. It will not be rendered when set to None.
Returns:
output (VisImage): image object with box drawn.
"""
cnt_x, cnt_y, w, h, angle = rotated_box
area = w * h
# use thinner lines when the box is small
linewidth = self._default_font_size / (
6 if area < _SMALL_OBJECT_AREA_THRESH * self.output.scale else 3
)
theta = angle * math.pi / 180.0
c = math.cos(theta)
s = math.sin(theta)
rect = [(-w / 2, h / 2), (-w / 2, -h / 2), (w / 2, -h / 2), (w / 2, h / 2)]
# x: left->right ; y: top->down
rotated_rect = [(s * yy + c * xx + cnt_x, c * yy - s * xx + cnt_y) for (xx, yy) in rect]
for k in range(4):
j = (k + 1) % 4
self.draw_line(
[rotated_rect[k][0], rotated_rect[j][0]],
[rotated_rect[k][1], rotated_rect[j][1]],
color=edge_color,
linestyle="--" if k == 1 else line_style,
linewidth=linewidth,
)
if label is not None:
text_pos = rotated_rect[1] # topleft corner
height_ratio = h / np.sqrt(self.output.height * self.output.width)
label_color = self._change_color_brightness(edge_color, brightness_factor=0.7)
font_size = (
np.clip((height_ratio - 0.02) / 0.08 + 1, 1.2, 2) * 0.5 * self._default_font_size
)
self.draw_text(label, text_pos, color=label_color, font_size=font_size, rotation=angle)
return self.output
def draw_circle(self, circle_coord, color, radius=3):
"""
Args:
circle_coord (list(int) or tuple(int)): contains the x and y coordinates
of the center of the circle.
color: color of the polygon. Refer to `matplotlib.colors` for a full list of
formats that are accepted.
radius (int): radius of the circle.
Returns:
output (VisImage): image object with box drawn.
"""
x, y = circle_coord
self.output.ax.add_patch(
mpl.patches.Circle(circle_coord, radius=radius, fill=True, color=color)
)
return self.output
def draw_line(self, x_data, y_data, color, linestyle="-", linewidth=None):
"""
Args:
x_data (list[int]): a list containing x values of all the points being drawn.
Length of list should match the length of y_data.
y_data (list[int]): a list containing y values of all the points being drawn.
Length of list should match the length of x_data.
color: color of the line. Refer to `matplotlib.colors` for a full list of
formats that are accepted.
linestyle: style of the line. Refer to `matplotlib.lines.Line2D`
for a full list of formats that are accepted.
linewidth (float or None): width of the line. When it's None,
a default value will be computed and used.
Returns:
output (VisImage): image object with line drawn.
"""
if linewidth is None:
linewidth = self._default_font_size / 3
linewidth = max(linewidth, 1)
self.output.ax.add_line(
mpl.lines.Line2D(
x_data,
y_data,
linewidth=linewidth * self.output.scale,
color=color,
linestyle=linestyle,
)
)
return self.output
def draw_binary_mask(
self, binary_mask, color=None, *, edge_color=None, text=None, alpha=0.5, area_threshold=0
):
"""
Args:
binary_mask (ndarray): numpy array of shape (H, W), where H is the image height and
W is the image width. Each value in the array is either a 0 or 1 value of uint8
type.
color: color of the mask. Refer to `matplotlib.colors` for a full list of
formats that are accepted. If None, will pick a random color.
edge_color: color of the polygon edges. Refer to `matplotlib.colors` for a
full list of formats that are accepted.
text (str): if None, will be drawn in the object's center of mass.
alpha (float): blending efficient. Smaller values lead to more transparent masks.
area_threshold (float): a connected component small than this will not be shown.
Returns:
output (VisImage): image object with mask drawn.
"""
if color is None:
color = random_color(rgb=True, maximum=1)
color = mplc.to_rgb(color)
has_valid_segment = False
binary_mask = binary_mask.astype("uint8") # opencv needs uint8
mask = GenericMask(binary_mask, self.output.height, self.output.width)
shape2d = (binary_mask.shape[0], binary_mask.shape[1])
if not mask.has_holes:
# draw polygons for regular masks
for segment in mask.polygons:
area = mask_util.area(mask_util.frPyObjects([segment], shape2d[0], shape2d[1]))
if area < (area_threshold or 0):
continue
has_valid_segment = True
segment = segment.reshape(-1, 2)
self.draw_polygon(segment, color=color, edge_color=edge_color, alpha=alpha)
else:
# TODO: Use Path/PathPatch to draw vector graphics:
# https://stackoverflow.com/questions/8919719/how-to-plot-a-complex-polygon
rgba = np.zeros(shape2d + (4,), dtype="float32")
rgba[:, :, :3] = color
rgba[:, :, 3] = (mask.mask == 1).astype("float32") * alpha
has_valid_segment = True
self.output.ax.imshow(rgba, extent=(0, self.output.width, self.output.height, 0))
if text is not None and has_valid_segment:
# TODO sometimes drawn on wrong objects. the heuristics here can improve.
lighter_color = self._change_color_brightness(color, brightness_factor=0.7)
_num_cc, cc_labels, stats, centroids = cv2.connectedComponentsWithStats(binary_mask, 8)
largest_component_id = np.argmax(stats[1:, -1]) + 1
# draw text on the largest component, as well as other very large components.
for cid in range(1, _num_cc):
if cid == largest_component_id or stats[cid, -1] > _LARGE_MASK_AREA_THRESH:
# median is more stable than centroid
# center = centroids[largest_component_id]
center = np.median((cc_labels == cid).nonzero(), axis=1)[::-1]
self.draw_text(text, center, color=lighter_color)
return self.output
def draw_polygon(self, segment, color, edge_color=None, alpha=0.5):
"""
Args:
segment: numpy array of shape Nx2, containing all the points in the polygon.
color: color of the polygon. Refer to `matplotlib.colors` for a full list of
formats that are accepted.
edge_color: color of the polygon edges. Refer to `matplotlib.colors` for a
full list of formats that are accepted. If not provided, a darker shade
of the polygon color will be used instead.
alpha (float): blending efficient. Smaller values lead to more transparent masks.
Returns:
output (VisImage): image object with polygon drawn.
"""
#luyao#
# edge_color = []
if edge_color is None:
# make edge color darker than the polygon color
if alpha > 0.8:
edge_color = self._change_color_brightness(color, brightness_factor=-0.7)
else:
edge_color = color
edge_color = mplc.to_rgb(edge_color) + (1,)
polygon = mpl.patches.Polygon(
segment,
fill=True,
facecolor=mplc.to_rgb(color) + (alpha,),
#luyao# qudiaomaskyanse
# edgecolor=edge_color,
linewidth=max(self._default_font_size // 15 * self.output.scale, 1),
)
self.output.ax.add_patch(polygon)
return self.output
"""
Internal methods:
"""
def _jitter(self, color):
"""
Randomly modifies given color to produce a slightly different color than the color given.
Args:
color (tuple[double]): a tuple of 3 elements, containing the RGB values of the color
picked. The values in the list are in the [0.0, 1.0] range.
Returns:
jittered_color (tuple[double]): a tuple of 3 elements, containing the RGB values of the
color after being jittered. The values in the list are in the [0.0, 1.0] range.
"""
color = mplc.to_rgb(color)
vec = np.random.rand(3)
# better to do it in another color space
vec = vec / np.linalg.norm(vec) * 0.5
res = np.clip(vec + color, 0, 1)
return tuple(res)
def _create_grayscale_image(self, mask=None):
"""
Create a grayscale version of the original image.
The colors in masked area, if given, will be kept.
"""
img_bw = self.img.astype("f4").mean(axis=2)
img_bw = np.stack([img_bw] * 3, axis=2)
if mask is not None:
img_bw[mask] = self.img[mask]
return img_bw
def _change_color_brightness(self, color, brightness_factor):
"""
Depending on the brightness_factor, gives a lighter or darker color i.e. a color with
less or more saturation than the original color.
Args:
color: color of the polygon. Refer to `matplotlib.colors` for a full list of
formats that are accepted.
brightness_factor (float): a value in [-1.0, 1.0] range. A lightness factor of
0 will correspond to no change, a factor in [-1.0, 0) range will result in
a darker color and a factor in (0, 1.0] range will result in a lighter color.
Returns:
modified_color (tuple[double]): a tuple containing the RGB values of the
modified color. Each value in the tuple is in the [0.0, 1.0] range.
"""
assert brightness_factor >= -1.0 and brightness_factor <= 1.0
color = mplc.to_rgb(color)
polygon_color = colorsys.rgb_to_hls(*mplc.to_rgb(color))
modified_lightness = polygon_color[1] + (brightness_factor * polygon_color[1])
modified_lightness = 0.0 if modified_lightness < 0.0 else modified_lightness
modified_lightness = 1.0 if modified_lightness > 1.0 else modified_lightness
modified_color = colorsys.hls_to_rgb(polygon_color[0], modified_lightness, polygon_color[2])
return modified_color
def _convert_boxes(self, boxes):
"""
Convert different format of boxes to an NxB array, where B = 4 or 5 is the box dimension.
"""
if isinstance(boxes, Boxes) or isinstance(boxes, RotatedBoxes):
return boxes.tensor.numpy()
else:
return np.asarray(boxes)
def _convert_masks(self, masks_or_polygons):
"""
Convert different format of masks or polygons to a tuple of masks and polygons.
Returns:
list[GenericMask]:
"""
m = masks_or_polygons
if isinstance(m, PolygonMasks):
m = m.polygons
if isinstance(m, BitMasks):
m = m.tensor.numpy()
if isinstance(m, torch.Tensor):
m = m.numpy()
ret = []
for x in m:
if isinstance(x, GenericMask):
ret.append(x)
else:
ret.append(GenericMask(x, self.output.height, self.output.width))
return ret
def _convert_keypoints(self, keypoints):
if isinstance(keypoints, Keypoints):
keypoints = keypoints.tensor
keypoints = np.asarray(keypoints)
return keypoints
def get_output(self):
"""
Returns:
output (VisImage): the image output containing the visualizations added
to the image.
"""
return self.output
def polygon2rbox(polygon, image_height, image_width):
poly = np.array(polygon).reshape((-1, 2)).astype(np.float32)
rect = cv2.minAreaRect(poly)
corners = cv2.boxPoints(rect)
corners = np.array(corners, dtype="int")
pts = get_tight_rect(corners, 0, 0, image_height, image_width, 1)
pts = list(map(int, pts))
return pts
def get_tight_rect(points, start_x, start_y, image_height, image_width, scale):
points = list(points)
ps = sorted(points, key=lambda x: x[0])
if ps[1][1] > ps[0][1]:
px1 = ps[0][0] * scale + start_x
py1 = ps[0][1] * scale + start_y
px4 = ps[1][0] * scale + start_x
py4 = ps[1][1] * scale + start_y
else:
px1 = ps[1][0] * scale + start_x
py1 = ps[1][1] * scale + start_y
px4 = ps[0][0] * scale + start_x
py4 = ps[0][1] * scale + start_y
if ps[3][1] > ps[2][1]:
px2 = ps[2][0] * scale + start_x
py2 = ps[2][1] * scale + start_y
px3 = ps[3][0] * scale + start_x
py3 = ps[3][1] * scale + start_y
else:
px2 = ps[3][0] * scale + start_x
py2 = ps[3][1] * scale + start_y
px3 = ps[2][0] * scale + start_x
py3 = ps[2][1] * scale + start_y
px1 = min(max(px1, 1), image_width - 1)
px2 = min(max(px2, 1), image_width - 1)
px3 = min(max(px3, 1), image_width - 1)
px4 = min(max(px4, 1), image_width - 1)
py1 = min(max(py1, 1), image_height - 1)
py2 = min(max(py2, 1), image_height - 1)
py3 = min(max(py3, 1), image_height - 1)
py4 = min(max(py4, 1), image_height - 1)
return [px1, py1, px2, py2, px3, py3, px4, py4]
|