det.py 3.1 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990
  1. # copyright (c) 2024 PaddlePaddle Authors. All Rights Reserve.
  2. #
  3. # Licensed under the Apache License, Version 2.0 (the "License");
  4. # you may not use this file except in compliance with the License.
  5. # You may obtain a copy of the License at
  6. #
  7. # http://www.apache.org/licenses/LICENSE-2.0
  8. #
  9. # Unless required by applicable law or agreed to in writing, software
  10. # distributed under the License is distributed on an "AS IS" BASIS,
  11. # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  12. # See the License for the specific language governing permissions and
  13. # limitations under the License.
  14. import os
  15. import cv2
  16. import numpy as np
  17. import PIL
  18. from PIL import Image, ImageDraw, ImageFont
  19. from ...utils.fonts import PINGFANG_FONT_FILE_PATH
  20. from ..utils.color_map import get_colormap, font_colormap
  21. from .base import CVResult
  22. def draw_box(img, boxes):
  23. """
  24. Args:
  25. img (PIL.Image.Image): PIL image
  26. boxes (list): a list of dictionaries representing detection box information.
  27. Returns:
  28. img (PIL.Image.Image): visualized image
  29. """
  30. font_size = int(0.024 * int(img.width)) + 2
  31. font = ImageFont.truetype(PINGFANG_FONT_FILE_PATH, font_size, encoding="utf-8")
  32. draw_thickness = int(max(img.size) * 0.005)
  33. draw = ImageDraw.Draw(img)
  34. clsid2color = {}
  35. catid2fontcolor = {}
  36. color_list = get_colormap(rgb=True)
  37. for i, dt in enumerate(boxes):
  38. clsid, bbox, score = dt["cls_id"], dt["coordinate"], dt["score"]
  39. if clsid not in clsid2color:
  40. color_index = i % len(color_list)
  41. clsid2color[clsid] = color_list[color_index]
  42. catid2fontcolor[clsid] = font_colormap(color_index)
  43. color = tuple(clsid2color[clsid])
  44. font_color = tuple(catid2fontcolor[clsid])
  45. xmin, ymin, xmax, ymax = bbox
  46. # draw bbox
  47. draw.line(
  48. [(xmin, ymin), (xmin, ymax), (xmax, ymax), (xmax, ymin), (xmin, ymin)],
  49. width=draw_thickness,
  50. fill=color,
  51. )
  52. # draw label
  53. text = "{} {:.2f}".format(dt["label"], score)
  54. if tuple(map(int, PIL.__version__.split("."))) <= (10, 0, 0):
  55. tw, th = draw.textsize(text, font=font)
  56. else:
  57. left, top, right, bottom = draw.textbbox((0, 0), text, font)
  58. tw, th = right - left, bottom - top
  59. if ymin < th:
  60. draw.rectangle([(xmin, ymin), (xmin + tw + 4, ymin + th + 1)], fill=color)
  61. draw.text((xmin + 2, ymin - 2), text, fill=font_color, font=font)
  62. else:
  63. draw.rectangle([(xmin, ymin - th), (xmin + tw + 4, ymin + 1)], fill=color)
  64. draw.text((xmin + 2, ymin - th - 2), text, fill=font_color, font=font)
  65. return img
  66. class DetResult(CVResult):
  67. """Save Result Transform"""
  68. _HARD_FLAG = False
  69. def _to_img(self):
  70. """apply"""
  71. boxes = self["boxes"]
  72. image = self._img_reader.read(self["input_path"])
  73. if self._HARD_FLAG:
  74. image_np = np.array(image)
  75. image = Image.fromarray(image_np[:, :, ::-1])
  76. image = draw_box(image, boxes)
  77. return image