Python/computer_vision/mosaic_augmentation.py
pre-commit-ci[bot] 895dffb412
[pre-commit.ci] pre-commit autoupdate ()
* [pre-commit.ci] pre-commit autoupdate

updates:
- [github.com/astral-sh/ruff-pre-commit: v0.0.291 → v0.0.292](https://github.com/astral-sh/ruff-pre-commit/compare/v0.0.291...v0.0.292)
- [github.com/codespell-project/codespell: v2.2.5 → v2.2.6](https://github.com/codespell-project/codespell/compare/v2.2.5...v2.2.6)
- [github.com/tox-dev/pyproject-fmt: 1.1.0 → 1.2.0](https://github.com/tox-dev/pyproject-fmt/compare/1.1.0...1.2.0)

* updating DIRECTORY.md

* Fix typos in test_min_spanning_tree_prim.py

* Fix typos

* codespell --ignore-words-list=manuel

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: github-actions <${GITHUB_ACTOR}@users.noreply.github.com>
Co-authored-by: Tianyi Zheng <tianyizheng02@gmail.com>
Co-authored-by: Christian Clauss <cclauss@me.com>
2023-10-07 21:32:28 +02:00

187 lines
6.9 KiB
Python

"""Source: https://github.com/jason9075/opencv-mosaic-data-aug"""
import glob
import os
import random
from string import ascii_lowercase, digits
import cv2
import numpy as np
# Parameters
OUTPUT_SIZE = (720, 1280) # Height, Width
SCALE_RANGE = (0.4, 0.6) # if height or width lower than this scale, drop it.
FILTER_TINY_SCALE = 1 / 100
LABEL_DIR = ""
IMG_DIR = ""
OUTPUT_DIR = ""
NUMBER_IMAGES = 250
def main() -> None:
"""
Get images list and annotations list from input dir.
Update new images and annotations.
Save images and annotations in output dir.
"""
img_paths, annos = get_dataset(LABEL_DIR, IMG_DIR)
for index in range(NUMBER_IMAGES):
idxs = random.sample(range(len(annos)), 4)
new_image, new_annos, path = update_image_and_anno(
img_paths,
annos,
idxs,
OUTPUT_SIZE,
SCALE_RANGE,
filter_scale=FILTER_TINY_SCALE,
)
# Get random string code: '7b7ad245cdff75241935e4dd860f3bad'
letter_code = random_chars(32)
file_name = path.split(os.sep)[-1].rsplit(".", 1)[0]
file_root = f"{OUTPUT_DIR}/{file_name}_MOSAIC_{letter_code}"
cv2.imwrite(f"{file_root}.jpg", new_image, [cv2.IMWRITE_JPEG_QUALITY, 85])
print(f"Succeeded {index+1}/{NUMBER_IMAGES} with {file_name}")
annos_list = []
for anno in new_annos:
width = anno[3] - anno[1]
height = anno[4] - anno[2]
x_center = anno[1] + width / 2
y_center = anno[2] + height / 2
obj = f"{anno[0]} {x_center} {y_center} {width} {height}"
annos_list.append(obj)
with open(f"{file_root}.txt", "w") as outfile:
outfile.write("\n".join(line for line in annos_list))
def get_dataset(label_dir: str, img_dir: str) -> tuple[list, list]:
"""
- label_dir <type: str>: Path to label include annotation of images
- img_dir <type: str>: Path to folder contain images
Return <type: list>: List of images path and labels
"""
img_paths = []
labels = []
for label_file in glob.glob(os.path.join(label_dir, "*.txt")):
label_name = label_file.split(os.sep)[-1].rsplit(".", 1)[0]
with open(label_file) as in_file:
obj_lists = in_file.readlines()
img_path = os.path.join(img_dir, f"{label_name}.jpg")
boxes = []
for obj_list in obj_lists:
obj = obj_list.rstrip("\n").split(" ")
xmin = float(obj[1]) - float(obj[3]) / 2
ymin = float(obj[2]) - float(obj[4]) / 2
xmax = float(obj[1]) + float(obj[3]) / 2
ymax = float(obj[2]) + float(obj[4]) / 2
boxes.append([int(obj[0]), xmin, ymin, xmax, ymax])
if not boxes:
continue
img_paths.append(img_path)
labels.append(boxes)
return img_paths, labels
def update_image_and_anno(
all_img_list: list,
all_annos: list,
idxs: list[int],
output_size: tuple[int, int],
scale_range: tuple[float, float],
filter_scale: float = 0.0,
) -> tuple[list, list, str]:
"""
- all_img_list <type: list>: list of all images
- all_annos <type: list>: list of all annotations of specific image
- idxs <type: list>: index of image in list
- output_size <type: tuple>: size of output image (Height, Width)
- scale_range <type: tuple>: range of scale image
- filter_scale <type: float>: the condition of downscale image and bounding box
Return:
- output_img <type: narray>: image after resize
- new_anno <type: list>: list of new annotation after scale
- path[0] <type: string>: get the name of image file
"""
output_img = np.zeros([output_size[0], output_size[1], 3], dtype=np.uint8)
scale_x = scale_range[0] + random.random() * (scale_range[1] - scale_range[0])
scale_y = scale_range[0] + random.random() * (scale_range[1] - scale_range[0])
divid_point_x = int(scale_x * output_size[1])
divid_point_y = int(scale_y * output_size[0])
new_anno = []
path_list = []
for i, index in enumerate(idxs):
path = all_img_list[index]
path_list.append(path)
img_annos = all_annos[index]
img = cv2.imread(path)
if i == 0: # top-left
img = cv2.resize(img, (divid_point_x, divid_point_y))
output_img[:divid_point_y, :divid_point_x, :] = img
for bbox in img_annos:
xmin = bbox[1] * scale_x
ymin = bbox[2] * scale_y
xmax = bbox[3] * scale_x
ymax = bbox[4] * scale_y
new_anno.append([bbox[0], xmin, ymin, xmax, ymax])
elif i == 1: # top-right
img = cv2.resize(img, (output_size[1] - divid_point_x, divid_point_y))
output_img[:divid_point_y, divid_point_x : output_size[1], :] = img
for bbox in img_annos:
xmin = scale_x + bbox[1] * (1 - scale_x)
ymin = bbox[2] * scale_y
xmax = scale_x + bbox[3] * (1 - scale_x)
ymax = bbox[4] * scale_y
new_anno.append([bbox[0], xmin, ymin, xmax, ymax])
elif i == 2: # bottom-left
img = cv2.resize(img, (divid_point_x, output_size[0] - divid_point_y))
output_img[divid_point_y : output_size[0], :divid_point_x, :] = img
for bbox in img_annos:
xmin = bbox[1] * scale_x
ymin = scale_y + bbox[2] * (1 - scale_y)
xmax = bbox[3] * scale_x
ymax = scale_y + bbox[4] * (1 - scale_y)
new_anno.append([bbox[0], xmin, ymin, xmax, ymax])
else: # bottom-right
img = cv2.resize(
img, (output_size[1] - divid_point_x, output_size[0] - divid_point_y)
)
output_img[
divid_point_y : output_size[0], divid_point_x : output_size[1], :
] = img
for bbox in img_annos:
xmin = scale_x + bbox[1] * (1 - scale_x)
ymin = scale_y + bbox[2] * (1 - scale_y)
xmax = scale_x + bbox[3] * (1 - scale_x)
ymax = scale_y + bbox[4] * (1 - scale_y)
new_anno.append([bbox[0], xmin, ymin, xmax, ymax])
# Remove bounding box small than scale of filter
if filter_scale > 0:
new_anno = [
anno
for anno in new_anno
if filter_scale < (anno[3] - anno[1]) and filter_scale < (anno[4] - anno[2])
]
return output_img, new_anno, path_list[0]
def random_chars(number_char: int) -> str:
"""
Automatic generate random 32 characters.
Get random string code: '7b7ad245cdff75241935e4dd860f3bad'
>>> len(random_chars(32))
32
"""
assert number_char > 1, "The number of character should greater than 1"
letter_code = ascii_lowercase + digits
return "".join(random.choice(letter_code) for _ in range(number_char))
if __name__ == "__main__":
main()
print("DONE ✅")