...

RandomFog

Targets:
image
volume
Image Types:uint8, float32

Simulates fog for the image by adding random fog-like artifacts.

This transform creates a fog effect by generating semi-transparent overlays that mimic the visual characteristics of fog. The fog intensity and distribution can be controlled to create various fog-like conditions. An image size dependent Gaussian blur is applied to the resulting image

Arguments
fog_coef_range
tuple[float, float]
[0.3,1]

Range for fog intensity coefficient. Should be in [0, 1] range.

alpha_coef
float
0.08

Transparency of the fog circles. Should be in [0, 1] range. Default: 0.08.

p
float
0.5

Probability of applying the transform. Default: 0.5.

Examples
>>> import numpy as np
>>> import albumentations as A
>>> image = np.random.randint(0, 256, [100, 100, 3], dtype=np.uint8)

# Default usage
>>> transform = A.RandomFog(p=1.0)
>>> foggy_image = transform(image=image)["image"]

# Custom fog intensity range
>>> transform = A.RandomFog(fog_coef_lower=0.3, fog_coef_upper=0.8, p=1.0)
>>> foggy_image = transform(image=image)["image"]

# Adjust fog transparency
>>> transform = A.RandomFog(fog_coef_lower=0.2, fog_coef_upper=0.5, alpha_coef=0.1, p=1.0)
>>> foggy_image = transform(image=image)["image"]
Notes
  • The fog effect is created by overlaying semi-transparent circles on the image.
  • Higher fog coefficient values result in denser fog effects.
  • The fog is typically denser in the center of the image and gradually decreases towards the edges.
  • Image is blurred to decrease the sharpness
  • This transform is useful for:
    • Simulating various weather conditions in outdoor scenes
    • Data augmentation for improving model robustness to foggy conditions
    • Creating atmospheric effects in image editing
References