Video Augmentation Techniques for Deep Learning

This python library helps you with augmenting videos for your deep learning architectures. It converts input videos into a new, much larger set of slightly altered videos.

Original Video

Requirements and installation

Required packages:

For installation, simply use sudo pip install git+https://github.com/okankop/vidaug. Alternatively, the repository can be download via git clone https://github.com/okankop/vidaug and installed by using python setup.py sdist && pip install dist/vidaug-0.1.tar.gz.

Examples

A classical video classification with CNN using augmentations on videos. Train on batches of images and augment each batch via random crop, random crop and horizontal flip:

from vidaug import augmentors as va

sometimes = lambda aug: va.Sometimes(0.5, aug) # Used to apply augmentor with 50% probability
seq = va.Sequential([
    va.RandomCrop(size=(240, 180)), # randomly crop video with a size of (240 x 180)
    va.RandomRotate(degrees=10), # randomly rotates the video with a degree randomly choosen from [-10, 10]  
    sometimes(va.HorizontalFlip()) # horizontally flip the video with 50% probability
])

for batch_idx in range(1000):
    # 'video' should be either a list of images from type of numpy array or PIL images
    video = load_batch(batch_idx)
    video_aug = seq(video)
    train_on_video(video)

The videos below show examples for most augmentation techniques:

Augmentation Type Augmented Video
Piecewise Affine Transform Piecewise Affine Transform
Superpixel Superpixel
Gausian Blur Gausian Blur
Invert Color Invert Color
Rondom Rotate Rondom Rotate
Random Resize Random Resize
Translate Translate
Center Crop Center Crop
Horizontal Flip Horizontal Flip
Vertical Flip Vertical Flip
Add Add
Multiply Multiply
Downsample Downsample
Upsample Upsample
Elastic Transformation Elastic Transformation
Salt Salt
Pepper Cropping
Shear Shear