Illumination-Based Data Augmentation for Robust Background Subtraction
This work addresses a core challenge in computer vision for applications like surveillance, but it is incremental as it builds on existing data augmentation techniques.
The paper tackles the problem of background subtraction in videos with sudden illumination changes by using data augmentation to simulate flashes and shadows, resulting in improved model generalization and performance under significant illumination variations.
A core challenge in background subtraction (BGS) is handling videos with sudden illumination changes in consecutive frames. In this paper, we tackle the problem from a data point-of-view using data augmentation. Our method performs data augmentation that not only creates endless data on the fly, but also features semantic transformations of illumination which enhance the generalisation of the model. It successfully simulates flashes and shadows by applying the Euclidean distance transform over a binary mask that is randomly generated. Such data allows us to effectively train an illumination-invariant deep learning model for BGS. Experimental results demonstrate the contribution of the synthetics in the ability of the models to perform BGS even when significant illumination changes take place. The source code of the project is made publicly available at https://github.com/dksakkos/illumination_augmentation.