Illumination-Based Data Augmentation for Robust Background Subtraction

Sakkos, Dimitrios, Shum, Hubert and Ho, Edmond (2019) Illumination-Based Data Augmentation for Robust Background Subtraction. In: SKIMA 2019 - 13th International Conference on Software, Knowledge, Information Management and Applications, 26th - 28th August 2019, Ulkulhas, Maldives. (In Press)

Sakkos et al - Illumination-Based Data Augmentation for Robust Background Subtraction AAM.pdf - Accepted Version

Download (15MB) | Preview


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 generated randomly. 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.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Background subtraction, convolutional neural networks, synthetics, data augmentation, illumination-invariant
Subjects: G400 Computer Science
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Related URLs:
Depositing User: Paul Burns
Date Deposited: 01 Oct 2019 11:53
Last Modified: 11 Oct 2019 13:32

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics

Policies: NRL Policies | NRL University Deposit Policy | NRL Deposit Licence