Search results

A core challenge in background subtraction (BGS) is handling videos with sudden illumination changes in consecutive frames. In our pilot study published in, Sakkos:SKIMA 2019, 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.

In our pilot study published in SKIMA 2019, the proposed framework successfully simulates flashes and shadows by applying the Euclidean distance transform over a binary mask generated randomly. In this paper, we further enhance the data augmentation framework by proposing new variations in image appearance both locally and globally.

Experimental results demonstrate the contribution of the synthetics in the ability of the models to perform BGS even when significant illumination changes take place.

Such data augmentation allows us to effectively train an illumination-invariant deep learning model for BGS. We further propose a post-processing method that removes noise from the output binary map of segmentation, resulting in a cleaner, more accurate segmentation map that can generalise to multiple scenes of different conditions. We show that it is possible to train deep learning models even with very limited training samples. The source code of the project is made publicly available at https://github.com/dksakkos/illumination_augmentation

1950, the centenary year of public libraries, now with us, must be a year of intense interest to all who read THE LIBRARY WORLD. Preparations have been made by the Library Association on very generous lines for its celebration. We have our Royal Charter, and now we have the privilege of the Consort of the Heir to the Throne as our President. What is more, H.M. the King has become our Patron. Who shall think meanly of librarians and their work hereafter? No longer, too, shall librarians think meanly of themselves. The writer of this month's Letters on Our Affairs, with some of which we may not entirely agree, is surely right in his assertion that the profession “is arriving.”