Please use this identifier to cite or link to this item:
http://dspace.bits-pilani.ac.in:8080/jspui/xmlui/handle/123456789/8349
Title: | Improving Aerial Instance Segmentation in the Dark with Self-Supervised Low Light Enhancement |
Authors: | Narang, Pratik |
Keywords: | Computer Science GANs |
Issue Date: | Feb-2021 |
Publisher: | ARXIV |
Abstract: | Low light conditions in aerial images adversely affect the performance of several vision based applications. There is a need for methods that can efficiently remove the low light attributes and assist in the performance of key vision tasks. In this work, we propose a new method that is capable of enhancing the low light image in a self-supervised fashion, and sequentially apply detection and segmentation tasks in an end-to-end manner. The proposed method occupies a very small overhead in terms of memory and computational power over the original algorithm and delivers superior results. Additionally, we propose the generation of a new low light aerial dataset using GANs, which can be used to evaluate vision based networks for similar adverse conditions. |
URI: | https://arxiv.org/abs/2102.05399 http://dspace.bits-pilani.ac.in:8080/xmlui/handle/123456789/8349 |
Appears in Collections: | Department of Computer Science and Information Systems |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.