Improving Aerial Instance Segmentation in the Dark with Self-Supervised Low Light Enhancement (Student Abstract)

Authors

  • Prateek Garg Department of Electrical and Electronics Engineering, BITS Pilani, Pilani, Rajasthan, India
  • Murari Mandal Department of Computer Science and Engineering, IIIT Kota, Kota, Rajasthan, India
  • Pratik Narang Department of Computer Science and Information Systems, BITS Pilani, Pilani, Rajasthan, India

Keywords:

Instance Segmentation, Visibility Enhancement, Low Light, Deep Learning, Generative Networks

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.

Downloads

Published

2021-05-18

How to Cite

Garg, P., Mandal, M., & Narang, P. (2021). Improving Aerial Instance Segmentation in the Dark with Self-Supervised Low Light Enhancement (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 15781-15782. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17887

Issue

Section

AAAI Student Abstract and Poster Program