Adapting Semantic Segmentation Models for Changes in Illumination and Camera Perspective
Abstract
Semantic segmentation using deep neural networks has been widely explored to generate high-level contextual information for autonomous vehicles. To acquire a complete semantic understanding of the forward surroundings, we propose to stitch semantic images from multiple cameras with varying orientations. However, previously trained semantic segmentation models showed unacceptable performance after significant changes to the camera orientations and the lighting conditions. To avoid time-consuming hand labeling, we explore and evaluate the use of data augmentation techniques, specifically skew and gamma correction, from a practical real-world standpoint to extend the existing model and provide more robust performance. The presented experimental results have shown significant improvements with varying illumination and camera perspective changes.
Cite
@article{arxiv.1809.04730,
title = {Adapting Semantic Segmentation Models for Changes in Illumination and Camera Perspective},
author = {Wei Zhou and Alex Zyner and Stewart Worrall and Eduardo Nebot},
journal= {arXiv preprint arXiv:1809.04730},
year = {2019}
}
Comments
Submitted to IEEE Robotics and Automation Letters (RA-L) and 2019 IEEE International Conference on Robotics and Automation (ICRA)