Pixel Invisibility: Detect Object Unseen in Color Domain

Yongxin Wang, Duminda Wijesekera

2021

Abstract

Deep neural networks have been very successful in image recognition. In order for those results to be useful for driving automatons require quantifiable safety guarantees during night, dusk, dawn, glare, fog, rain and snow. In order to address this problem, we developed an algorithm that predicts a pixel-level invisibility map for color images that does not require manual labeling - that computes the probability that a pixel/region contains objects that are invisible in color domain, during light challenged conditions such as day, night and fog. We do so by using a novel use of cross modality knowledge distillation from color to thermal domain using weakly-aligned image pairs obtained during daylight and construct indicators for the pixel-level invisibility by mapping both the color and thermal images into a shared space. Quantitative experiments show good performance of our pixel-level invisibility masks and also the effectiveness of distilled mid-level features on object detection in thermal imagery.

Paper Citation

in Harvard Style

Wang Y. and Wijesekera D. (2021). Pixel Invisibility: Detect Object Unseen in Color Domain. In Proceedings of the 7th International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS, ISBN 978-989-758-513-5, pages 201-210. DOI: 10.5220/0010479002010210

in Bibtex Style

@conference{vehits21,
author={Yongxin Wang and Duminda Wijesekera},
title={Pixel Invisibility: Detect Object Unseen in Color Domain},
booktitle={Proceedings of the 7th International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS,},
year={2021},
pages={201-210},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010479002010210},
isbn={978-989-758-513-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 7th International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS,
TI - Pixel Invisibility: Detect Object Unseen in Color Domain
SN - 978-989-758-513-5
AU - Wang Y.
AU - Wijesekera D.
PY - 2021
SP - 201
EP - 210
DO - 10.5220/0010479002010210