End-to-end Semantic Segmentation Network for Low-Light Scenes

Document Type

Conference Proceeding

Publication Date

1-1-2024

Abstract

In the fields of robotic perception and computer vision, achieving accurate semantic segmentation of low-light or nighttime scenes is challenging. This is primarily due to the limited visibility of objects and the reduced texture and color contrasts among them. To address the issue of limited visibility, we propose a hierarchical gated convolution unit, which simultaneously expands the receptive field and restores edge texture. To address the issue of reduced texture among objects, we propose a dual closed-loop bipartite matching algorithm to establish a total loss function consisting of the unsupervised illumination enhancement loss and supervised intersection-over-union loss, thus enabling the joint minimization of both losses via the Hungarian algorithm. We thus achieve end-to-end training for a semantic segmentation network especially suitable for handling low-light scenes. Experimental results demonstrate that the proposed network surpasses existing methods on the Cityscapes dataset and notably outperforms state-of-the-art methods on both Dark Zurich and Nighttime Driving datasets.

Identifier

85202443488 (Scopus)

ISBN

[9798350384574]

Publication Title

Proceedings - IEEE International Conference on Robotics and Automation

External Full Text Location

https://doi.org/10.1109/ICRA57147.2024.10611148

ISSN

10504729

First Page

7725

Last Page

7731

Grant

L223019

Fund Ref

Natural Science Foundation of Beijing Municipality

This document is currently not available here.

Share

COinS