Saved in:
Bibliographic Details
Main Authors: Lin, Henghong, Zhu, Zihan, Wang, Tao, Ioannou, Anastasia, Huang, Yuanshui
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.01639
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913972716830720
author Lin, Henghong
Zhu, Zihan
Wang, Tao
Ioannou, Anastasia
Huang, Yuanshui
author_facet Lin, Henghong
Zhu, Zihan
Wang, Tao
Ioannou, Anastasia
Huang, Yuanshui
contents We address the problem of glass surface segmentation with an RGB-D camera, with a focus on effectively fusing RGB and depth information. To this end, we propose a Weighted Feature Fusion (WFF) module that dynamically and adaptively combines RGB and depth features to tackle issues such as transparency, reflections, and occlusions. This module can be seamlessly integrated with various deep neural network backbones as a plug-and-play solution. Additionally, we introduce the MJU-Glass dataset, a comprehensive RGB-D dataset collected by a service robot navigating real-world environments, providing a valuable benchmark for evaluating segmentation models. Experimental results show significant improvements in segmentation accuracy and robustness, with the WFF module enhancing performance in both mean Intersection over Union (mIoU) and boundary IoU (bIoU), achieving a 7.49% improvement in bIoU when integrated with PSPNet. The proposed module and dataset provide a robust framework for advancing glass surface segmentation in robotics and reducing the risk of collisions with glass objects.
format Preprint
id arxiv_https___arxiv_org_abs_2508_01639
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Glass Surface Segmentation with an RGB-D Camera via Weighted Feature Fusion for Service Robots
Lin, Henghong
Zhu, Zihan
Wang, Tao
Ioannou, Anastasia
Huang, Yuanshui
Computer Vision and Pattern Recognition
We address the problem of glass surface segmentation with an RGB-D camera, with a focus on effectively fusing RGB and depth information. To this end, we propose a Weighted Feature Fusion (WFF) module that dynamically and adaptively combines RGB and depth features to tackle issues such as transparency, reflections, and occlusions. This module can be seamlessly integrated with various deep neural network backbones as a plug-and-play solution. Additionally, we introduce the MJU-Glass dataset, a comprehensive RGB-D dataset collected by a service robot navigating real-world environments, providing a valuable benchmark for evaluating segmentation models. Experimental results show significant improvements in segmentation accuracy and robustness, with the WFF module enhancing performance in both mean Intersection over Union (mIoU) and boundary IoU (bIoU), achieving a 7.49% improvement in bIoU when integrated with PSPNet. The proposed module and dataset provide a robust framework for advancing glass surface segmentation in robotics and reducing the risk of collisions with glass objects.
title Glass Surface Segmentation with an RGB-D Camera via Weighted Feature Fusion for Service Robots
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.01639