Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Holistic indoor scene understanding by context-supported instance segmentation

Holistic indoor scene understanding by context-supported instance segmentation We propose a new method flow that utilizes pixel-level labeling information for instance-level object detection in indoor scenes from RGB-D data. Semantic labeling and instance segmentation are two different paradigms for indoor scene understanding that are usually accomplished separately and independently. We are interested in integrating the two tasks in a synergistic way in order to take advantage of their complementary nature for comprehensive understanding. Our work can capitalize on any deep learning networks used for semantic labeling by treating the intermediate layer as the category-wise local detection output, from which instance segmentation is optimized by jointly considering both the spatial fitness and the relational context encoded by three graphical models, namely, the vertical placement model (VPM), horizontal placement model (HPM) and non-placement model (NPM). VPM, HPM and NPM represent three common but distinct indoor object placement configurations: vertical, horizontal and hanging relationships, respectively. Experimental results on two standard RGB-D datasets show that our method can significantly improve small object segmentation with promising overall performance that is competitive with the state-of-the-art methods. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Multimedia Tools and Applications Springer Journals

Holistic indoor scene understanding by context-supported instance segmentation

Multimedia Tools and Applications , Volume 81 (25): 23 – Oct 1, 2022

Loading next page...
 
/lp/springer-journals/holistic-indoor-scene-understanding-by-context-supported-instance-pKKPreTeuT

References (69)

Publisher
Springer Journals
Copyright
Copyright © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2021
ISSN
1380-7501
eISSN
1573-7721
DOI
10.1007/s11042-021-11145-y
Publisher site
See Article on Publisher Site

Abstract

We propose a new method flow that utilizes pixel-level labeling information for instance-level object detection in indoor scenes from RGB-D data. Semantic labeling and instance segmentation are two different paradigms for indoor scene understanding that are usually accomplished separately and independently. We are interested in integrating the two tasks in a synergistic way in order to take advantage of their complementary nature for comprehensive understanding. Our work can capitalize on any deep learning networks used for semantic labeling by treating the intermediate layer as the category-wise local detection output, from which instance segmentation is optimized by jointly considering both the spatial fitness and the relational context encoded by three graphical models, namely, the vertical placement model (VPM), horizontal placement model (HPM) and non-placement model (NPM). VPM, HPM and NPM represent three common but distinct indoor object placement configurations: vertical, horizontal and hanging relationships, respectively. Experimental results on two standard RGB-D datasets show that our method can significantly improve small object segmentation with promising overall performance that is competitive with the state-of-the-art methods.

Journal

Multimedia Tools and ApplicationsSpringer Journals

Published: Oct 1, 2022

Keywords: Semantic labeling; Object detection; Instance segmentation; RGB-D; Deep learning

There are no references for this article.