Cargando…
RGB-D salient object detection via convolutional capsule network based on feature extraction and integration
Fully convolutional neural network has shown advantages in the salient object detection by using the RGB or RGB-D images. However, there is an object-part dilemma since most fully convolutional neural network inevitably leads to an incomplete segmentation of the salient object. Although the capsule...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10582015/ https://www.ncbi.nlm.nih.gov/pubmed/37848501 http://dx.doi.org/10.1038/s41598-023-44698-z |
_version_ | 1785122235272396800 |
---|---|
author | Xu, Kun Guo, Jichang |
author_facet | Xu, Kun Guo, Jichang |
author_sort | Xu, Kun |
collection | PubMed |
description | Fully convolutional neural network has shown advantages in the salient object detection by using the RGB or RGB-D images. However, there is an object-part dilemma since most fully convolutional neural network inevitably leads to an incomplete segmentation of the salient object. Although the capsule network is capable of recognizing a complete object, it is highly computational demand and time consuming. In this paper, we propose a novel convolutional capsule network based on feature extraction and integration for dealing with the object-part relationship, with less computation demand. First and foremost, RGB features are extracted and integrated by using the VGG backbone and feature extraction module. Then, these features, integrating with depth images by using feature depth module, are upsampled progressively to produce a feature map. In the next step, the feature map is fed into the feature-integrated convolutional capsule network to explore the object-part relationship. The proposed capsule network extracts object-part information by using convolutional capsules with locally-connected routing and predicts the final salient map based on the deconvolutional capsules. Experimental results on four RGB-D benchmark datasets show that our proposed method outperforms 23 state-of-the-art algorithms. |
format | Online Article Text |
id | pubmed-10582015 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Nature Publishing Group UK |
record_format | MEDLINE/PubMed |
spelling | pubmed-105820152023-10-19 RGB-D salient object detection via convolutional capsule network based on feature extraction and integration Xu, Kun Guo, Jichang Sci Rep Article Fully convolutional neural network has shown advantages in the salient object detection by using the RGB or RGB-D images. However, there is an object-part dilemma since most fully convolutional neural network inevitably leads to an incomplete segmentation of the salient object. Although the capsule network is capable of recognizing a complete object, it is highly computational demand and time consuming. In this paper, we propose a novel convolutional capsule network based on feature extraction and integration for dealing with the object-part relationship, with less computation demand. First and foremost, RGB features are extracted and integrated by using the VGG backbone and feature extraction module. Then, these features, integrating with depth images by using feature depth module, are upsampled progressively to produce a feature map. In the next step, the feature map is fed into the feature-integrated convolutional capsule network to explore the object-part relationship. The proposed capsule network extracts object-part information by using convolutional capsules with locally-connected routing and predicts the final salient map based on the deconvolutional capsules. Experimental results on four RGB-D benchmark datasets show that our proposed method outperforms 23 state-of-the-art algorithms. Nature Publishing Group UK 2023-10-17 /pmc/articles/PMC10582015/ /pubmed/37848501 http://dx.doi.org/10.1038/s41598-023-44698-z Text en © The Author(s) 2023 https://creativecommons.org/licenses/by/4.0/Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) . |
spellingShingle | Article Xu, Kun Guo, Jichang RGB-D salient object detection via convolutional capsule network based on feature extraction and integration |
title | RGB-D salient object detection via convolutional capsule network based on feature extraction and integration |
title_full | RGB-D salient object detection via convolutional capsule network based on feature extraction and integration |
title_fullStr | RGB-D salient object detection via convolutional capsule network based on feature extraction and integration |
title_full_unstemmed | RGB-D salient object detection via convolutional capsule network based on feature extraction and integration |
title_short | RGB-D salient object detection via convolutional capsule network based on feature extraction and integration |
title_sort | rgb-d salient object detection via convolutional capsule network based on feature extraction and integration |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10582015/ https://www.ncbi.nlm.nih.gov/pubmed/37848501 http://dx.doi.org/10.1038/s41598-023-44698-z |
work_keys_str_mv | AT xukun rgbdsalientobjectdetectionviaconvolutionalcapsulenetworkbasedonfeatureextractionandintegration AT guojichang rgbdsalientobjectdetectionviaconvolutionalcapsulenetworkbasedonfeatureextractionandintegration |