E-Mail Alert

Add your e-mail address to receive forthcoming issues of this journal:

Journal Browser

Journal Browser

Special Issue "Robust Multispectral/Hyperspectral Image Analysis and Classification"

A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Remote Sensing Image Processing".

Deadline for manuscript submissions: 1 December 2019

Special Issue Editors

Guest Editor
Dr. Chen Chen

Department of Electrical and Computer Engineering, The University of North Carolina at Charlotte, Charlotte, NC 28223
Website | E-Mail
Interests: compressed sensing; signal and image processing; pattern recognition; computer vision; hyperspectral image analysis
Guest Editor
Dr. Junjun Jiang

National Institute of Informatics, Tokyo, Japan
Website | E-Mail
Interests: multi- and hyperspectral remote sensing image processing and analysis; super-resolution, fusion, denoising, unmixing, classification, feature extraction
Guest Editor
Dr. Jiayi Ma

Electronic Information School, Wuhan University, Wuhan 430072, China
Website | E-Mail
Interests: deep learning; computer vision; pattern recognition; remote sensing
Guest Editor
Dr. Sidike Paheding

Remote Sensing Lab, Dept. of Earth & Atmospheric Sciences, Saint Louis University St. Louis, MO, 63108, USA
Website | E-Mail
Interests: computer vision; machine learning; remote sensing; biomedical imaging

Special Issue Information

Dear Colleagues,

We observe that satellite imagery, such as a multispectral/hyperspectral image, is a powerful source of information, as it contains different spatial, spectral and temporal resolutions, compared to traditional images. In the past decade, the remote sensing community has introduced intensive works to establish accurate remote sensing image classifiers. However, there are inherent challenges for remote sensing imagery analysis and classification. For example, the quantity of labeled data for remote sensing imagery (e.g., multispectral and hyperspectral image) is limited since it is time-consuming and expensive to obtain a large number of samples with class labels. Also, actual hyperspectral image data inevitably contain considerable noise (Gaussian noise, dead-lines, and other mixed noise) due to the physical limitations of the imaging sensors. In addition, label noise (i.e. mis-labeling of pixels) poses challenges for supervised classification algorithms. Therefore, developing robust image classification and analysis methods that can handle these issues becomes a pressing need for practical applications.

The aim of this Special Issue is to gather cutting-edge works that address the aforementioned challenges in multispectral/hyperspectral image analysis and classification. The main topics include, but not limited to:

  • Robust multispectral/hyperspectral image classification algorithms and feature representations under the conditions of
    • Noisy data
    • Noisy label
    • Small sample size
    • Data imbalance
  • Multispectral/hyperspectral image denoising
  • Missing data reconstruction
  • Multispectral/hyperspectral data unmixing
  • Illumination Enhancement
  • Noise robust multispectral/hyperspectral image analysis
    • Compression
    • Compressive sensing
    • Object/target/anomaly detection
    • Super-resolution
    • Feature/corresponding matching
    • Fusion
Dr. Chen Chen
Dr. Junjun Jiang
Dr. Jiayi Ma
Dr. Sidike Paheding
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Multispectral/hyperspectral remote sensing
  • Remote sensing image analysis
  • Noise robust classification
  • Data imbalance
  • Computer vision
  • Machine learning

Published Papers (12 papers)

View options order results:
result details:
Displaying articles 1-12
Export citation of selected articles as:

Research

Open AccessArticle
Feedback Unilateral Grid-Based Clustering Feature Matching for Remote Sensing Image Registration
Remote Sens. 2019, 11(12), 1418; https://doi.org/10.3390/rs11121418
Received: 27 April 2019 / Revised: 10 June 2019 / Accepted: 10 June 2019 / Published: 14 June 2019
PDF Full-text (20923 KB) | HTML Full-text | XML Full-text
Abstract
In feature-based image matching, implementing a fast and ultra-robust feature matching technique is a challenging task. To solve the problems that the traditional feature matching algorithm suffers from, such as long running time and low registration accuracy, an algorithm called feedback unilateral grid-based [...] Read more.
In feature-based image matching, implementing a fast and ultra-robust feature matching technique is a challenging task. To solve the problems that the traditional feature matching algorithm suffers from, such as long running time and low registration accuracy, an algorithm called feedback unilateral grid-based clustering (FUGC) is presented which is able to improve computation efficiency, accuracy and robustness of feature-based image matching while applying it to remote sensing image registration. First, the image is divided by using unilateral grids and then fast coarse screening of the initial matching feature points through local grid clustering is performed to eliminate a great deal of mismatches in milliseconds. To ensure that true matches are not erroneously screened, a local linear transformation is designed to take feedback verification further, thereby performing fine screening between true matching points deleted erroneously and undeleted false positives in and around this area. This strategy can not only extract high-accuracy matching from coarse baseline matching with low accuracy, but also preserves the true matching points to the greatest extent. The experimental results demonstrate the strong robustness of the FUGC algorithm on various real-world remote sensing images. The FUGC algorithm outperforms current state-of-the-art methods and meets the real-time requirement. Full article
(This article belongs to the Special Issue Robust Multispectral/Hyperspectral Image Analysis and Classification)
Figures

Figure 1

Open AccessArticle
Region Merging Method for Remote Sensing Spectral Image Aided by Inter-Segment and Boundary Homogeneities
Remote Sens. 2019, 11(12), 1414; https://doi.org/10.3390/rs11121414
Received: 11 May 2019 / Revised: 6 June 2019 / Accepted: 6 June 2019 / Published: 14 June 2019
PDF Full-text (10011 KB) | HTML Full-text | XML Full-text
Abstract
Image segmentation is extensively used in remote sensing spectral image processing. Most of the existing region merging methods assess the heterogeneity or homogeneity using global or pre-defined parameters, which lack the flexibility to further improve the goodness-of-fit. Recently, the local spectral angle (SA) [...] Read more.
Image segmentation is extensively used in remote sensing spectral image processing. Most of the existing region merging methods assess the heterogeneity or homogeneity using global or pre-defined parameters, which lack the flexibility to further improve the goodness-of-fit. Recently, the local spectral angle (SA) threshold was used to produce promising segmentation results. However, this method falls short of considering the inherent relationship between adjacent segments. In order to overcome this limitation, an adaptive SA thresholds methods, which combines the inter-segment and boundary homogeneities of adjacent segment pairs by their respective weights to refine predetermined SA threshold, is employed in a hybrid segmentation framework to enhance the image segmentation accuracy. The proposed method can effectively improve the segmentation accuracy with different kinds of reference objects compared to the conventional segmentation approaches based on the global SA and local SA thresholds. The results of the visual comparison also reveal that our method can match more accurately with reference polygons of varied sizes and types. Full article
(This article belongs to the Special Issue Robust Multispectral/Hyperspectral Image Analysis and Classification)
Figures

Figure 1

Open AccessArticle
Spatial Filtering in DCT Domain-Based Frameworks for Hyperspectral Imagery Classification
Remote Sens. 2019, 11(12), 1405; https://doi.org/10.3390/rs11121405
Received: 7 May 2019 / Revised: 10 June 2019 / Accepted: 11 June 2019 / Published: 13 June 2019
PDF Full-text (5721 KB) | HTML Full-text | XML Full-text
Abstract
In this article, we propose two effective frameworks for hyperspectral imagery classification based on spatial filtering in Discrete Cosine Transform (DCT) domain. In the proposed approaches, spectral DCT is performed on the hyperspectral image to obtain a spectral profile representation, where the most [...] Read more.
In this article, we propose two effective frameworks for hyperspectral imagery classification based on spatial filtering in Discrete Cosine Transform (DCT) domain. In the proposed approaches, spectral DCT is performed on the hyperspectral image to obtain a spectral profile representation, where the most significant information in the transform domain is concentrated in a few low-frequency components. The high-frequency components that generally represent noisy data are further processed using a spatial filter to extract the remaining useful information. For the spatial filtering step, both two-dimensional DCT (2D-DCT) and two-dimensional adaptive Wiener filter (2D-AWF) are explored. After performing the spatial filter, an inverse spectral DCT is applied on all transformed bands including the filtered bands to obtain the final preprocessed hyperspectral data, which is subsequently fed into a linear Support Vector Machine (SVM) classifier. Experimental results using three hyperspectral datasets show that the proposed framework Cascade Spectral DCT Spatial Wiener Filter (CDCT-WF_SVM) outperforms several state-of-the-art methods in terms of classification accuracy, the sensitivity regarding different sizes of the training samples, and computational time. Full article
(This article belongs to the Special Issue Robust Multispectral/Hyperspectral Image Analysis and Classification)
Figures

Figure 1

Open AccessArticle
Double-Branch Multi-Attention Mechanism Network for Hyperspectral Image Classification
Remote Sens. 2019, 11(11), 1307; https://doi.org/10.3390/rs11111307
Received: 8 May 2019 / Revised: 25 May 2019 / Accepted: 27 May 2019 / Published: 1 June 2019
PDF Full-text (2508 KB) | HTML Full-text | XML Full-text
Abstract
Recently, Hyperspectral Image (HSI) classification has gradually been getting attention from more and more researchers. HSI has abundant spectral and spatial information; thus, how to fuse these two types of information is still a problem worth studying. In this paper, to extract spectral [...] Read more.
Recently, Hyperspectral Image (HSI) classification has gradually been getting attention from more and more researchers. HSI has abundant spectral and spatial information; thus, how to fuse these two types of information is still a problem worth studying. In this paper, to extract spectral and spatial feature, we propose a Double-Branch Multi-Attention mechanism network (DBMA) for HSI classification. This network has two branches to extract spectral and spatial feature respectively which can reduce the interference between the two types of feature. Furthermore, with respect to the different characteristics of these two branches, two types of attention mechanism are applied in the two branches respectively, which ensures to extract more discriminative spectral and spatial feature. The extracted features are then fused for classification. A lot of experiment results on three hyperspectral datasets shows that the proposed method performs better than the state-of-the-art method. Full article
(This article belongs to the Special Issue Robust Multispectral/Hyperspectral Image Analysis and Classification)
Figures

Figure 1

Open AccessArticle
Label Noise Cleansing with Sparse Graph for Hyperspectral Image Classification
Remote Sens. 2019, 11(9), 1116; https://doi.org/10.3390/rs11091116
Received: 20 April 2019 / Revised: 4 May 2019 / Accepted: 6 May 2019 / Published: 10 May 2019
PDF Full-text (4033 KB) | HTML Full-text | XML Full-text
Abstract
In a real hyperspectral image classification task, label noise inevitably exists in training samples. To deal with label noise, current methods assume that noise obeys the Gaussian distribution, which is not the real case in practice, because in most cases, we are more [...] Read more.
In a real hyperspectral image classification task, label noise inevitably exists in training samples. To deal with label noise, current methods assume that noise obeys the Gaussian distribution, which is not the real case in practice, because in most cases, we are more likely to misclassify training samples at the boundaries between different classes. In this paper, we propose a spectral–spatial sparse graph-based adaptive label propagation (SALP) algorithm to address a more practical case, where the label information is contaminated by random noise and boundary noise. Specifically, the SALP mainly includes two steps: First, a spectral–spatial sparse graph is constructed to depict the contextual correlations between pixels within the same superpixel homogeneous region, which are generated by superpixel image segmentation, and then a transfer matrix is produced to describe the transition probability between pixels. Second, after randomly splitting training pixels into “clean” and “polluted,” we iteratively propagate the label information from “clean” to “polluted” based on the transfer matrix, and the relabeling strategy for each pixel is adaptively adjusted along with its spatial position in the corresponding homogeneous region. Experimental results on two standard hyperspectral image datasets show that the proposed SALP over four major classifiers can significantly decrease the influence of noisy labels, and our method achieves better performance compared with the baselines. Full article
(This article belongs to the Special Issue Robust Multispectral/Hyperspectral Image Analysis and Classification)
Figures

Graphical abstract

Open AccessArticle
Spectral-Spatial Attention Networks for Hyperspectral Image Classification
Remote Sens. 2019, 11(8), 963; https://doi.org/10.3390/rs11080963
Received: 12 March 2019 / Revised: 15 April 2019 / Accepted: 20 April 2019 / Published: 23 April 2019
PDF Full-text (2162 KB) | HTML Full-text | XML Full-text
Abstract
Many deep learning models, such as convolutional neural network (CNN) and recurrent neural network (RNN), have been successfully applied to extracting deep features for hyperspectral tasks. Hyperspectral image classification allows distinguishing the characterization of land covers by utilizing their abundant information. Motivated by [...] Read more.
Many deep learning models, such as convolutional neural network (CNN) and recurrent neural network (RNN), have been successfully applied to extracting deep features for hyperspectral tasks. Hyperspectral image classification allows distinguishing the characterization of land covers by utilizing their abundant information. Motivated by the attention mechanism of the human visual system, in this study, we propose a spectral-spatial attention network for hyperspectral image classification. In our method, RNN with attention can learn inner spectral correlations within a continuous spectrum, while CNN with attention is designed to focus on saliency features and spatial relevance between neighboring pixels in the spatial dimension. Experimental results demonstrate that our method can fully utilize the spectral and spatial information to obtain competitive performance. Full article
(This article belongs to the Special Issue Robust Multispectral/Hyperspectral Image Analysis and Classification)
Figures

Graphical abstract

Open AccessArticle
Hyperspectral Unmixing with Gaussian Mixture Model and Low-Rank Representation
Remote Sens. 2019, 11(8), 911; https://doi.org/10.3390/rs11080911
Received: 12 March 2019 / Revised: 3 April 2019 / Accepted: 11 April 2019 / Published: 15 April 2019
PDF Full-text (11328 KB) | HTML Full-text | XML Full-text
Abstract
Gaussian mixture model (GMM) has been one of the most representative models for hyperspectral unmixing while considering endmember variability. However, the GMM unmixing models only have proper smoothness and sparsity prior constraints on the abundances and thus do not take into account the [...] Read more.
Gaussian mixture model (GMM) has been one of the most representative models for hyperspectral unmixing while considering endmember variability. However, the GMM unmixing models only have proper smoothness and sparsity prior constraints on the abundances and thus do not take into account the possible local spatial correlation. When the pixels that lie on the boundaries of different materials or the inhomogeneous region, the abundances of the neighboring pixels do not have those prior constraints. Thus, we propose a novel GMM unmixing method based on superpixel segmentation (SS) and low-rank representation (LRR), which is called GMM-SS-LRR. we adopt the SS in the first principal component of HSI to get the homogeneous regions. Moreover, the HSI to be unmixed is partitioned into regions where the statistical property of the abundance coefficients have the underlying low-rank property. Then, to further exploit the spatial data structure, under the Bayesian framework, we use GMM to formulate the unmixing problem, and put the low-rank property into the objective function as a prior knowledge, using generalized expectation maximization to solve the objection function. Experiments on synthetic datasets and real HSIs demonstrated that the proposed GMM-SS-LRR is efficient compared with other current popular methods. Full article
(This article belongs to the Special Issue Robust Multispectral/Hyperspectral Image Analysis and Classification)
Figures

Graphical abstract

Open AccessArticle
Divide-and-Conquer Dual-Architecture Convolutional Neural Network for Classification of Hyperspectral Images
Remote Sens. 2019, 11(5), 484; https://doi.org/10.3390/rs11050484
Received: 25 January 2019 / Revised: 19 February 2019 / Accepted: 22 February 2019 / Published: 27 February 2019
Cited by 1 | PDF Full-text (7045 KB) | HTML Full-text | XML Full-text
Abstract
Convolutional neural network (CNN) is well-known for its powerful capability on image classification. In hyperspectral images (HSIs), fixed-size spatial window is generally used as the input of CNN for pixel-wise classification. However, single fixed-size spatial architecture hinders the excellent performance of CNN due [...] Read more.
Convolutional neural network (CNN) is well-known for its powerful capability on image classification. In hyperspectral images (HSIs), fixed-size spatial window is generally used as the input of CNN for pixel-wise classification. However, single fixed-size spatial architecture hinders the excellent performance of CNN due to the neglect of various land-cover distributions in HSIs. Moreover, insufficient samples in HSIs may cause the overfitting problem. To address these problems, a novel divide-and-conquer dual-architecture CNN (DDCNN) method is proposed for HSI classification. In DDCNN, a novel regional division strategy based on local and non-local decisions is devised to distinguish homogeneous and heterogeneous regions. Then, for homogeneous regions, a multi-scale CNN architecture with larger spatial window inputs is constructed to learn joint spectral-spatial features. For heterogeneous regions, a fine-grained CNN architecture with smaller spatial window inputs is constructed to learn hierarchical spectral features. Moreover, to alleviate the problem of insufficient training samples, unlabeled samples with high confidences are pre-labeled under adaptively spatial constraint. Experimental results on HSIs demonstrate that the proposed method provides encouraging classification performance, especially region uniformity and edge preservation with limited training samples. Full article
(This article belongs to the Special Issue Robust Multispectral/Hyperspectral Image Analysis and Classification)
Figures

Graphical abstract

Open AccessArticle
Dense Semantic Labeling with Atrous Spatial Pyramid Pooling and Decoder for High-Resolution Remote Sensing Imagery
Remote Sens. 2019, 11(1), 20; https://doi.org/10.3390/rs11010020
Received: 17 November 2018 / Revised: 14 December 2018 / Accepted: 19 December 2018 / Published: 22 December 2018
Cited by 3 | PDF Full-text (4704 KB) | HTML Full-text | XML Full-text
Abstract
Dense semantic labeling is significant in high-resolution remote sensing imagery research and it has been widely used in land-use analysis and environment protection. With the recent success of fully convolutional networks (FCN), various types of network architectures have largely improved performance. Among them, [...] Read more.
Dense semantic labeling is significant in high-resolution remote sensing imagery research and it has been widely used in land-use analysis and environment protection. With the recent success of fully convolutional networks (FCN), various types of network architectures have largely improved performance. Among them, atrous spatial pyramid pooling (ASPP) and encoder-decoder are two successful ones. The former structure is able to extract multi-scale contextual information and multiple effective field-of-view, while the latter structure can recover the spatial information to obtain sharper object boundaries. In this study, we propose a more efficient fully convolutional network by combining the advantages from both structures. Our model utilizes the deep residual network (ResNet) followed by ASPP as the encoder and combines two scales of high-level features with corresponding low-level features as the decoder at the upsampling stage. We further develop a multi-scale loss function to enhance the learning procedure. In the postprocessing, a novel superpixel-based dense conditional random field is employed to refine the predictions. We evaluate the proposed method on the Potsdam and Vaihingen datasets and the experimental results demonstrate that our method performs better than other machine learning or deep learning methods. Compared with the state-of-the-art DeepLab_v3+ our model gains 0.4% and 0.6% improvements in overall accuracy on these two datasets respectively. Full article
(This article belongs to the Special Issue Robust Multispectral/Hyperspectral Image Analysis and Classification)
Figures

Graphical abstract

Open AccessArticle
Hyperspectral Unmixing with Bandwise Generalized Bilinear Model
Remote Sens. 2018, 10(10), 1600; https://doi.org/10.3390/rs10101600
Received: 5 September 2018 / Revised: 30 September 2018 / Accepted: 6 October 2018 / Published: 9 October 2018
Cited by 2 | PDF Full-text (2999 KB) | HTML Full-text | XML Full-text
Abstract
Generalized bilinear model (GBM) has received extensive attention in the field of hyperspectral nonlinear unmixing. Traditional GBM unmixing methods are usually assumed to be degraded only by additive white Gaussian noise (AWGN), and the intensity of AWGN in each band of hyperspectral image [...] Read more.
Generalized bilinear model (GBM) has received extensive attention in the field of hyperspectral nonlinear unmixing. Traditional GBM unmixing methods are usually assumed to be degraded only by additive white Gaussian noise (AWGN), and the intensity of AWGN in each band of hyperspectral image (HSI) is assumed to be the same. However, the real HSIs are usually degraded by mixture of various kinds of noise, which include Gaussian noise, impulse noise, dead pixels or lines, stripes, and so on. Besides, the intensity of AWGN is usually different for each band of HSI. To address the above mentioned issues, we propose a novel nonlinear unmixing method based on the bandwise generalized bilinear model (NU-BGBM), which can be adapted to the presence of complex mixed noise in real HSI. Besides, the alternative direction method of multipliers (ADMM) is adopted to solve the proposed NU-BGBM. Finally, extensive experiments are conducted to demonstrate the effectiveness of the proposed NU-BGBM compared with some other state-of-the-art unmixing methods. Full article
(This article belongs to the Special Issue Robust Multispectral/Hyperspectral Image Analysis and Classification)
Figures

Graphical abstract

Open AccessArticle
Self-Dictionary Regression for Hyperspectral Image Super-Resolution
Remote Sens. 2018, 10(10), 1574; https://doi.org/10.3390/rs10101574
Received: 28 June 2018 / Revised: 13 September 2018 / Accepted: 21 September 2018 / Published: 1 October 2018
Cited by 3 | PDF Full-text (2566 KB) | HTML Full-text | XML Full-text
Abstract
Due to sensor limitations, hyperspectral images (HSIs) are acquired by hyperspectral sensors with high-spectral-resolution but low-spatial-resolution. It is difficult for sensors to acquire images with high-spatial-resolution and high-spectral-resolution simultaneously. Hyperspectral image super-resolution tries to enhance the spatial resolution of HSI by software techniques. [...] Read more.
Due to sensor limitations, hyperspectral images (HSIs) are acquired by hyperspectral sensors with high-spectral-resolution but low-spatial-resolution. It is difficult for sensors to acquire images with high-spatial-resolution and high-spectral-resolution simultaneously. Hyperspectral image super-resolution tries to enhance the spatial resolution of HSI by software techniques. In recent years, various methods have been proposed to fuse HSI and multispectral image (MSI) from an unmixing or a spectral dictionary perspective. However, these methods extract the spectral information from each image individually, and therefore ignore the cross-correlation between the observed HSI and MSI. It is difficult to achieve high-spatial-resolution while preserving the spatial-spectral consistency between low-resolution HSI and high-resolution HSI. In this paper, a self-dictionary regression based method is proposed to utilize cross-correlation between the observed HSI and MSI. Both the observed low-resolution HSI and MSI are simultaneously considered to estimate the endmember dictionary and the abundance code. To preserve the spectral consistency, the endmember dictionary is extracted by performing a common sparse basis selection on the concatenation of observed HSI and MSI. Then, a consistent constraint is exploited to ensure the spatial consistency between the abundance code of low-resolution HSI and the abundance code of high-resolution HSI. Extensive experiments on three datasets demonstrate that the proposed method outperforms the state-of-the-art methods. Full article
(This article belongs to the Special Issue Robust Multispectral/Hyperspectral Image Analysis and Classification)
Figures

Figure 1

Open AccessArticle
ERN: Edge Loss Reinforced Semantic Segmentation Network for Remote Sensing Images
Remote Sens. 2018, 10(9), 1339; https://doi.org/10.3390/rs10091339
Received: 7 July 2018 / Revised: 14 August 2018 / Accepted: 14 August 2018 / Published: 22 August 2018
Cited by 3 | PDF Full-text (5425 KB) | HTML Full-text | XML Full-text
Abstract
The semantic segmentation of remote sensing images faces two major challenges: high inter-class similarity and interference from ubiquitous shadows. In order to address these issues, we develop a novel edge loss reinforced semantic segmentation network (ERN) that leverages the spatial boundary context to [...] Read more.
The semantic segmentation of remote sensing images faces two major challenges: high inter-class similarity and interference from ubiquitous shadows. In order to address these issues, we develop a novel edge loss reinforced semantic segmentation network (ERN) that leverages the spatial boundary context to reduce the semantic ambiguity. The main contributions of this paper are as follows: (1) we propose a novel end-to-end semantic segmentation network for remote sensing, which involves multiple weighted edge supervisions to retain spatial boundary information; (2) the main representations of the network are shared between the edge loss reinforced structures and semantic segmentation, which means that the ERN simultaneously achieves semantic segmentation and edge detection without significantly increasing the model complexity; and (3) we explore and discuss different ERN schemes to guide the design of future networks. Extensive experimental results on two remote sensing datasets demonstrate the effectiveness of our approach both in quantitative and qualitative evaluation. Specifically, the semantic segmentation performance in shadow-affected regions is significantly improved. Full article
(This article belongs to the Special Issue Robust Multispectral/Hyperspectral Image Analysis and Classification)
Figures

Figure 1

Remote Sens. EISSN 2072-4292 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top