Special Issue "Data Mining and Feature Extraction from Satellite Images and Point Cloud Data"

A special issue of ISPRS International Journal of Geo-Information (ISSN 2220-9964).

Deadline for manuscript submissions: closed (31 March 2019)

Special Issue Editor

Guest Editor
Dr. Pedram Ghamisi

Helmholtz-Zentrum Dresden-Rossendorf, Helmholtz Institute Freiberg for Resource Technology, Division Exploration, Machine Learning Group, Germany
Website | E-Mail
Phone: +491796931140
Interests: spectral and spatial techniques for hyperspectral image classification; multisensor data fusion; machine learning; deep learning

Special Issue Information

Dear Colleagues,

The vibrant field of Earth observation (EO), or remote sensing, is now facing an entirely different dimension of challenge in image interpretation due to the tremendous volumes and huge variety of data being generated by EO missions. An enormous increase in the number of missions coupled with a wide variety of available sensors (e.g., radar, passive microwave, thermal and LiDAR) have led the community to an unprecedented number and complexity of data to process, which is already a major challenge to the existing algorithms.

Such an increase in dimensionality, volume, and varieties provide users with rich data contain for a plethora of applications. However, for a specific application, not all the measurements are important and useful. This data contain may cause a serious issue known as “curse of dimensionality”, which negatively influences on the corresponding feature space for representing the data and downgrades the quality of the further processing steps such as data classification. To address this issue, data mining, which includes feature generation, feature selection, and feature extraction, is a crucial step.

It is expected that the advancement of data mining will continue to push the remote sensing and photogrammetry communities forward. Hence, we passionately encourage authors to submit original research articles, case studies, and review papers from both theoretical and application-oriented perspectives on this important and vibrant subject. In more details, topics appropriate for this Special Issue include (but are not necessarily limited to):

  1. Dimensionality reduction
  2. Feature selection, extraction, and object tracking
  3. Deep learning
  4. Spectral, spatial, and elevation information extraction
  5. Feature fusion
  6. Low-rank models for classification, detection, unmixing, resolution enhancement, and denoising.

Dr. Pedram Ghamisi
Guest Editor

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. ISPRS International Journal of Geo-Information is an international peer-reviewed open access monthly 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 1000 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

  • dimensionality reduction
  • feature selection, feature extraction, and object tracking
  • deep learning
  • spectral, spatial, and elevation information extraction
  • feature fusion
  • low-rank models for classification, detection, unmixing, resolution enhancement, and denoising

Published Papers (12 papers)

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

Research

Open AccessArticle Automatic Building Footprint Extraction from Multi-Resolution Remote Sensing Images Using a Hybrid FCN
ISPRS Int. J. Geo-Inf. 2019, 8(4), 191; https://doi.org/10.3390/ijgi8040191
Received: 26 February 2019 / Revised: 29 March 2019 / Accepted: 6 April 2019 / Published: 12 April 2019
PDF Full-text (8661 KB) | HTML Full-text | XML Full-text
Abstract
Recent technical developments made it possible to supply large-scale satellite image coverage. This poses the challenge of efficient discovery of imagery. One very important task in applications like urban planning and reconstruction is to automatically extract building footprints. The integration of different information, [...] Read more.
Recent technical developments made it possible to supply large-scale satellite image coverage. This poses the challenge of efficient discovery of imagery. One very important task in applications like urban planning and reconstruction is to automatically extract building footprints. The integration of different information, which is presently achievable due to the availability of high-resolution remote sensing data sources, makes it possible to improve the quality of the extracted building outlines. Recently, deep neural networks were extended from image-level to pixel-level labelling, allowing to densely predict semantic labels. Based on these advances, we propose an end-to-end U-shaped neural network, which efficiently merges depth and spectral information within two parallel networks combined at the late stage for binary building mask generation. Moreover, as satellites usually provide high-resolution panchromatic images, but only low-resolution multi-spectral images, we tackle this issue by using a residual neural network block. It fuses those images with different spatial resolution at the early stage, before passing the fused information to the Unet stream, responsible for processing spectral information. In a parallel stream, a stereo digital surface model (DSM) is also processed by the Unet. Additionally, we demonstrate that our method generalizes for use in cities which are not included in the training data. Full article
Figures

Figure 1

Open AccessArticle Oil Film Classification Using Deep Learning-Based Hyperspectral Remote Sensing Technology
ISPRS Int. J. Geo-Inf. 2019, 8(4), 181; https://doi.org/10.3390/ijgi8040181
Received: 13 February 2019 / Revised: 16 March 2019 / Accepted: 31 March 2019 / Published: 6 April 2019
PDF Full-text (6167 KB) | HTML Full-text | XML Full-text
Abstract
Marine oil spills seriously impact the marine environment and transportation. When oil spill accidents occur, oil spill distribution information, in particular, the relative thickness of the oil film, is vital for emergency decision-making and cleaning. Hyperspectral remote sensing technology is an effective means [...] Read more.
Marine oil spills seriously impact the marine environment and transportation. When oil spill accidents occur, oil spill distribution information, in particular, the relative thickness of the oil film, is vital for emergency decision-making and cleaning. Hyperspectral remote sensing technology is an effective means to extract oil spill information. In this study, the concept of deep learning is introduced to the classification of oil film thickness based on hyperspectral remote sensing technology. According to the spatial and spectral characteristics, the stacked autoencoder network model based on the support vector machine is improved, enhancing the algorithm’s classification accuracy in validating data sets. A method for classifying oil film thickness using the convolutional neural network is designed and implemented to solve the problem of space homogeneity and heterogeneity. Through numerous experiments and analyses, the potential of the two proposed deep learning methods for accurately classifying hyperspectral oil spill data is verified. Full article
Figures

Figure 1

Open AccessArticle A Spectral Feature Based Convolutional Neural Network for Classification of Sea Surface Oil Spill
ISPRS Int. J. Geo-Inf. 2019, 8(4), 160; https://doi.org/10.3390/ijgi8040160
Received: 17 February 2019 / Revised: 22 March 2019 / Accepted: 24 March 2019 / Published: 27 March 2019
PDF Full-text (3262 KB) | HTML Full-text | XML Full-text
Abstract
Spectral characteristics play an important role in the classification of oil film, but the presence of too many bands can lead to information redundancy and reduced classification accuracy. In this study, a classification model that combines spectral indices-based band selection (SIs) and one-dimensional [...] Read more.
Spectral characteristics play an important role in the classification of oil film, but the presence of too many bands can lead to information redundancy and reduced classification accuracy. In this study, a classification model that combines spectral indices-based band selection (SIs) and one-dimensional convolutional neural networks was proposed to realize automatic oil films classification using hyperspectral remote sensing images. Additionally, for comparison, the minimum Redundancy Maximum Relevance (mRMR) was tested for reducing the number of bands. The support vector machine (SVM), random forest (RF), and Hu’s convolutional neural networks (CNN) were trained and tested. The results show that the accuracy of classifications through the one dimensional convolutional neural network (1D CNN) models surpassed the accuracy of other machine learning algorithms such as SVM and RF. The model of SIs+1D CNN could produce a relatively higher accuracy oil film distribution map within less time than other models. Full article
Figures

Figure 1

Open AccessArticle Polarimetric Target Decompositions and Light Gradient Boosting Machine for Crop Classification: A Comparative Evaluation
ISPRS Int. J. Geo-Inf. 2019, 8(2), 97; https://doi.org/10.3390/ijgi8020097
Received: 13 December 2018 / Revised: 31 January 2019 / Accepted: 12 February 2019 / Published: 21 February 2019
PDF Full-text (3137 KB) | HTML Full-text | XML Full-text
Abstract
In terms of providing various scattering mechanisms, polarimetric target decompositions provide certain benefits for the interpretation of PolSAR images. This paper tested the capabilities of different polarimetric target decompositions in crop classification, while using a recently launched ensemble learning algorithm—namely Light Gradient Boosting [...] Read more.
In terms of providing various scattering mechanisms, polarimetric target decompositions provide certain benefits for the interpretation of PolSAR images. This paper tested the capabilities of different polarimetric target decompositions in crop classification, while using a recently launched ensemble learning algorithm—namely Light Gradient Boosting Machine (LightGBM). For the classification of different crops (maize, potato, wheat, sunflower, and alfalfa) in the test site, multi-temporal polarimetric C-band RADARSAT-2 images were acquired over an agricultural area near Konya, Turkey. Four different decomposition models (Cloude–Pottier, Freeman–Durden, Van Zyl, and Yamaguchi) were employed to evaluate polarimetric target decomposition for crop classification. Besides the polarimetric target decomposed parameters, the original polarimetric features (linear backscatter coefficients, coherency, and covariance matrices) were also incorporated for crop classification. The experimental results demonstrated that polarimetric target decompositions, with the exception of Cloude–Pottier, were found to be superior to the original features in terms of overall classification accuracy. The highest classification accuracy (92.07%) was achieved by Yamaguchi, whereas the lowest (75.99%) was achieved by the covariance matrix. Model-based decompositions achieved higher performance with respect to eigenvector-based decompositions in terms of class-based accuracies. Furthermore, the results emphasize the added benefits of model-based decompositions for crop classification using PolSAR data. Full article
Figures

Graphical abstract

Open AccessArticle TLS Measurement during Static Load Testing of a Railway Bridge
ISPRS Int. J. Geo-Inf. 2019, 8(1), 44; https://doi.org/10.3390/ijgi8010044
Received: 10 December 2018 / Revised: 14 January 2019 / Accepted: 14 January 2019 / Published: 17 January 2019
PDF Full-text (5093 KB) | HTML Full-text | XML Full-text
Abstract
Terrestrial laser scanning (TLS) technology has become increasingly popular in investigating displacement and deformation of natural and anthropogenic objects. Regardless of the accuracy of deformation identification, TLS provides remote comprehensive information about the measured object in a short time. These features of TLS [...] Read more.
Terrestrial laser scanning (TLS) technology has become increasingly popular in investigating displacement and deformation of natural and anthropogenic objects. Regardless of the accuracy of deformation identification, TLS provides remote comprehensive information about the measured object in a short time. These features of TLS were why TLS measurement was used for a static load test of an old, steel railway bridge. The results of the measurement using the Z + F Imager 5010 scanner and traditional surveying methods (for improved georeferencing) were compared to results of precise reflectorless tacheometry and precise levelling. The analyses involved various procedures for the determination of displacement from 3D data (black & white target analysis, point cloud analysis, and mesh surface analysis) and the need to pre-process the· 3D data was considered (georeferencing, automated filtering). The results demonstrate that TLS measurement can identify vertical displacement in line with the results of traditional measurements down to ±1 mm. Full article
Figures

Figure 1

Open AccessArticle Multi-Temporal Sentinel-1 and -2 Data Fusion for Optical Image Simulation
ISPRS Int. J. Geo-Inf. 2018, 7(10), 389; https://doi.org/10.3390/ijgi7100389
Received: 26 July 2018 / Revised: 8 September 2018 / Accepted: 21 September 2018 / Published: 26 September 2018
PDF Full-text (7589 KB) | HTML Full-text | XML Full-text
Abstract
In this paper, we present the optical image simulation from synthetic aperture radar (SAR) data using deep learning based methods. Two models, i.e., optical image simulation directly from the SAR data and from multi-temporal SAR-optical data, are proposed to testify the possibilities. The [...] Read more.
In this paper, we present the optical image simulation from synthetic aperture radar (SAR) data using deep learning based methods. Two models, i.e., optical image simulation directly from the SAR data and from multi-temporal SAR-optical data, are proposed to testify the possibilities. The deep learning based methods that we chose to achieve the models are a convolutional neural network (CNN) with a residual architecture and a conditional generative adversarial network (cGAN). We validate our models using the Sentinel-1 and -2 datasets. The experiments demonstrate that the model with multi-temporal SAR-optical data can successfully simulate the optical image; meanwhile, the state-of-the-art model with simple SAR data as input failed. The optical image simulation results indicate the possibility of SAR-optical information blending for the subsequent applications such as large-scale cloud removal, and optical data temporal super-resolution. We also investigate the sensitivity of the proposed models against the training samples, and reveal possible future directions. Full article
Figures

Figure 1

Open AccessArticle Feature Extraction and Selection of Sentinel-1 Dual-Pol Data for Global-Scale Local Climate Zone Classification
ISPRS Int. J. Geo-Inf. 2018, 7(9), 379; https://doi.org/10.3390/ijgi7090379
Received: 31 July 2018 / Revised: 7 September 2018 / Accepted: 10 September 2018 / Published: 18 September 2018
Cited by 4 | PDF Full-text (10671 KB) | HTML Full-text | XML Full-text
Abstract
The concept of the local climate zone (LCZ) has been recently proposed as a generic land-cover/land-use classification scheme. It divides urban regions into 17 categories based on compositions of man-made structures and natural landscapes. Although it was originally designed for temperature study, the [...] Read more.
The concept of the local climate zone (LCZ) has been recently proposed as a generic land-cover/land-use classification scheme. It divides urban regions into 17 categories based on compositions of man-made structures and natural landscapes. Although it was originally designed for temperature study, the morphological structure concealed in LCZs also reflects economic status and population distribution. To this end, global LCZ classification is of great value for worldwide studies on economy and population. Conventional classification approaches are usually successful for an individual city using optical remote sensing data. This paper, however, attempts for the first time to produce global LCZ classification maps using polarimetric synthetic aperture radar (PolSAR) data. Specifically, we first produce polarimetric features, local statistical features, texture features, and morphological features and compare them, with respect to their classification performance. Here, an ensemble classifier is investigated, which is trained and tested on already separated transcontinental cities. Considering the challenging global scope this work handles, we conclude the classification accuracy is not yet satisfactory. However, Sentinel-1 dual-Pol SAR data could contribute the classification for several LCZ classes. According to our feature studies, the combination of local statistical features and morphological features yields the best classification results with 61.8% overall accuracy (OA), which is 3% higher than the OA produced by the second best features combination. The 3% is considerably large for a global scale. Based on our feature importance analysis, features related to VH polarized data contributed the most to the eventual classification result. Full article
Figures

Figure 1

Open AccessArticle Road Extraction from VHR Remote-Sensing Imagery via Object Segmentation Constrained by Gabor Features
ISPRS Int. J. Geo-Inf. 2018, 7(9), 362; https://doi.org/10.3390/ijgi7090362
Received: 8 August 2018 / Revised: 26 August 2018 / Accepted: 31 August 2018 / Published: 2 September 2018
PDF Full-text (5712 KB) | HTML Full-text | XML Full-text
Abstract
Automatic road extraction from remote-sensing imagery plays an important role in many applications. However, accurate and efficient extraction from very high-resolution (VHR) images remains difficult because of, for example, increased data size and superfluous details, the spatial and spectral diversity of road targets, [...] Read more.
Automatic road extraction from remote-sensing imagery plays an important role in many applications. However, accurate and efficient extraction from very high-resolution (VHR) images remains difficult because of, for example, increased data size and superfluous details, the spatial and spectral diversity of road targets, disturbances (e.g., vehicles, shadows of trees, and buildings), the necessity of finding weak road edges while avoiding noise, and the fast-acquisition requirement of road information for crisis response. To solve these difficulties, a two-stage method combining edge information and region characteristics is presented. In the first stage, convolutions are executed by applying Gabor wavelets in the best scale to detect Gabor features with location and orientation information. The features are then merged into one response map for connection analysis. In the second stage, highly complete, connected Gabor features are used as edge constraints to facilitate stable object segmentation and limit region growing. Finally, segmented objects are evaluated by some fundamental shape features to eliminate nonroad objects. The results indicate the validity and superiority of the proposed method to efficiently extract accurate road targets from VHR remote-sensing images. Full article
Figures

Graphical abstract

Open AccessArticle Representative Band Selection for Hyperspectral Image Classification
ISPRS Int. J. Geo-Inf. 2018, 7(9), 338; https://doi.org/10.3390/ijgi7090338
Received: 25 June 2018 / Revised: 1 August 2018 / Accepted: 20 August 2018 / Published: 22 August 2018
Cited by 3 | PDF Full-text (3776 KB) | HTML Full-text | XML Full-text
Abstract
The high dimensionality of hyperspectral images (HSIs) brings great difficulty for their later data processing. Band selection, as a commonly used dimension reduction technique, is the selection of optimal band combinations from the original bands, while attempting to remove the redundancy between bands [...] Read more.
The high dimensionality of hyperspectral images (HSIs) brings great difficulty for their later data processing. Band selection, as a commonly used dimension reduction technique, is the selection of optimal band combinations from the original bands, while attempting to remove the redundancy between bands and maintain a good classification ability. In this study, a novel hybrid filter-wrapper band selection method is proposed by a three-step strategy, i.e., band subset decomposition, band selection and band optimization. Based on the information gain (IG) and the spectral curve of the hyperspectral dataset, the band subset decomposition technique is improved, and a random selection strategy is suggested. The implementation of the first two steps addresses the problem of reducing inter-band redundancy. An optimization strategy based on a gray wolf optimizer (GWO) ensures that the selected band combination has a good classification ability. The classification performance of the selected band combination is verified on the Indian Pines, Pavia University and Salinas hyperspectral datasets with the aid of support vector machine (SVM) with a five-fold cross-validation. By comparing the proposed IG-GWO method with five state-of-the-art band selection approaches, the superiority of the proposed method for HSIs classification is experimentally demonstrated on three well-known hyperspectral datasets. Full article
Figures

Figure 1

Open AccessArticle Analysis of Scattering Properties of Continuous Slow-Release Slicks on the Sea Surface Based on Polarimetric Synthetic Aperture Radar
ISPRS Int. J. Geo-Inf. 2018, 7(7), 237; https://doi.org/10.3390/ijgi7070237
Received: 20 May 2018 / Revised: 9 June 2018 / Accepted: 18 June 2018 / Published: 21 June 2018
Cited by 1 | PDF Full-text (10128 KB) | HTML Full-text | XML Full-text
Abstract
This study employs polarimetric synthetic aperture radar (Pol-SAR) to examine the scattering properties of continuous slow-release oil slicks on the sea surface. The objective is to extract and analyze the general polarization scattering properties of continuous slow-release slicks, i.e., those slicks that consist [...] Read more.
This study employs polarimetric synthetic aperture radar (Pol-SAR) to examine the scattering properties of continuous slow-release oil slicks on the sea surface. The objective is to extract and analyze the general polarization scattering properties of continuous slow-release slicks, i.e., those slicks that consist of substances released at a fairly slow and relatively constant rate, and to determine the influence of the slick formation process on these properties. Using multi-polarization feature parameters derived from the averaged coherency matrix, we find that the scattering mechanisms related to the continuous slow-release slicks differ from those of anthropogenic slicks, possibly as a result of the multiple scattering mechanisms that occur between the interfaces formed by the thick slick layer. Combinations of entropy (H) and modified anisotropy (A12) are relatively robust parameters for identifying continuous slow-release slicks under different sea conditions, and may serve as a reference parameter for slick detection. Full article
Figures

Figure 1

Open AccessArticle Semi-Supervised Ground-to-Aerial Adaptation with Heterogeneous Features Learning for Scene Classification
ISPRS Int. J. Geo-Inf. 2018, 7(5), 182; https://doi.org/10.3390/ijgi7050182
Received: 2 April 2018 / Revised: 1 May 2018 / Accepted: 9 May 2018 / Published: 10 May 2018
PDF Full-text (16327 KB) | HTML Full-text | XML Full-text
Abstract
Currently, huge quantities of remote sensing images (RSIs) are becoming available. Nevertheless, the scarcity of labeled samples hinders the semantic understanding of RSIs. Fortunately, many ground-level image datasets with detailed semantic annotations have been collected in the vision community. In this paper, we [...] Read more.
Currently, huge quantities of remote sensing images (RSIs) are becoming available. Nevertheless, the scarcity of labeled samples hinders the semantic understanding of RSIs. Fortunately, many ground-level image datasets with detailed semantic annotations have been collected in the vision community. In this paper, we attempt to exploit the abundant labeled ground-level images to build discriminative models for overhead-view RSI classification. However, images from the ground-level and overhead view are represented by heterogeneous features with different distributions; how to effectively combine multiple features and reduce the mismatch of distributions are two key problems in this scene-model transfer task. Specifically, a semi-supervised manifold-regularized multiple-kernel-learning (SMRMKL) algorithm is proposed for solving these problems. We employ multiple kernels over several features to learn an optimal combined model automatically. Multi-kernel Maximum Mean Discrepancy (MK-MMD) is utilized to measure the data mismatch. To make use of unlabeled target samples, a manifold regularized semi-supervised learning process is incorporated into our framework. Extensive experimental results on both cross-view and aerial-to-satellite scene datasets demonstrate that: (1) SMRMKL has an appealing extension ability to effectively fuse different types of visual features; and (2) manifold regularization can improve the adaptation performance by utilizing unlabeled target samples. Full article
Figures

Graphical abstract

Open AccessArticle Multilevel Cloud Detection for High-Resolution Remote Sensing Imagery Using Multiple Convolutional Neural Networks
ISPRS Int. J. Geo-Inf. 2018, 7(5), 181; https://doi.org/10.3390/ijgi7050181
Received: 5 April 2018 / Revised: 5 May 2018 / Accepted: 7 May 2018 / Published: 9 May 2018
Cited by 3 | PDF Full-text (6276 KB) | HTML Full-text | XML Full-text
Abstract
In high-resolution image data, multilevel cloud detection is a key task for remote sensing data processing. Generally, it is difficult to obtain high accuracy for multilevel cloud detection when using satellite imagery which only contains visible and near-infrared spectral bands. So, multilevel cloud [...] Read more.
In high-resolution image data, multilevel cloud detection is a key task for remote sensing data processing. Generally, it is difficult to obtain high accuracy for multilevel cloud detection when using satellite imagery which only contains visible and near-infrared spectral bands. So, multilevel cloud detection for high-resolution remote sensing imagery is challenging. In this paper, a new multilevel cloud detection technique is proposed based on the multiple convolutional neural networks for high-resolution remote sensing imagery. In order to avoid input the entire image into the network for cloud detection, the adaptive simple linear iterative clustering (A-SCLI) algorithm was applied to the segmentation of the satellite image to obtain good-quality superpixels. After that, a new multiple convolutional neural networks (MCNNs) architecture is designed to extract multiscale features from each superpixel, and the superpixels are marked as thin cloud, thick cloud, cloud shadow, and non-cloud. The results suggest that the proposed method can detect multilevel clouds and obtain a high accuracy for high-resolution remote sensing imagery. Full article
Figures

Figure 1

ISPRS Int. J. Geo-Inf. EISSN 2220-9964 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top