Submit to Remote Sensing Review for Remote Sensing Propose a Special Issue

Journal Menu

Journal Browser

Computer Vision and Pattern Recognition for the Analysis of 2D/3D Remote Sensing Data in Geoscience

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Benefits of Publishing in a Special Issue
Published Papers

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

Deadline for manuscript submissions: closed (21 January 2022) | Viewed by 36487

Share This Special Issue

Special Issue Editors

Prof. Dr. Michalis Savelonas

E-Mail Website
Guest Editor

Department of Computer Science and Biomedical Informatics, School of Science, Campus of Lamia, University of Thessaly, GR-35131 Lamia, Greece
Interests: pattern recognition; computer vision; expert systems
Special Issues, Collections and Topics in MDPI journals

Dr. Emmanuel Vassilakis

E-Mail Website
Guest Editor

National and Kapodistrian University of Athens, 157 72 Athens, Greece
Interests: airborne and terrestrial LiDAR data interpretation; UAV data acquisition and processing; active tectonics; coastline displacement and high precision geodetic techniques
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The advent of various 2D/3D imaging technologies in the area of remote sensing raises multiple challenges for computational tools capable of assisting domain experts, such as earth scientists, in the study of a diverse range of phenomena, including natural disasters. The growing availability of huge amounts of imaging data in the form of 2D images (aerial, satellite, etc.), point clouds, 3D meshes, and hyperspectral images creates an ideal field for the application of various deep learning strategies, as well as of standard descriptor-based computer vision approaches. In addition, the processing and analysis of time-series derived from remote sensing modalities could reveal temporal patterns reflecting changes that could be quantified. The recent development of various types of recurrent neural networks (RNNs) provides a promising direction for the development of intelligent computational tools handling such time-series.

This Special Issue aims to explore the state-of-the-art in computer vision and pattern recognition applications on remote sensing, with an emphasis on geoscience data. Research contributions, as well as surveys are welcome. In particular, novel contributions covering, but not limited to, the following subtopics are welcome:

- Applications on different techniques for point cloud generation, such as: vehicle-based laser scanning (VLS); terrestrial laser scanning (TLS), airborne laser scanning (ALS) and photogrammetry (structure-from-motion), are welcome;

- Quantifying land surface processes with high-resolution topography and terrain analysis: The use of point clouds has promising perspectives in different fields of geosciences, for supporting high-resolution geological or geomorphological mapping, for studying the evolution of active processes, as well as for monitoring various kinds of natural hazards;

- Point clouds mainly acquired by easy-to-carry scanning equipment, specifically designed for scanning smaller geomorphs or objects called GeoSLAM and Sense 3D: We encourage works carried out at all scales and environments, including comparative studies, as well as the description of new methodologies, best practices, advantages and limitations for the use of such datasets.

Prof. Michalis Savelonas
Prof. Emmanuel Vassilakis
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 submissions that pass pre-check are 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 2700 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

Point-clouds
LiDAR
Hyper-spectral imaging
Computer vision
Pattern recognition
3D shape analysis
Time-series analysis
3D change detection
Structure-from-motion
Quantitative geomorphology
Geo-morphometry

Benefits of Publishing in a Special Issue

Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (9 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

21 pages, 2479 KiB

Open AccessArticle

A Visual Compass Based on Point and Line Features for UAV High-Altitude Orientation Estimation

by Ying Liu, Junyi Tao, Da Kong, Yu Zhang and Ping Li

Remote Sens. 2022, 14(6), 1430; https://doi.org/10.3390/rs14061430 - 16 Mar 2022

Cited by 4 | Viewed by 3417

Abstract

The accurate and reliable high-altitude orientation estimation is of great significance for unmanned aerial vehicles (UAVs) localization, and further assists them to conduct some fundamental functions, such as aerial mapping, environmental monitoring, and risk management. However, the traditional orientation estimation is susceptible to electromagnetic interference, high maneuverability, and substantial scale variations. Hence, this paper aims to present a new visual compass algorithm to estimate the orientation of a UAV employing the appearance and geometry structure of the point and line features in the remote sensing images. In this study, a coarse-to-fine feature tracking method is used to locate the matched keypoints precisely. An LK-ZNCC algorithm is proposed to match line segments in real-time. A hierarchical fusion method for point and line features is designed to expand the scope of the usage of this system. Many comparative experiments between this algorithm and others are conducted on a UAV. Experimental results show that the proposed visual compass algorithm is a reliable, precise, and versatile system applicable to other UAV navigation systems, especially when they do not work in particular situations. Full article

(This article belongs to the Special Issue Computer Vision and Pattern Recognition for the Analysis of 2D/3D Remote Sensing Data in Geoscience)

► Show Figures

Graphical abstract

23 pages, 6978 KiB

Open AccessArticle

Object Tracking in Satellite Videos Based on Correlation Filter with Multi-Feature Fusion and Motion Trajectory Compensation

by Yaosheng Liu, Yurong Liao, Cunbao Lin, Yutong Jia, Zhaoming Li and Xinyan Yang

Remote Sens. 2022, 14(3), 777; https://doi.org/10.3390/rs14030777 - 7 Feb 2022

Cited by 19 | Viewed by 3144

Abstract

As a new type of earth observation satellite approach, video satellites can continuously monitor an area of the Earth and acquire dynamic and abundant information by utilizing video imaging. Hence, video satellites can afford to track various objects of interest on the Earth's surface. Inspired by the capabilities of video satellites, this paper presents a novel method to track fast-moving objects in satellite videos based on the kernelized correlation filter (KCF) embedded with multi-feature fusion and motion trajectory compensation. The contributions of the suggested algorithm are multifold. First, a multi-feature fusion strategy is proposed to describe an object comprehensively, which is challenging for the single-feature approach. Second, a subpixel positioning method is developed to calculate the object’s position and overcome the poor tracking accuracy difficulties caused by inaccurate object localization. Third, introducing an adaptive Kalman filter (AKF) enables compensation and correction of the KCF tracker results and reduces the object’s bounding box drift, solving the moving object occlusion problem. Based on the correlation filtering tracking framework, combined with the above improvement strategies, our algorithm improves the tracking accuracy by at least 17% on average and the success rate by at least 18% on average compared to the KCF algorithm. Hence, our method effectively solves poor object tracking accuracy caused by complex backgrounds and object occlusion. The experimental results utilize satellite videos from the Jilin-1 satellite constellation and highlight the proposed algorithm's appealing tracking results against current state-of-the-art trackers regarding success rate, precision, and robustness metrics. Full article

(This article belongs to the Special Issue Computer Vision and Pattern Recognition for the Analysis of 2D/3D Remote Sensing Data in Geoscience)

► Show Figures

Figure 1

22 pages, 5235 KiB

Open AccessArticle

Multiscale Feature Fusion Network Incorporating 3D Self-Attention for Hyperspectral Image Classification

by Yuhao Qing, Quanzhen Huang, Liuyan Feng, Yueyan Qi and Wenyi Liu

Remote Sens. 2022, 14(3), 742; https://doi.org/10.3390/rs14030742 - 5 Feb 2022

Cited by 22 | Viewed by 4217

Abstract

In recent years, the deep learning-based hyperspectral image (HSI) classification method has achieved great success, and the convolutional neural network (CNN) method has achieved good classification performance in the HSI classification task. However, the convolutional operation only works with local neighborhoods, and is effective in extracting local features. It is difficult to capture interactive features over long distances, which affects the accuracy of classification to some extent. At the same time, the data from HSI have the characteristics of three-dimensionality, redundancy, and noise. To solve these problems, we propose a 3D self-attention multiscale feature fusion network (3DSA-MFN) that integrates 3D multi-head self-attention. 3DSA-MFN first uses different sized convolution kernels to extract multiscale features, samples the different granularities of the feature map, and effectively fuses the spatial and spectral features of the feature map. Then, we propose an improved 3D multi-head self-attention mechanism that provides local feature details for the self-attention branch, and fully exploits the context of the input matrix. To verify the performance of the proposed method, we compare it with six current methods on three public datasets. The experimental results show that the proposed 3DSA-MFN achieves competitive classification and highlights the HSI classification task. Full article

(This article belongs to the Special Issue Computer Vision and Pattern Recognition for the Analysis of 2D/3D Remote Sensing Data in Geoscience)

► Show Figures

Figure 1

32 pages, 6374 KiB

Open AccessArticle

4D U-Nets for Multi-Temporal Remote Sensing Data Classification

by Michalis Giannopoulos, Grigorios Tsagkatakis and Panagiotis Tsakalides

Remote Sens. 2022, 14(3), 634; https://doi.org/10.3390/rs14030634 - 28 Jan 2022

Cited by 12 | Viewed by 4935

Abstract

Multispectral sensors constitute a core earth observation imaging technology generating massive high-dimensional observations acquired across multiple time instances. The collected multi-temporal remote sensed data contain rich information for Earth monitoring applications, from flood detection to crop classification. To easily classify such naturally multidimensional data, conventional low-order deep learning models unavoidably toss away valuable information residing across the available dimensions. In this work, we extend state-of-the-art convolutional network models based on the U-Net architecture to their high-dimensional analogs, which can naturally capture multi-dimensional dependencies and correlations. We introduce several model architectures, both of low as well as of high order, and we quantify the achieved classification performance vis-à-vis the latest state-of-the-art methods. The experimental analysis on observations from Landsat-8 reveals that approaches based on low-order U-Net models exhibit poor classification performance and are outperformed by our proposed high-dimensional U-Net scheme. Full article

(This article belongs to the Special Issue Computer Vision and Pattern Recognition for the Analysis of 2D/3D Remote Sensing Data in Geoscience)

► Show Figures

Figure 1

21 pages, 3832 KiB

Open AccessArticle

Encoding Spectral-Spatial Features for Hyperspectral Image Classification in the Satellite Internet of Things System

by Ning Lv, Zhen Han, Chen Chen, Yijia Feng, Tao Su, Sotirios Goudos and Shaohua Wan

Remote Sens. 2021, 13(18), 3561; https://doi.org/10.3390/rs13183561 - 7 Sep 2021

Cited by 5 | Viewed by 2558

Abstract

Hyperspectral image classification is essential for satellite Internet of Things (IoT) to build a large scale land-cover surveillance system. After acquiring real-time land-cover information, the edge of the network transmits all the hyperspectral images by satellites with low-latency and high-efficiency to the cloud computing center, which are provided by satellite IoT. A gigantic amount of remote sensing data bring challenges to the storage and processing capacity of traditional satellite systems. When hyperspectral images are used in annotation of land-cover application, data dimension reduction for classifier efficiency often leads to the decrease of classifier accuracy, especially the region to be annotated consists of natural landform and artificial structure. This paper proposes encoding spectral-spatial features for hyperspectral image classification in the satellite Internet of Things system to extract features effectively, namely attribute profile stacked autoencoder (AP-SAE). Firstly, extended morphology attribute profiles EMAP is used to obtain spatial features of different attribute scales. Secondly, AP-SAE is used to extract spectral features with similar spatial attributes. In this stage the program can learn feature mappings, on which the pixels from the same land-cover class are mapped as closely as possible and the pixels from different land-cover categories are separated by a large margin. Finally, the program trains an effective classifier by using the network of the AP-SAE. Experimental results on three widely-used hyperspectral image (HSI) datasets and comprehensive comparisons with existing methods demonstrate that our proposed method can be used effectively in hyperspectral image classification. Full article

(This article belongs to the Special Issue Computer Vision and Pattern Recognition for the Analysis of 2D/3D Remote Sensing Data in Geoscience)

► Show Figures

Figure 1

24 pages, 6282 KiB

Open AccessArticle

Changes in the End-of-Summer Snow Line Altitude of Summer-Accumulation-Type Glaciers in the Eastern Tien Shan Mountains from 1994 to 2016

by Xiaoying Yue, Zhongqin Li, Jun Zhao, Huilin Li, Puyu Wang and Lin Wang

Remote Sens. 2021, 13(6), 1080; https://doi.org/10.3390/rs13061080 - 12 Mar 2021

Cited by 11 | Viewed by 2739

Abstract

For summer-accumulation-type glaciers, the glaciological literature is lacking studies on determining the snow line altitude (SLA) from optical images at the end of the summer as an indicator of the equilibrium line altitude (ELA). This paper presents a workflow for extracting the SLA from Landsat images based on the variation in the albedo with the altitude in the central line area of glaciers. The correlation of >0.8 at the 99% confidence level between the retrieved SLAs with ELAs derived from the interpolation of ground-based, mass balance measurements indicated that the workflow can be applied to derive the SLA from end-of-summer satellite data as an indicator of ELA. The ELA was under-estimated by the calculated SLA. The relationship between the end-of-summer SLA and the ELA depends on the intensity of glacier melting. Subsequently, the workflow was applied to the seven glaciers in the Eastern Tien Shan Mountains, and a time series of the SLA was obtained using 12 end-of-summer Landsat scenes from 1994 to 2016. Over the whole study period, a mean SLA of 4011.6 ± 20.7 m above sea level (a.s.l.) was derived for the seven investigated glaciers, and an increasing SLA was demonstrated. The increase in SLAs was consistent for the seven glaciers from 1994 to 2016. Concerning the spatial variability, the east–west difference was prominent, and these differences exhibited a decreasing trend. The average SLA of each glacier is more influenced by its morpho-topographic variables. The interannual variations in the average SLA are mainly driven by the increasing summer air temperature, and the high correlation with the cumulative summer solid precipitation reflects the characteristics of the summer-accumulation-type glaciers. Full article

(This article belongs to the Special Issue Computer Vision and Pattern Recognition for the Analysis of 2D/3D Remote Sensing Data in Geoscience)

► Show Figures

Figure 1

17 pages, 10031 KiB

Open AccessArticle

Morphometric Analysis of Pluto’s Impact Craters

by Caio Vidaurre Nassif Villaça, Alvaro Penteado Crósta and Carlos Henrique Grohmann

Remote Sens. 2021, 13(3), 377; https://doi.org/10.3390/rs13030377 - 22 Jan 2021

Cited by 4 | Viewed by 3377

Abstract

The scope of this work is to carry out a morphometric analysis of Pluto’s impact craters. A global Pluto digital elevation model (DEM) with a resolution of 300 m/px, created from stereoscopic pairs obtained by the New Horizons Mission, was used to extract the morphometric data of craters. Pluto’s surface was divided according to different morphometric characteristics in order to analyze possible differences in the impact dynamics and modification rate in each region. A Python code was developed, within the QGIS 3× software environment, to automate the process of crater outlining and collection of morphometric data: diameter (D), depth (d), depth variation, slope of the inner wall (Sw), diameter of the base (Db), and the width of the wall (Ww). Data have been successfully obtained for 237 impact craters on five distinct terrains over the west side of Sputnik Planitia on Pluto. With the collected data, it was possible to observe that craters near the equator (areas 3 and 4) are deeper than craters above 35°N (areas 1 and 2). Craters on the western regions (areas 2 and 3) contain the lowest depth values for a given diameter. The transition diameter from simple to complex crater morphology was found to change throughout the areas of study. Craters within areas 1 and 4 exhibit a transition diameter (Dt) of approximately 10 km, while Dt for craters within areas 3 and 5 the transitions occurs at 15 km approximately. The presence of volatile ices in the north and north-west regions may be the reason for the difference of morphometry between these two terrains of Pluto. Two hypotheses are presented to explain these differences: (1) The presence of volatile ices can affect the formation of craters by making the target surface weaker and more susceptible to major changes (e.g., mass waste and collapse of the walls) during the formation process until its final stage; (2) The high concentration of volatiles can affect the depth of the craters by atmospheric decantation, considering that these elements undergo seasonal decantation and sublimation cycles. Full article

(This article belongs to the Special Issue Computer Vision and Pattern Recognition for the Analysis of 2D/3D Remote Sensing Data in Geoscience)

► Show Figures

Graphical abstract

27 pages, 18065 KiB

Open AccessArticle

Unmanned Aerial Systems-Aided Post-Flood Peak Discharge Estimation in Ephemeral Streams

by Emmanouil Andreadakis, Michalis Diakakis, Emmanuel Vassilakis, Georgios Deligiannakis, Antonis Antoniadis, Petros Andriopoulos, Nafsika I. Spyrou and Efthymios I. Nikolopoulos

Remote Sens. 2020, 12(24), 4183; https://doi.org/10.3390/rs12244183 - 21 Dec 2020

Cited by 18 | Viewed by 3502

Abstract

The spatial and temporal scale of flash flood occurrence provides limited opportunities for observations and measurements using conventional monitoring networks, turning the focus to event-based, post-disaster studies. Post-flood surveys exploit field evidence to make indirect discharge estimations, aiming to improve our understanding of hydrological response dynamics under extreme meteorological forcing. However, discharge estimations are associated with demanding fieldwork aiming to record in small timeframes delicate data and data prone-to-be-lost and achieve the desired accuracy in measurements to minimize various uncertainties of the process. In this work, we explore the potential of unmanned aerial systems (UAS) technology, in combination with the Structure for Motion (SfM) and optical granulometry techniques in peak discharge estimations. We compare the results of the UAS-aided discharge estimations to estimates derived from differential Global Navigation Satellite System (d-GNSS) surveys and hydrologic modelling. The application in the catchment of the Soures torrent in Greece, after a catastrophic flood, shows that the UAS-aided method determined peak discharge with accuracy, providing very similar values compared to the ones estimated by the established traditional approach. The technique proved to be particularly effective, providing flexibility in terms of resources and timing, although there are certain limitations to its applicability, related mostly to the optical granulometry as well as the condition of the channel. The application highlighted important advantages and certain weaknesses of these emerging tools in indirect discharge estimations, which we discuss in detail. Full article

(This article belongs to the Special Issue Computer Vision and Pattern Recognition for the Analysis of 2D/3D Remote Sensing Data in Geoscience)

► Show Figures

Graphical abstract

23 pages, 5964 KiB

Open AccessArticle

Object-Based Analysis Using Unmanned Aerial Vehicles (UAVs) for Site-Specific Landslide Assessment

by Efstratios Karantanellis, Vassilis Marinos, Emmanuel Vassilakis and Basile Christaras

Remote Sens. 2020, 12(11), 1711; https://doi.org/10.3390/rs12111711 - 27 May 2020

Cited by 57 | Viewed by 6362

Abstract

The increased development of computer vision technology combined with the increased availability of innovative platforms with ultra-high-resolution sensors, has generated new opportunities and fields for investigation in the engineering geology domain in general and landslide identification and characterization in particular. During the last decade, the so-called Unmanned Aerial Vehicles (UAVs) have been evaluated for diverse applications such as 3D terrain analysis, slope stability, mass movement hazard and risk management. Their advantages of detailed data acquisition at a low cost and effective performance identifies them as leading platforms for site-specific 3D modelling. In this study, the proposed methodology has been developed based on Object-Based Image Analysis (OBIA) and fusion of multivariate data resulted from UAV photogrammetry processing in order to take full advantage of the produced data. Two landslide case studies within the territory of Greece, with different geological and geomorphological characteristics, have been investigated in order to assess the developed landslide detection and characterization algorithm performance in distinct scenarios. The methodology outputs demonstrate the potential for an accurate characterization of individual landslide objects within this natural process based on ultra high-resolution data from close range photogrammetry and OBIA techniques for landslide conceptualization. This proposed study shows that UAV-based landslide modelling on the specific case sites provides a detailed characterization of local scale events in an automated sense with high adaptability on the specific case site. Full article

(This article belongs to the Special Issue Computer Vision and Pattern Recognition for the Analysis of 2D/3D Remote Sensing Data in Geoscience)

► Show Figures

Journal Menu

Journal Browser

Computer Vision and Pattern Recognition for the Analysis of 2D/3D Remote Sensing Data in Geoscience

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (9 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI