[go: up one dir, main page]

 
 
Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Article Types

Countries / Regions

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Search Results (1,008)

Search Parameters:
Keywords = Worldview-2

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
16 pages, 1511 KiB  
Article
“Sharing Worldviews: Learning in Encounter for Common Values in Diversity” in School and Teacher Education—Contexts in Germany and Europe
by Katja Boehme
Religions 2024, 15(9), 1077; https://doi.org/10.3390/rel15091077 - 5 Sep 2024
Viewed by 296
Abstract
Challenges and tensions that arise in a pluralistic society with differing worldviews among its citizens must be addressed from the outset in school education. To enable social cohesion within a heterogeneous society, students must learn to harmonize their own worldviews with other interpretations [...] Read more.
Challenges and tensions that arise in a pluralistic society with differing worldviews among its citizens must be addressed from the outset in school education. To enable social cohesion within a heterogeneous society, students must learn to harmonize their own worldviews with other interpretations of the world in a spirit of “reciprocal inclusivity” (Reinhold Bernhardt). This article argues that this task particularly falls within the responsibility of subjects in schools that address the existential “problems of constitutive rationality” (Jürgen Baumert), specifically religious education, ethics, and philosophy. In Germany and Austria, multiple subjects within denominational religious education, as well as ethics and philosophy, are offered in schools. When these subjects collaborate on projects, students learn to engage in dialogue with the various religious and secular, individual, and collective interpretations, perspectives, and worldviews they encounter. Since 2002/03, and in teacher training since 2011, such a didactically guided Sharing Worldviews approach has been implemented in school projects in Southern Germany through a four-phase concept. This concept can be flexibly applied to the local conditions of the school, contributes to internationalisation and digitalisation, and does not require additional teaching hours. By incorporating secular worldviews, Sharing Worldviews goes beyond interreligious learning and has also been realised digitally in other European countries. The following article begins by considering the educational requirements in a heterogeneous society (1), describes the prerequisites needed to positively influence students’ attitudes (2), outlines common foundational concepts for interreligious and inter-worldview dialogue (3), and recommends “Mutual Hospitality” as the basis for such dialogue in schools (4). The article then explains how “Mutual Hospitality” can be practically implemented in a four-phase concept of Sharing Worldviews both in schools and in teacher training (5 and 6) by tracing the origins of this concept (7). The Sharing Worldviews concept has been both internationalised and digitalised in schools and teacher education (8), aligns with the educational principles of the OECD (9), and demonstrates significant benefits in empirical studies (10). Full article
(This article belongs to the Special Issue Shared Religious Education)
Show Figures

Figure 1

Figure 1
<p><span class="html-italic">Sharing Wordviews</span> in four phases with presentation phase and discussion phase as station work in mixed groups of students. Each subject prepares a station from its own worldview on the topic (cf. <a href="#B12-religions-15-01077" class="html-bibr">Boehme 2023, p. 381</a>; <a href="http://www.sharing-worldviews.com/en/node/2" target="_blank">www.sharing-worldviews.com/en/node/2</a>, accessed on 29 August 2024).</p>
Full article ">Figure 2
<p><span class="html-italic">Sharing Wordviews</span> in four phases with presentation phase and discussion phase as station work in mixed groups of students. Each subject contributes its own view of a subtopic to each station (cf. <a href="#B12-religions-15-01077" class="html-bibr">Boehme 2023, p. 382</a>; <a href="http://www.sharing-worldviews.com/en/node/2" target="_blank">www.sharing-worldviews.com/en/node/2</a>, accessed on 1 September 2024).</p>
Full article ">
20 pages, 2417 KiB  
Article
Indigenous Subsistence Practices of the Sakha Horse Herders under Changing Climate in the Arctic
by Lena Popova
Climate 2024, 12(9), 134; https://doi.org/10.3390/cli12090134 - 3 Sep 2024
Viewed by 485
Abstract
This article provides, firstly, an overview of Arctic traditional horse herding as one of the Indigenous subsistence practices of the Republic of Sakha (Yakutia). It discusses the origins, characteristics, and spiritual and material importance of Sakha horses and horse herding practices to inform [...] Read more.
This article provides, firstly, an overview of Arctic traditional horse herding as one of the Indigenous subsistence practices of the Republic of Sakha (Yakutia). It discusses the origins, characteristics, and spiritual and material importance of Sakha horses and horse herding practices to inform the overall understanding of this traditional subsistence activity, which remains largely unexplored. Secondly, by conducting in-depth semi-structured interviews with Indigenous Sakha horse herders, this study explores the ways in which Indigenous subsistence practices are evolving and reacting to the climate and environmental changes. Results show that climate change is altering the local ecosystem and introducing new challenges to communities in Central Yakutia. Local herders describe climate change as a complex interplay of diverse transformations rather than a singular phenomenon. While historical adaptation strategies relied on the flexibility of traditional practices, today, this flexibility is often hindered by non-climatic factors. This article further discusses adaptability of Indigenous practices to climate change and offers recommendations for their development, particularly traditional horse herding. Future research related to climate change and Arctic Indigenous communities should encompass deeper and broader aspects, covering historical, cultural, social, and economic contexts and the worldviews of Indigenous peoples, distinct from Western perspectives. Full article
Show Figures

Figure 1

Figure 1
<p>Location of the Republic of Sakha (Yakutia).</p>
Full article ">Figure 2
<p>The Sakha horse breed. Source: <a href="https://old.nlrs.ru/exhibitions/yakutian-horse/" target="_blank">https://old.nlrs.ru/exhibitions/yakutian-horse/</a> (accessed on 16 February 2024).</p>
Full article ">Figure 3
<p>(<b>a</b>) Horse breeders and their herd; (<b>b</b>) Horses in a paddock in Oymiakon uluus. Photographs: Egor Makarov (<b>a</b>), Lena Popova (<b>b</b>).</p>
Full article ">Figure 4
<p>The Sakha breed of horse: (<b>a</b>) One-year-old foal; (<b>b</b>) Horse herd in Oymyakon uluus. Photographs: Iliya Voskresensky.</p>
Full article ">Figure 5
<p>The study area. 1—Tattinsky uluus, 2—Churapchinsky uluus, 3—Vilyuisky uluus.</p>
Full article ">
17 pages, 288 KiB  
Article
Re-Thinking Subjectivation beyond Work and Appropriation: The Yanomami Anti-Production Strategies
by Ana Suelen Tossige Gomes
Philosophies 2024, 9(5), 136; https://doi.org/10.3390/philosophies9050136 - 29 Aug 2024
Viewed by 361
Abstract
Western culture has assigned an essential role to productive activity in defining our lives. In Locke’s and Hegel’s thought, we see the model that became dominant in modern political philosophy: that of conceiving the subject as a result of, and only possible within, [...] Read more.
Western culture has assigned an essential role to productive activity in defining our lives. In Locke’s and Hegel’s thought, we see the model that became dominant in modern political philosophy: that of conceiving the subject as a result of, and only possible within, the triad of work–property–subject. Nowadays, this has reached the level of shaping the meaning of living, and our entire existences seem to be subjected to a concept of lives-as-work. Combining anthropology and philosophy, this article seeks to rethink subjectivation beyond the process of work and appropriation, delving into worldviews different from those of the West. Specifically, we will focus on the Yanomami form of life, a non-stratified indigenous people living in the Brazilian Amazon. We will analyze how the Yanomami prevent the process of subjectification by the objectification of one’s own work through a sort of anti-work and anti-property apparatus. This is achieved through specific techniques of underproduction, which constitute another approach to work, as well as through a completely different way of conceiving subjectivity. Furthermore, the Yanomami’s view of all entities as subjects endowed with intentionality appears as de-ontologizing the subject position and deactivating the dyads of subject/object and own/common. The result is a worldview where, with everyone being subjects—humans and non-humans, living and dead, entities and things of nature—no one can be dominus of anyone. Full article
11 pages, 247 KiB  
Article
The Relevancy of Religious Literacy in Social Studies Curricula: Quebec’s CCQ as a Case Study
by W. Y. Alice Chan, Sivane Hirsch and Hicham Tiflati
Religions 2024, 15(9), 1046; https://doi.org/10.3390/rel15091046 - 28 Aug 2024
Viewed by 353
Abstract
This article explores Quebec’s recent transition from the “Ethics and Religious Culture” (ERC) program to the “Culture and Citizenship in Quebec” (CCQ) program, emphasizing the role of religious literacy in secular societies. We investigate the rationale behind the shift, and examine the ERC’s [...] Read more.
This article explores Quebec’s recent transition from the “Ethics and Religious Culture” (ERC) program to the “Culture and Citizenship in Quebec” (CCQ) program, emphasizing the role of religious literacy in secular societies. We investigate the rationale behind the shift, and examine the ERC’s focus on fostering understanding of diverse religious and ethical perspectives as well as CCQ’s broader mandate to integrate cultural and civic education and its aim at the development of a shared and common public Quebecois culture. The case study highlights the pedagogical and societal implications of this change, discussing how the CCQ program aims to enhance civic engagement, cultural awareness, and social cohesion. Furthermore, the article identifies opportunities for educators to address pressing global challenges, such as polarization, reconciliation, and the climate crisis, within the new curriculum framework. By promoting critical thinking, inclusivity, and active citizenship, fostering religious literacy in such programs presents a unique opportunity for educators and youth to contribute to a more resilient and harmonious society. Full article
(This article belongs to the Special Issue Religious Diversity and Social Studies Education)
18 pages, 2642 KiB  
Article
An Unsupervised CNN-Based Pansharpening Framework with Spectral-Spatial Fidelity Balance
by Matteo Ciotola, Giuseppe Guarino and Giuseppe Scarpa
Remote Sens. 2024, 16(16), 3014; https://doi.org/10.3390/rs16163014 - 16 Aug 2024
Viewed by 442
Abstract
In recent years, deep learning techniques for pansharpening multiresolution images have gained increasing interest. Due to the lack of ground truth data, most deep learning solutions rely on synthetic reduced-resolution data for supervised training. This approach has limitations due to the statistical mismatch [...] Read more.
In recent years, deep learning techniques for pansharpening multiresolution images have gained increasing interest. Due to the lack of ground truth data, most deep learning solutions rely on synthetic reduced-resolution data for supervised training. This approach has limitations due to the statistical mismatch between real full-resolution and synthetic reduced-resolution data, which affects the models’ generalization capacity. Consequently, there has been a shift towards unsupervised learning frameworks for pansharpening deep learning-based techniques. Unsupervised schemes require defining sophisticated loss functions with at least two components: one for spectral quality, ensuring consistency between the pansharpened image and the input multispectral component, and another for spatial quality, ensuring consistency between the output and the panchromatic input. Despite promising results, there has been limited investigation into the interaction and balance of these loss terms to ensure stability and accuracy. This work explores how unsupervised spatial and spectral consistency losses can be reliably combined preserving the outocome quality. By examining these interactions, we propose a general rule for balancing the two loss components to enhance the stability and performance of unsupervised pansharpening models. Experiments on three state-of-the-art algorithms using WorldView-3 images demonstrate that methods trained with the proposed framework achieve good performance in terms of visual quality and numerical indexes. Full article
(This article belongs to the Special Issue Weakly Supervised Deep Learning in Exploiting Remote Sensing Big Data)
Show Figures

Figure 1

Figure 1
<p>A-PNN model for Z-PNN [<a href="#B46-remotesensing-16-03014" class="html-bibr">46</a>].</p>
Full article ">Figure 2
<p>PanNet architecture [<a href="#B11-remotesensing-16-03014" class="html-bibr">11</a>].</p>
Full article ">Figure 3
<p>BDPN model [<a href="#B37-remotesensing-16-03014" class="html-bibr">37</a>].</p>
Full article ">Figure 4
<p>Spectral loss terms after 200 iterations for different <math display="inline"><semantics> <mfenced separators="" open="(" close=")"> <mi>α</mi> <mo>,</mo> <mi>β</mi> </mfenced> </semantics></math> configurations.</p>
Full article ">Figure 5
<p>Spatial loss terms after 200 iterations for different <math display="inline"><semantics> <mfenced separators="" open="(" close=")"> <mi>α</mi> <mo>,</mo> <mi>β</mi> </mfenced> </semantics></math> configurations.</p>
Full article ">Figure 6
<p>Sample results taken from WV3 Adelaide dataset: input MS and PAN followed by related pansharpenings obtained by Z-PNN through target adaptation for 500 epochs with different <math display="inline"><semantics> <mrow> <mo>(</mo> <mi>α</mi> <mo>,</mo> <mi>β</mi> <mo>)</mo> </mrow> </semantics></math> settings.</p>
Full article ">Figure 7
<p>Sample results taken from WV3 Adelaide dataset: input MS and PAN followed by related pansharpenings obtained by PanNet through target adaptation for 500 epochs with different <math display="inline"><semantics> <mrow> <mo>(</mo> <mi>α</mi> <mo>,</mo> <mi>β</mi> <mo>)</mo> </mrow> </semantics></math> settings.</p>
Full article ">Figure 8
<p>Sample results taken from WV3 Adelaide dataset: input MS and PAN followed by related pansharpenings obtained by BDPN through target adaptation for 500 epochs with different <math display="inline"><semantics> <mrow> <mo>(</mo> <mi>α</mi> <mo>,</mo> <mi>β</mi> <mo>)</mo> </mrow> </semantics></math> settings.</p>
Full article ">Figure 9
<p>Full-resolution accuracy indexes for Z-PNN, with <math display="inline"><semantics> <mrow> <mi>α</mi> <mo>=</mo> <mn>0.03</mn> </mrow> </semantics></math> and <math display="inline"><semantics> <mrow> <mi>β</mi> <mo>∈</mo> <mfenced separators="" open="[" close="]"> <mn>3</mn> <mo>·</mo> <msup> <mn>10</mn> <mrow> <mo>−</mo> <mn>5</mn> </mrow> </msup> <mo>,</mo> <mn>3</mn> <mo>·</mo> <msup> <mn>10</mn> <mrow> <mo>−</mo> <mn>4</mn> </mrow> </msup> <mo>,</mo> <mo>…</mo> <mo>,</mo> <mn>3</mn> <mo>·</mo> <msup> <mn>10</mn> <mn>3</mn> </msup> </mfenced> </mrow> </semantics></math>.</p>
Full article ">Figure 10
<p>Full-resolution accuracy indexes for PanNet, with <math display="inline"><semantics> <mrow> <mi>α</mi> <mo>=</mo> <mn>0.03</mn> </mrow> </semantics></math> and <math display="inline"><semantics> <mrow> <mi>β</mi> <mo>∈</mo> <mfenced separators="" open="[" close="]"> <mn>3</mn> <mo>·</mo> <msup> <mn>10</mn> <mrow> <mo>−</mo> <mn>5</mn> </mrow> </msup> <mo>,</mo> <mn>3</mn> <mo>·</mo> <msup> <mn>10</mn> <mrow> <mo>−</mo> <mn>4</mn> </mrow> </msup> <mo>,</mo> <mo>…</mo> <mo>,</mo> <mn>3</mn> <mo>·</mo> <msup> <mn>10</mn> <mn>3</mn> </msup> </mfenced> </mrow> </semantics></math>.</p>
Full article ">Figure 11
<p>Full-resolution accuracy indexes for BDPN, with <math display="inline"><semantics> <mrow> <mi>α</mi> <mo>=</mo> <mn>0.03</mn> </mrow> </semantics></math> and <math display="inline"><semantics> <mrow> <mi>β</mi> <mo>∈</mo> <mfenced separators="" open="[" close="]"> <mn>3</mn> <mo>·</mo> <msup> <mn>10</mn> <mrow> <mo>−</mo> <mn>5</mn> </mrow> </msup> <mo>,</mo> <mn>3</mn> <mo>·</mo> <msup> <mn>10</mn> <mrow> <mo>−</mo> <mn>4</mn> </mrow> </msup> <mo>,</mo> <mo>…</mo> <mo>,</mo> <mn>3</mn> <mo>·</mo> <msup> <mn>10</mn> <mn>3</mn> </msup> </mfenced> </mrow> </semantics></math>.</p>
Full article ">
14 pages, 3435 KiB  
Article
Setting a Pedagogical Course: Four Modes Clarifying the Dynamics of Shared Religious Education
by Karlo Meyer
Religions 2024, 15(8), 992; https://doi.org/10.3390/rel15080992 - 16 Aug 2024
Viewed by 431
Abstract
On the level of fundamental didactic decisions and hermeneutic clarifications, this article examines the possible orientations of Shared Religious Education. The prerequisite for this is the assumption that in such lessons, the opportunity should be used to empower children and young people to [...] Read more.
On the level of fundamental didactic decisions and hermeneutic clarifications, this article examines the possible orientations of Shared Religious Education. The prerequisite for this is the assumption that in such lessons, the opportunity should be used to empower children and young people to become personally and creatively involved in teaching and learning when different denominations, religions, and worldviews come together in education. Against this background, four modes of possible activation are proposed as a structuring aid for didactic decisions: Pupils can (a) plan appropriate forms of encounter themselves and develop ways of dealing with mutually experienced foreignness and with bridges and gaps between traditions; (b) they can be activated to engage in existential discussions about ultimate questions, (c) they can carry out small-scale “research” projects into each other’s religious practices and concepts; and (d) they can get involved in joint (ethical, ecological, neighbourly) projects that have an impact on the region around the school that may also have global applications. The model of these four modes can be represented graphically and this helps to analyse and locate existing concepts and approaches to RE. The article concludes with a closer look at the underlying concept of religion and current research. Full article
(This article belongs to the Special Issue Shared Religious Education)
Show Figures

Figure 1

Figure 1
<p>Four modes of discovering and comprehending religious traditions.</p>
Full article ">Figure 2
<p>Four modes—horizontal transitions.</p>
Full article ">Figure 3
<p>Four modes—vertical transitions.</p>
Full article ">Figure 4
<p>Four modes locating Grimmitt’s and Hull’s “A Gift” approach.</p>
Full article ">Figure 5
<p>Four modes locating Jackson’s interpretative approach.</p>
Full article ">Figure 6
<p>Dynamics of double individual referentiality (<a href="#B36-religions-15-00992" class="html-bibr">Meyer 2021, p. 273</a>).</p>
Full article ">
23 pages, 1472 KiB  
Article
The Protection of Natural and Cultural Landscapes through Community-Based Tourism: The Case of the Indigenous Kamoro Tribe in West Papua, Indonesia
by Timika Aryani Anindhita, Seweryn Zielinski, Celene B. Milanes and Young-joo Ahn
Land 2024, 13(8), 1237; https://doi.org/10.3390/land13081237 - 8 Aug 2024
Viewed by 766
Abstract
Community-based tourism (CBT) aims to offer responsible travel to natural areas, conserving the environment, sustaining local communities’ well-being, and promoting environmental and cultural education. The long-term sustainability of CBT depends on its ability to enhance local livelihoods while protecting natural landscapes. For the [...] Read more.
Community-based tourism (CBT) aims to offer responsible travel to natural areas, conserving the environment, sustaining local communities’ well-being, and promoting environmental and cultural education. The long-term sustainability of CBT depends on its ability to enhance local livelihoods while protecting natural landscapes. For the Kamoro indigenous tribe in Papua, Indonesia, CBT offers a way to engage with the capitalist world on their own terms while preserving their customs, traditions, and ecocentric worldviews, and sharing them with tourists interested in their culture. However, as evidenced by many failed CBT initiatives, it is not always a desirable or viable path for development due to numerous barriers faced by communities and the potential negative impacts of tourism. Therefore, this study aimed to determine the Kamoro people’s attitudes towards tourism, the barriers to engaging in tourism, and their concerns about its impacts. Semi-structured and in-depth interviews were conducted with community members and local organizations. The results show that although local people view tourism as a viable economic alternative, they face significant challenges, including a lack of trained human resources, infrastructure, financial support, tourism knowledge, government backing, and cooperation among local stakeholders, among others. While tourism development does not always guarantee the protection of natural and cultural landscapes, a community-led initiative supported by the government can serve as a barrier against the engagement of less sustainable industries controlled by external agents, which could have far more serious negative consequences. Full article
(This article belongs to the Special Issue Landscape-Scale Sustainable Tourism Development)
Show Figures

Figure 1

Figure 1
<p>The interview process and themes.</p>
Full article ">Figure 2
<p>Area of the study.</p>
Full article ">
11 pages, 193 KiB  
Article
The Glories of Scripturally Informed Natural Law in Secular Education
by David H. Wenkel
Religions 2024, 15(8), 940; https://doi.org/10.3390/rel15080940 - 2 Aug 2024
Viewed by 799
Abstract
Today’s culture is becoming increasingly secularized and characterized by social fragmentation. Christian teachers in public schools should no longer expect to share the same worldview as their students. It is only natural to ask the question: can anything good come about in a [...] Read more.
Today’s culture is becoming increasingly secularized and characterized by social fragmentation. Christian teachers in public schools should no longer expect to share the same worldview as their students. It is only natural to ask the question: can anything good come about in a public-school classroom? This essay outlines a Christian vision for individual educators in public and pluralistic contexts that draws from a scripturally informed view of natural law. This paper answers this question in the affirmative: not only can it be good, but it can also be glorious, even if such glories are diminutive. Full article
12 pages, 288 KiB  
Article
“Fruit of the Earth”, “Fruit of the Vine”, “Work of Human Hands”: A Logiké Latreía towards a Transformative Response to the Ecological Crisis? Liturgical and Pastoral Implications
by Dorianne Buttigieg
Religions 2024, 15(8), 913; https://doi.org/10.3390/rel15080913 - 27 Jul 2024
Viewed by 823
Abstract
This paper aims to explore how liturgical celebration can serve as a transformative response to the contemporary ecological crisis and its consequences. This is inextricably bound to the importance of addressing the pastoral needs of individuals who are hurting due to their interactions [...] Read more.
This paper aims to explore how liturgical celebration can serve as a transformative response to the contemporary ecological crisis and its consequences. This is inextricably bound to the importance of addressing the pastoral needs of individuals who are hurting due to their interactions or lack thereof with the cosmos and the erosion of their relationship with nature in a technocratic consumerist society. Ritual, as a vehicle for personal and communal transformation, takes on heightened significance in a world wounded by ecological devastation. Rituals, often deeply embedded in cultural, religious, or personal practices, indeed have the capacity to facilitate personal transformation. They provide a framework for individuals to navigate life transitions, foster a sense of belonging, and connect with the overarching narrative. However, in an ecologically wounded world, where environmental degradation, climate change, and biodiversity loss are pressing concerns, the ramifications of ritual take on added significance and complexity. This paper seeks to address the urgency of the need to respond to this multifaceted crisis by paying attention to the pastoral needs of the individual and the community at large by redressing the real meaning of worship and reflecting on how, within a Christian tradition, this reconfiguration of worship can be provocative enough to instil change. However, this endeavour is not without inherent challenges and enduring questions. The pervasive influence of a technocratic worldview poses a significant threat not only to our relationship with the earth but also to the very essence of ritual itself. Can the liturgical experience, reaching its climax in the Eucharistic celebration, be truly a catalyst in asserting a proper relationship of humanity on various levels, which are concentric and, thus, dependant on each other, with humanity itself, with the cosmos, and with God? Full article
(This article belongs to the Special Issue Pastoral Theology in a Multi-Crisis Environment)
17 pages, 17604 KiB  
Article
Remote Sensing for Mapping Natura 2000 Habitats in the Brière Marshes: Setting Up a Long-Term Monitoring Strategy to Understand Changes
by Thomas Lafitte, Marc Robin, Patrick Launeau and Françoise Debaine
Remote Sens. 2024, 16(15), 2708; https://doi.org/10.3390/rs16152708 - 24 Jul 2024
Viewed by 423
Abstract
On a global scale, wetlands are suffering from a steady decline in surface area and environmental quality. Protecting them is essential and requires a careful spatialisation of their natural habitats. Traditionally, in our study area, species discrimination for floristic mapping has been achieved [...] Read more.
On a global scale, wetlands are suffering from a steady decline in surface area and environmental quality. Protecting them is essential and requires a careful spatialisation of their natural habitats. Traditionally, in our study area, species discrimination for floristic mapping has been achieved through on-site field inventories, but this approach is very time-consuming in these difficult-to-access environments. Usually, the resulting maps are also not spatially exhaustive and are not frequently updated. In this paper, we propose to establish a complete map of the study area using remote sensors and set up a long-term and regular observatory of environmental changes to monitor the evolution of a major French wetland. This methodology combines three dataset acquisition technologies, airborne hyperspectral and WorldView-3 multispectral images, supplemented by LiDAR images, which we compared to evaluate the difference in performances. To do so, we applied the Random Forest supervised classification methods using ground reference areas and compared the out-of-bag score (OOB score) as well as the matrix of confusion resulting from each dataset. Thirteen habitats were discriminated at level 4 of the European Nature Information System (EUNIS) typology, at a spatial resolution of around 1.2 m. We first show that a multispectral image with 19 variables produces results which are almost as good as those produced by a hyperspectral image with 58 variables. The experiment with different features also demonstrates that the use of four bands derived from LiDAR datasets can improve the quality of the classification. Invasive alien species Ludwigia grandiflora and Crassula helmsii were also detected without error which is very interesting when applied to these endangered environments. Therefore, since WV-3 images provide very good results and are easier to acquire than airborne hyperspectral data, we propose to use them going forward for the regular observation of the Brière marshes habitat we initiated. Full article
(This article belongs to the Special Issue Remote Sensing for the Study of the Changes in Wetlands)
Show Figures

Figure 1

Figure 1
<p>Location of the natural regional Park of Brière and the coverage for the two types of remote sensing images used in the study.</p>
Full article ">Figure 2
<p>Location of the 95 ROIs overlaid on the WorldView-3 image in false-colour composition (Red channel: band 6; Green channel: band 5; Blue channel: band 4).</p>
Full article ">Figure 3
<p>Methodology for classifying airborne hyperspectral and WV-3 multispectral images.</p>
Full article ">Figure 4
<p>Average contribution of each variable to RF accuracy. The points represent the Mean Decrease Gini value, indicative of the importance of each variable (<b>a</b>) for the 19-variable WorldView-3 image and (<b>b</b>) for the 58-variable hyperspectral image (only the first 29 are shown because the contributions of the following are close to zero).</p>
Full article ">Figure 5
<p>(<b>a</b>) WorldView-3 classification confusion matrix (<b>a</b>) for the 8 VNIR bands and 10 indices; (<b>b</b>) for the 8 VNIR bands and 10 indices, with the addition of the DHM.</p>
Full article ">Figure 6
<p>Habitat classification obtained (<b>a</b>) from the hyperspectral image and (<b>b</b>) from the WorldView-3 image. The size of the WV-3 image has been reduced because this was a test phase. Arrows and numbers on (<b>a</b>) correspond to <a href="#remotesensing-16-02708-f007" class="html-fig">Figure 7</a> pictures numbers.</p>
Full article ">Figure 7
<p>Pictures of some characteristic habitats of the Brière marshes. (<b>a</b>) Reed canary-grass ([Phalaris]) beds—EUNIS C.26; (<b>b</b>) beds of large [Carex] species—EUNIS D5.21; (<b>c</b>) Atlantic and sub-Atlantic humid meadows—EUNIS E3.41; (<b>d</b>) Willow carr and fen scrub (along a channel)—EUNIS F9.2; (<b>e</b>) Crassula helmsii beds; (<b>f</b>) <span class="html-italic">Ludwigia</span> sp. beds.</p>
Full article ">
16 pages, 4385 KiB  
Article
Emptiness/Nothingness as Explained by Ryu Yongmo (Tasŏk) (1890–1981) and Isaac Jacob Schmidt (1779–1847): A Cross-Cultural Study of the Integration of Asian Intellectual Heritage into the Worldview of Two Protestant Christians
by Kaspars Kļaviņš
Religions 2024, 15(7), 871; https://doi.org/10.3390/rel15070871 - 19 Jul 2024
Viewed by 689
Abstract
The concepts of emptiness and nothingness are extremely important in Eastern as well as Western spiritual traditions. In East Asia, they are relevant in Daoism, Confucianism (in the context of integrating Daoist ideas) and Buddhism (in Śūnyatā), while in the European Christian discourse [...] Read more.
The concepts of emptiness and nothingness are extremely important in Eastern as well as Western spiritual traditions. In East Asia, they are relevant in Daoism, Confucianism (in the context of integrating Daoist ideas) and Buddhism (in Śūnyatā), while in the European Christian discourse they are significant in the context of creatio ex nihilo, kenotic theories, individual self-emptying out of humility and Nihilianism. These concepts have formed and continue to form the basis of important intercultural interactions, influencing philosophical and scholarly discourse in both the “East” and “West” to the present day. This article compares the perception of emptiness/nothingness from two representatives of Protestantism: the Korean Christian philosopher Ryu Yongmo (1890–1981, pen name Tasŏk) and the Moravian missionary Isaac Jacob Schmidt (1779–1847), who was a pioneer of Buddhist studies in Europe. A comparison between Schmidt and Tasŏk is important, because tracing the evolution of the worldview of both thinkers reveals a great similarity in how they reconciled the spiritual heritage of Asia with the principles of Western Protestant Christianity despite their different backgrounds. It also could shed new light on the possibility of dialogue between Christianity and Buddhism, especially in the context of two major philosophical systems of Mahāyāna Buddhism: Yogācāra and Mādhyamika, which were once so important in East Asia. In addition, it is exactly the interpretation of emptiness/nothingness that forms the cornerstone of the analogy of the religious–philosophical ideas of the two thinkers compared in the article. Full article
16 pages, 4099 KiB  
Article
Multi-Frequency Spectral–Spatial Interactive Enhancement Fusion Network for Pan-Sharpening
by Yunxuan Tang, Huaguang Li, Guangxu Xie, Peng Liu and Tong Li
Electronics 2024, 13(14), 2802; https://doi.org/10.3390/electronics13142802 - 16 Jul 2024
Viewed by 424
Abstract
The objective of pan-sharpening is to effectively fuse high-resolution panchromatic (PAN) images with limited spectral information and low-resolution multispectral (LR-MS) images, thereby generating a fused image with a high spatial resolution and rich spectral information. However, current fusion techniques face significant challenges, including [...] Read more.
The objective of pan-sharpening is to effectively fuse high-resolution panchromatic (PAN) images with limited spectral information and low-resolution multispectral (LR-MS) images, thereby generating a fused image with a high spatial resolution and rich spectral information. However, current fusion techniques face significant challenges, including insufficient edge detail, spectral distortion, increased noise, and limited robustness. To address these challenges, we propose a multi-frequency spectral–spatial interaction enhancement network (MFSINet) that comprises the spectral–spatial interactive fusion (SSIF) and multi-frequency feature enhancement (MFFE) subnetworks. The SSIF enhances both spatial and spectral fusion features by optimizing the characteristics of each spectral band through band-aware processing. The MFFE employs a variant of wavelet transform to perform multiresolution analyses on remote sensing scenes, enhancing the spatial resolution, spectral fidelity, and the texture and structural features of the fused images by optimizing directional and spatial properties. Moreover, qualitative analysis and quantitative comparative experiments using the IKONOS and WorldView-2 datasets indicate that this method significantly improves the fidelity and accuracy of the fused images. Full article
(This article belongs to the Topic Computational Intelligence in Remote Sensing: 2nd Edition)
Show Figures

Figure 1

Figure 1
<p>Framework of the proposed MFSINet.</p>
Full article ">Figure 2
<p>Framework of the proposed SSIF.</p>
Full article ">Figure 3
<p>Framework of the proposed MFFE.</p>
Full article ">Figure 4
<p>Results images of the nine methods and GT on the IKONOS simulated dataset, as well as images of the absolute error.</p>
Full article ">Figure 5
<p>Resulting images of the nine methods and GT on the WV-2 simulated dataset, as well as images of the absolute error.</p>
Full article ">Figure 6
<p>Resulting images of the nine methods on the IKONOS real dataset. The lower part indicates the magnified details of the fused results (red and blue boxes).</p>
Full article ">Figure 7
<p>Resulting images of the nine methods on the WV-2 real dataset. The lower part indicates the magnified details of the fused results (red and blue boxes).</p>
Full article ">Figure 8
<p>Resulting images of different types of ablation experiments on the IKONOS (<b>top</b>) and WV-2 (<b>bottom</b>) simulated datasets, along with the absolute error images.</p>
Full article ">
17 pages, 9818 KiB  
Article
Constraining the Geometry of NeRFs for Accurate DSM Generation from Multi-View Satellite Images
by Qifeng Wan, Yuzheng Guan, Qiang Zhao, Xiang Wen and Jiangfeng She
ISPRS Int. J. Geo-Inf. 2024, 13(7), 243; https://doi.org/10.3390/ijgi13070243 - 8 Jul 2024
Viewed by 838
Abstract
Neural Radiance Fields (NeRFs) are an emerging approach to 3D reconstruction that use neural networks to reconstruct scenes. However, its applications for multi-view satellite photogrammetry, which aim to reconstruct the Earth’s surface, struggle to acquire accurate digital surface models (DSMs). To address this [...] Read more.
Neural Radiance Fields (NeRFs) are an emerging approach to 3D reconstruction that use neural networks to reconstruct scenes. However, its applications for multi-view satellite photogrammetry, which aim to reconstruct the Earth’s surface, struggle to acquire accurate digital surface models (DSMs). To address this issue, a novel framework, Geometric Constrained Neural Radiance Field (GC-NeRF) tailored for multi-view satellite photogrammetry, is proposed. GC-NeRF achieves higher DSM accuracy from multi-view satellite images. The key point of this approach is a geometric loss term, which constrains the scene geometry by making the scene surface thinner. The geometric loss term alongside z-axis scene stretching and multi-view DSM fusion strategies greatly improve the accuracy of generated DSMs. During training, bundle-adjustment-refined satellite camera models are used to cast rays through the scene. To avoid the additional input of altitude bounds described in previous works, the sparse point cloud resulting from the bundle adjustment is converted to an occupancy grid to guide the ray sampling. Experiments on WorldView-3 images indicate GC-NeRF’s superiority in accurate DSM generation from multi-view satellite images. Full article
Show Figures

Figure 1

Figure 1
<p>Overview of GC-NeRFs. GC-NeRFs use satellite images and corresponding satellite camera models to reconstruct scenes and generate accurate DSMs. Their key contributions include z-axis scene stretching, an occupancy grid converted from sparse point clouds, DSM fusion, and a geometric loss term for network training, which are shown in bold.</p>
Full article ">Figure 2
<p>Z-axis scene stretching. (<b>a</b>) The original satellite scene is flat. (<b>b</b>) The suitably stretched scene makes full use of multi-resolution hash encodings. (<b>c</b>) The over-stretched scene presents excessive hash conflicts.</p>
Full article ">Figure 3
<p>The architecture of the GC-NeRF network. The model receives 3D spatial coordinate <math display="inline"><semantics> <mrow> <mi>X</mi> </mrow> </semantics></math>, sun direction <math display="inline"><semantics> <mrow> <msub> <mrow> <mi>d</mi> </mrow> <mrow> <mi>s</mi> <mi>u</mi> <mi>n</mi> </mrow> </msub> </mrow> </semantics></math>, and viewing direction <math display="inline"><semantics> <mrow> <msub> <mrow> <mi>d</mi> </mrow> <mrow> <mi>v</mi> <mi>i</mi> <mi>e</mi> <mi>w</mi> </mrow> </msub> </mrow> </semantics></math> as inputs to predict the volume density <math display="inline"><semantics> <mrow> <msub> <mrow> <mi>σ</mi> </mrow> <mrow> <mi>X</mi> </mrow> </msub> </mrow> </semantics></math> and color <math display="inline"><semantics> <mrow> <msub> <mrow> <mi>c</mi> </mrow> <mrow> <mi>X</mi> </mrow> </msub> </mrow> </semantics></math> at <math display="inline"><semantics> <mrow> <mi>X</mi> </mrow> </semantics></math>.</p>
Full article ">Figure 4
<p>The converting and updating of the occupancy grid. (<b>a</b>) The point cloud is freely obtained from the bundle adjustment. (<b>a</b>,<b>b</b>) The point cloud is converted into a bit occupancy grid. (<b>b</b>,<b>c</b>) The bit grid cells are classified by the float grid cells. (<b>c</b>,<b>d</b>) The float grid cells are updated by the <math display="inline"><semantics> <mrow> <mi>α</mi> </mrow> </semantics></math> value predicted from the network.</p>
Full article ">Figure 5
<p>(<b>a</b>) At the same camera parameter error angle <math display="inline"><semantics> <mrow> <mi>θ</mi> </mrow> </semantics></math>, the geometric error is greater in the satellite scene. (<b>b</b>) Without <math display="inline"><semantics> <mrow> <msub> <mrow> <mi>L</mi> <mi>o</mi> <mi>s</mi> <mi>s</mi> </mrow> <mrow> <mi>g</mi> </mrow> </msub> </mrow> </semantics></math>, the sample weight distribution is scattered around the true depth, resulting in significant errors in depth estimation. By contrast, the weight distribution is compactly around the true depth.</p>
Full article ">Figure 6
<p>The relativity between positive DSM errors in merged point clouds and the root mean square error (RMSE) of multi-view DSMs. The predicted elevation is greater than the actual elevation in most areas with a large elevation standard deviation.</p>
Full article ">Figure 7
<p>Visualization of 3D models derived by superimposing DSMs onto images. The DSMs and images are generated by GC-NeRFs.</p>
Full article ">Figure 8
<p>Images rendered by S-NeRFs, Sat-NeRFs, and GC-NeRFs. (<b>a</b>,<b>b</b>) Sat-NeRFs are robust to transient phenomenon such as cars. (<b>c</b>,<b>d</b>) GC-NeRFs render clearer images.</p>
Full article ">Figure 9
<p>Visualization of lidar, S-NeRFs, Sat-NeRFs, and GC-NeRF DSMs. Areas marked by water and building changes are masked. (<b>a</b>,<b>b</b>) The DSM rendered by a GC-NeRF shows that the road is uneven compared to lidar DSM. (<b>c</b>,<b>d</b>) The GC-NeRF DSM displays sharper building edges than the Sat-NeRF DSM. (<b>e</b>,<b>f</b>) The DSM quality rendered by the GC-NeRF is superior to that of the S-NeRF.</p>
Full article ">Figure 10
<p>The MAE of DSMs under different <math display="inline"><semantics> <mrow> <msub> <mrow> <mi>s</mi> </mrow> <mrow> <mi>z</mi> </mrow> </msub> </mrow> </semantics></math>. Low MAE indicates high DSM accuracy, and the best <math display="inline"><semantics> <mrow> <msub> <mrow> <mi mathvariant="bold-italic">s</mi> </mrow> <mrow> <mi mathvariant="bold-italic">z</mi> </mrow> </msub> </mrow> </semantics></math> value is around 0.8.</p>
Full article ">
21 pages, 4350 KiB  
Article
A Comparison of Satellite Imagery Sources for Automated Detection of Retrogressive Thaw Slumps
by Heidi Rodenhizer, Yili Yang, Greg Fiske, Stefano Potter, Tiffany Windholz, Andrew Mullen, Jennifer D. Watts and Brendan M. Rogers
Remote Sens. 2024, 16(13), 2361; https://doi.org/10.3390/rs16132361 - 27 Jun 2024
Viewed by 1031
Abstract
Retrogressive thaw slumps (RTS) are a form of abrupt permafrost thaw that can rapidly mobilize ancient frozen soil carbon, magnifying the permafrost carbon feedback. However, the magnitude of this effect is uncertain, largely due to limited information about the distribution and extent of [...] Read more.
Retrogressive thaw slumps (RTS) are a form of abrupt permafrost thaw that can rapidly mobilize ancient frozen soil carbon, magnifying the permafrost carbon feedback. However, the magnitude of this effect is uncertain, largely due to limited information about the distribution and extent of RTS across the circumpolar region. Although deep learning methods such as Convolutional Neural Networks (CNN) have shown the ability to map RTS from high-resolution satellite imagery (≤10 m), challenges remain in deploying these models across large areas. Imagery selection and procurement remain one of the largest challenges to upscaling RTS mapping projects, as the user must balance cost with resolution and sensor quality. In this study, we compared the performance of three satellite imagery sources that differed in terms of sensor quality and cost in predicting RTS using a Unet3+ CNN model and identified RTS characteristics that impact detectability. Maxar WorldView imagery was the most expensive option, with a ground sample distance of 1.85 m in the multispectral bands (downloaded at 4 m resolution). Planet Labs PlanetScope imagery was a less expensive option with a ground sample distance of approximately 3.0–4.2 m (downloaded at 3 m resolution). Although PlanetScope imagery was downloaded at a higher resolution than WorldView, the radiometric footprint is around 10–12 m, resulting in less crisp imagery. Finally, Sentinel-2 imagery is freely available and has a 10 m resolution. We used 756 RTS polygons from seven sites across Arctic Canada and Siberia in model training and 63 RTS polygons in model testing. The mean IoU of the validation and testing data sets were 0.69 and 0.75 for the WorldView model, 0.70 and 0.71 for the PlanetScope model, and 0.66 and 0.68 for the Sentinel-2 model, respectively. The IoU of the RTS class was nonlinearly related to the RTS Area, showing a strong positive correlation that attenuated as the RTS Area increased. The models were better able to predict RTS that appeared bright on a dark background and were less able to predict RTS that had higher plant cover, indicating that bare ground was a primary way the models detected RTS. Additionally, the models performed less well in wet areas or areas with patchy ground cover. These results indicate that all imagery sources tested here were able to predict larger RTS, but higher-quality imagery allows more accurate detection of smaller RTS. Full article
(This article belongs to the Special Issue Advances in Remote Sensing in Glacial and Periglacial Geomorphology)
Show Figures

Graphical abstract

Graphical abstract
Full article ">Figure 1
<p>Map of the locations of RTS features used in model testing. The Arctic Circle is shown as a dashed line. Regions used only in model training are shown in gray, while all other regions, which were used in model training and testing, are coded by color.</p>
Full article ">Figure 2
<p>RGB imagery and prediction outlines for a subset of the 63 RTS testing features. The quality of the prediction relative to feature size is indicated by the color of the prediction outline. The RTS feature of interest is shown in light gray. In cases where there are multiple RTS features within a tile, the other RTS features are shown in a thinner light gray line, and the mask area is shown in a dashed light gray line. Columns show the different imagery sources, and rows show different RTS features, which were selected to display differences in the predictions and imagery. Rows labeled “Good Prediction” show predictions that had some of the highest IoU scores. Rows labeled “Bright RTS” show examples of how bright RTS on a dark background were predicted well in the PlanetScope imagery. The row labeled “Variable Performance” shows predictions that varied significantly among imagery types. The row labeled “Green RTS” shows an RTS with a high plant cover that was undetected in all models. The rows labeled “Small RTS” show some of the smaller RTS features, which were often undetected. The row labeled “Snow” shows one example of how snow in the WorldView image was inaccurately labeled as an RTS feature.</p>
Full article ">Figure 3
<p>Histograms of the IoU scores of the RTS class across the testing dataset. Mean and median IoU scores are shown as solid and dashed lines, respectively.</p>
Full article ">Figure 4
<p>The relationship between RTS Area and RTS IoU. Each point represents the prediction for a single RTS feature. The nonlinear relationship is shown as a solid line, and 50% confidence intervals are shown in light gray. RTS feature predictions that fell outside of the 50% confidence interval were considered of higher or lower prediction quality than expected, and this is indicated by point color.</p>
Full article ">Figure 5
<p>Prediction quality across all imagery types for each RTS feature in the testing dataset. RTS features tended to have the same or similar prediction qualities across imagery types, indicating that there were characteristics of RTS features that made them more or less detectable across imagery types.</p>
Full article ">Figure 6
<p>The difference in input data values between RTS and non-water background (BG) pixels (RTS—BG) across prediction quality classes. The points were calculated by first taking the difference in mean pixel values (z-score) between RTS and non-water background (BG) pixels on a tile-by-tile basis and then averaging this value across all 63 testing tiles. The error bars show the standard deviation across tiles. Z-scores were calculated using all pixel values, including water pixels. Relative elevation and shaded relief are not included, as there were no discernable patterns across classes. Statistically different groups are indicated with lines between the two classes and a label for the level of significance (<span class="html-italic">p</span> &lt; 0.1: ‘.’, <span class="html-italic">p</span> &lt; 0.05: ‘*’).</p>
Full article ">Figure 7
<p>Prediction quality across geographic regions. The percentage of predictions that were high, expected, and low is shown on the Y-axis. The total count of RTS features within each region is indicated at the top of the bars. Banks Island and the Yamal/Gydan region had the highest percentage of low-quality predictions.</p>
Full article ">Figure 8
<p>Frequency distributions of RTS Area and RTS shape across regions. Region is indicated with the fill color. RTS Area is shown on a log scale. Smaller RTS shape values indicate less compact shapes, and larger values indicate more compact or circular shapes.</p>
Full article ">
27 pages, 10814 KiB  
Article
UPGAN: An Unsupervised Generative Adversarial Network Based on U-Shaped Structure for Pansharpening
by Xin Jin, Yuting Feng, Qian Jiang, Shengfa Miao, Xing Chu, Huangqimei Zheng and Qianqian Wang
ISPRS Int. J. Geo-Inf. 2024, 13(7), 222; https://doi.org/10.3390/ijgi13070222 - 26 Jun 2024
Viewed by 1051
Abstract
Pansharpening is the fusion of panchromatic images and multispectral images to obtain images with high spatial resolution and high spectral resolution, which have a wide range of applications. At present, methods based on deep learning can fit the nonlinear features of images and [...] Read more.
Pansharpening is the fusion of panchromatic images and multispectral images to obtain images with high spatial resolution and high spectral resolution, which have a wide range of applications. At present, methods based on deep learning can fit the nonlinear features of images and achieve excellent image quality; however, the images generated with supervised learning approaches lack real-world applicability. Therefore, in this study, we propose an unsupervised pansharpening method based on a generative adversarial network. Considering the fine tubular structures in remote sensing images, a dense connection attention module is designed based on dynamic snake convolution to recover the details of spatial information. In the stage of image fusion, the fusion of features in groups is applied through the cross-scale attention fusion module. Moreover, skip layers are implemented at different scales to integrate significant information, thus improving the objective index values and visual appearance. The loss function contains four constraints, allowing the model to be effectively trained without reference images. The experimental results demonstrate that the proposed method outperforms other widely accepted state-of-the-art methods on the QuickBird and WorldView2 data sets. Full article
(This article belongs to the Special Issue Advances in AI-Driven Geospatial Analysis and Data Generation)
Show Figures

Figure 1

Figure 1
<p>Network architecture of UPGAN.</p>
Full article ">Figure 2
<p>Slender tubular structures in remote sensing images.</p>
Full article ">Figure 3
<p>The structure of DCAM.</p>
Full article ">Figure 4
<p>The framework of MSDFL.</p>
Full article ">Figure 5
<p>The structure of SSA.</p>
Full article ">Figure 6
<p>The channel attention mechanism in SSA.</p>
Full article ">Figure 7
<p>The framework of CSAF.</p>
Full article ">Figure 8
<p>Frameworks of the two discriminators: (<b>a</b>) spectral discriminator and (<b>b</b>) spatial discriminator.</p>
Full article ">Figure 9
<p>Qualitative comparison of UPGAN with 10 counterparts on a sample from the QB data set. (<b>a</b>) Brovey [<a href="#B14-ijgi-13-00222" class="html-bibr">14</a>]. (<b>b</b>) MTF_GLP_HPM [<a href="#B22-ijgi-13-00222" class="html-bibr">22</a>]. (<b>c</b>) PCA [<a href="#B13-ijgi-13-00222" class="html-bibr">13</a>]. (<b>d</b>) SFIM [<a href="#B15-ijgi-13-00222" class="html-bibr">15</a>]. (<b>e</b>) SR-D [<a href="#B29-ijgi-13-00222" class="html-bibr">29</a>]. (<b>f</b>) ZeRGAN [<a href="#B52-ijgi-13-00222" class="html-bibr">52</a>]. (<b>g</b>) UCGAN [<a href="#B51-ijgi-13-00222" class="html-bibr">51</a>]. (<b>h</b>) LDPNet [<a href="#B41-ijgi-13-00222" class="html-bibr">41</a>]. (<b>i</b>) PanGAN [<a href="#B47-ijgi-13-00222" class="html-bibr">47</a>]. (<b>j</b>) ZS-Pan [<a href="#B44-ijgi-13-00222" class="html-bibr">44</a>]. (<b>k</b>) UPGAN. (<b>l</b>) GT.</p>
Full article ">Figure 10
<p>The residual images between the pansharpened results and reference images in <a href="#ijgi-13-00222-f009" class="html-fig">Figure 9</a>. (<b>a</b>) Brovey [<a href="#B14-ijgi-13-00222" class="html-bibr">14</a>]. (<b>b</b>) MTF_GLP_HPM [<a href="#B22-ijgi-13-00222" class="html-bibr">22</a>]. (<b>c</b>) PCA [<a href="#B13-ijgi-13-00222" class="html-bibr">13</a>]. (<b>d</b>) SFIM [<a href="#B15-ijgi-13-00222" class="html-bibr">15</a>]. (<b>e</b>) SR-D [<a href="#B29-ijgi-13-00222" class="html-bibr">29</a>]. (<b>f</b>) ZeRGAN [<a href="#B52-ijgi-13-00222" class="html-bibr">52</a>]. (<b>g</b>) UCGAN [<a href="#B51-ijgi-13-00222" class="html-bibr">51</a>]. (<b>h</b>) LDPNet [<a href="#B41-ijgi-13-00222" class="html-bibr">41</a>]. (<b>i</b>) PanGAN [<a href="#B47-ijgi-13-00222" class="html-bibr">47</a>]. (<b>j</b>) ZS-Pan [<a href="#B44-ijgi-13-00222" class="html-bibr">44</a>]. (<b>k</b>) UPGAN. (<b>l</b>) GT.</p>
Full article ">Figure 11
<p>Qualitative comparison of UPGAN with 10 counterparts on a typical satellite image pair from the QB data set at full resolution. (<b>a</b>) Brovey [<a href="#B14-ijgi-13-00222" class="html-bibr">14</a>]. (<b>b</b>) MTF_GLP_HPM [<a href="#B22-ijgi-13-00222" class="html-bibr">22</a>]. (<b>c</b>) PCA [<a href="#B13-ijgi-13-00222" class="html-bibr">13</a>]. (<b>d</b>) SFIM [<a href="#B15-ijgi-13-00222" class="html-bibr">15</a>]. (<b>e</b>) SR-D [<a href="#B29-ijgi-13-00222" class="html-bibr">29</a>]. (<b>f</b>) ZeRGAN [<a href="#B52-ijgi-13-00222" class="html-bibr">52</a>]. (<b>g</b>) UCGAN [<a href="#B51-ijgi-13-00222" class="html-bibr">51</a>]. (<b>h</b>) LDPNet [<a href="#B41-ijgi-13-00222" class="html-bibr">41</a>]. (<b>i</b>) PanGAN [<a href="#B47-ijgi-13-00222" class="html-bibr">47</a>]. (<b>j</b>) ZS-Pan [<a href="#B44-ijgi-13-00222" class="html-bibr">44</a>]. (<b>k</b>) UPGAN. (<b>l</b>) PAN. (<b>m</b>) MS.</p>
Full article ">Figure 12
<p>Qualitative comparison of UPGAN with 10 counterparts on a sample from the WV2 data set. (<b>a</b>) Brovey [<a href="#B14-ijgi-13-00222" class="html-bibr">14</a>]. (<b>b</b>) MTF_GLP_HPM [<a href="#B22-ijgi-13-00222" class="html-bibr">22</a>]. (<b>c</b>) PCA [<a href="#B13-ijgi-13-00222" class="html-bibr">13</a>]. (<b>d</b>) SFIM [<a href="#B15-ijgi-13-00222" class="html-bibr">15</a>]. (<b>e</b>) SR-D [<a href="#B29-ijgi-13-00222" class="html-bibr">29</a>]. (<b>f</b>) ZeRGAN [<a href="#B52-ijgi-13-00222" class="html-bibr">52</a>]. (<b>g</b>) UCGAN [<a href="#B51-ijgi-13-00222" class="html-bibr">51</a>]. (<b>h</b>) LDPNet [<a href="#B41-ijgi-13-00222" class="html-bibr">41</a>]. (<b>i</b>) PanGAN [<a href="#B47-ijgi-13-00222" class="html-bibr">47</a>]. (<b>j</b>) ZS-Pan [<a href="#B44-ijgi-13-00222" class="html-bibr">44</a>]. (<b>k</b>) UPGAN. (<b>l</b>) GT.</p>
Full article ">Figure 13
<p>The residual images between the pansharpened results and reference images in <a href="#ijgi-13-00222-f012" class="html-fig">Figure 12</a>. (<b>a</b>) Brovey [<a href="#B14-ijgi-13-00222" class="html-bibr">14</a>]. (<b>b</b>) MTF_GLP_HPM [<a href="#B22-ijgi-13-00222" class="html-bibr">22</a>]. (<b>c</b>) PCA [<a href="#B13-ijgi-13-00222" class="html-bibr">13</a>]. (<b>d</b>) SFIM [<a href="#B15-ijgi-13-00222" class="html-bibr">15</a>]. (<b>e</b>) SR-D [<a href="#B29-ijgi-13-00222" class="html-bibr">29</a>]. (<b>f</b>) ZeRGAN [<a href="#B52-ijgi-13-00222" class="html-bibr">52</a>]. (<b>g</b>) UCGAN [<a href="#B51-ijgi-13-00222" class="html-bibr">51</a>]. (<b>h</b>) LDPNet [<a href="#B41-ijgi-13-00222" class="html-bibr">41</a>]. (<b>i</b>) PanGAN [<a href="#B47-ijgi-13-00222" class="html-bibr">47</a>]. (<b>j</b>) ZS-Pan [<a href="#B44-ijgi-13-00222" class="html-bibr">44</a>]. (<b>k</b>) UPGAN. (<b>l</b>) GT.</p>
Full article ">Figure 14
<p>Qualitative comparison of UPGAN with 10 counterparts on a typical satellite image pair from the QB data set at full resolution. (<b>a</b>) Brovey [<a href="#B14-ijgi-13-00222" class="html-bibr">14</a>]. (<b>b</b>) MTF_GLP_HPM [<a href="#B22-ijgi-13-00222" class="html-bibr">22</a>]. (<b>c</b>) PCA [<a href="#B13-ijgi-13-00222" class="html-bibr">13</a>]. (<b>d</b>) SFIM [<a href="#B15-ijgi-13-00222" class="html-bibr">15</a>]. (<b>e</b>) SR-D [<a href="#B29-ijgi-13-00222" class="html-bibr">29</a>]. (<b>f</b>) ZeRGAN [<a href="#B52-ijgi-13-00222" class="html-bibr">52</a>]. (<b>g</b>) UCGAN [<a href="#B51-ijgi-13-00222" class="html-bibr">51</a>]. (<b>h</b>) LDPNet [<a href="#B41-ijgi-13-00222" class="html-bibr">41</a>]. (<b>i</b>) PanGAN [<a href="#B47-ijgi-13-00222" class="html-bibr">47</a>]. (<b>j</b>) ZS-Pan [<a href="#B44-ijgi-13-00222" class="html-bibr">44</a>]. (<b>k</b>) UPGAN. (<b>l</b>) PAN. (<b>m</b>) MS.</p>
Full article ">Figure 15
<p>The connection structure in the generator.</p>
Full article ">Figure 16
<p>Average quantitative results for the number of sub-modules in DCAM on the QB data set. (<b>a</b>) PSNR. (<b>b</b>) SCC. (<b>c</b>) SAM. (<b>d</b>) ERGAS. (<b>e</b>) UIQI.</p>
Full article ">
Back to TopTop