Special Issue "Multi-Source Geoinformation Fusion"
A special issue of ISPRS International Journal of Geo-Information (ISSN 2220-9964).
Deadline for manuscript submissions: 1 May 2019
Twenty years ago, several HAPEX (Hydrologic and Atmospheric Pilot Experiments) and the Alpilles- ReSeDA (Remote Sensing Data Assimilation) were the first large-scale international experiments to specifically explore the fusion of multi-source geoinformation. That geoinformation was almost exclusively made up of satellite and aerial imagery, but what was then called data assimilation, was already a complex operation between data collected at different scales, from different sensors, involving physics "transfer models" in order to "fusing" these data, if evaluated as similar enough.
What has changed in this research field, since then?
Nowadays, the range of sources is considerably larger. Several dozen satellites are observing our planet, from the continental scale, down to streets and neighborhoods. The vision is not just flat: LiDAR or UAVs pictures deliver a 3D vision. Time of delivery is no longer an issue: IoT sensors deliver real-time environmental data, vehicle traffic data, etc.
The number of data sources is not the only factor that has changed, variety also has increased a great deal. Automated cartography and remote sensing are no longer two realms ignoring each other, as was the case 20 years ago. Handling pixel and vector data, together, is no longer a handicap in designing geospatial information. Software development, knowledge representation, and reasoning tools have greatly evolved, allowing for the smooth integration of (ontologically) different sources.
Volume and variety have increased, and velocity has changed radically. Large data files are no longer mailed as digital tapes. You can download data, or you can process it using web services, and download only the results. You can process raw data thoroughly, using your own code, or rely on web applications that apply your chosen corrections and models. Will these models soon be determined by artificial intelligence? Will web services be choosing the models that are most relevant for your applications?
These questions are on the table today; about where geoinformation fusion research and development is heading.
We invite you to contribute to this Special Issue, which could be a big step forward in research on multi-source geoinformation fusion, summing up its different facets and application domains.
Several ISPRS Work Group (WG) are actively working on related topics: WG.III.6 (fusion), ICWG.III/IVb (Remote Sensing quality) and WG.IV.3 (quality), as well as WG.III.7, in the application domain of land-cover/use, to cite a few. National space agencies are designing infrastructure for the large-scale delivery of spatial data, and global Earth observation system of systems (GEOSS) is now a mature international organization devoted to provisioning multi-source data. In addition, there is also an active research community on the more theoretical aspects of geospatial information fusion and revision.
Therefore, we encourage contribution on (but not limited to) the following themes:
- Theories, frameworks, and paradigms of geospatial information fusion
- Fusion background improvement: Geoinformation metamodelling, model integration, and uniform knowledge representation
- Big data's specific impact on geoinformation fusion (not just volume and access)
- Artificial intelligence (AI)/machine learning in relation with geoinformation fusion
- Advances in the integration of new sensor sources with classical ones (LiDAR, UAVs imagery, IoT environmental or mobility data, volunteer information, etc.)
- Applications making intensive use of fusion: Agricultural systems, land use, urban development, etc.
- Geospatial education and capacity-building efforts with geoinformation fusion
- Ethical and societal considerations (privately owned data, citizen participation, data integrity variability)
Manuscripts for this Special Issue should be submitted by 30 October 2018, for timely selection, peer-review, and publication in this open access Special Issue of IJGI.Prof. Robert Jeansoulin
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.
The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.
FusionImage: An R Package for Pan-Sharpening Images in Open-Source Software
Pre-departamental Unit of Civil Engineering, Universidad Politécnica de Cartagena; [email protected]
Image pan-sharpening is the process by which a set of multispectral layers are fused with a panchromatic layer with higher spatial resolution and whose spectral width encompasses those of the multispectral layers. The objective is to obtain a product with the spatial resolution of the panchromatic and the spectral resolution of the multispectral. Several algorithms have been proposed to perform such fusion whereas other algorithms have been used to evaluate the resulting layers. The objective of this paper is to use three pan-sharpening algorithms: High Pass Filter, Principal Component Analysis and Gram-Schmidt and evaluate their results with three indices: the universal image quality index (Q index), the ERGAS index and the Spatial ERGAS index. A secondary objective is to produce an R package called fusionImage implementing the six aforementioned techniques.
From a qualitative point of view, the images with higher spatial ratio between the multispectral resolution and the panchromatic resolution (QuickBird, Ikonos and Natmur-08, an image obtained with an aerotransported sensor, with spatial resolution ratio ranging from 4 to 4.4) present better results than those obtained with Landsat 7 and 8 whose spatial resolution ratio is two. These two last sensor presented greater colour distortion. However, the best quantitative results were obtained with Landsat-7 and Landsat-8 images whichever the fusion method used. This contrasts reflects the importance of taking into account both evaluation approaches. So, there is no method a priori, better that the others; the results will depend on the characteristics of the sensors, but also on the atmospherics conditions and peculiarities of the study sites.
Another result of this research is an R package called fusionImage, which implements all the fusion and validation algorithms used in this research. When comparing the results obtained with this software with those of proprietary software, our software obtained, in general, better results.