In 2014 ISPRS has introduced the so called Scientific Initiative to support projects of interest to the ISPRS community. Call are normally launched in autum of evenly numbered years. Details of the regulations an be found at http://www.isprs.org/documents/orangebook/app9a.aspx.
Reports of previous calls are available at
ISPRS Scientific Initiatives 2023
For 2023 competition, the Council has approved the seven selected projects for funding. Council would like to take thank all applicants who responded this Call for Proposals. The following provides a brief summary of the above-awarded projects together with the information of their principle investigator(s) and co-investigator(s):
|Benchmarking of absolute and relative positioning solutions under GNSS denied environments for mobile geomatics
||Yunsheng Wang & Liang Chen
|Publishing dataset guideline: gaps and trends in research data management in the ISPRS community
||I & IV
|BeBaOI: Benchmark and Baseline Methods for determining Overlapping Images
||Xin Wang & Yu Feng
||II & I
|NAUTILUS uNder And throUgh waTer datasets for geospatIaL stUdieS
||II & I
|Benchmarking of publicly available software solutions for close-range point cloud processing of forest ecosystems
||Carlos Cabo & Xinlian Liang
|Geospatial data base for exposomics
|Integrating IndoorGML with outdoors: Automatic routing graph generation for indoor‐outdoor transitional space for seamless navigation
||IV & II
Benchmarking of absolute and relative positioning solutions under GNSS denied environments for mobile geomatics
PIs: Y. Wang, Finnish Geospatial Research Institute, Finland, & L. Chen, Wuhan University, China
CoIs: H. Yao (Wuhan University, China), X. Wang (Wuhan University, China), H. Qi (Wuhan University, China), T. Hakala (Finnish Geospatial Research Institute, Finland), J. Muhojoki (Finnish Geospatial Research Institute, Finland), J. Wang (China University of Mining and Technology, China), Z. Liu (Chinese Academy of Surveying and Mapping, China)
Accurate localization and positioning in global navigation satellite system (GNSS) denied environments, such as indoor/underground spaces, urban canyon, and forests, has been confronted with profound challenges because of the great complexity of perception tasks. Different sensors, algorithms, and combinations of those have been developed in past decades, which provide a great variety of possible solutions that deliver different positioning accuracies. However, a rigorous evaluation of the positioning accuracy of mainstream solutions is missing, mainly because of the difficulties in acquiring reliable ground truth for referencing and the lack of comparable test/application conditions. A comprehensive benchmarking will be carried out in this project based on the comparisons of solutions that consist of different combinations of a few most used positioning technologies, including inertial measurement unit (IMU), ultra-wideband (UWB), camera, light detection and ranging (lidar), and radio detection and ranging (radar), as well as emerging technologies, such as 5G, and sound positioning. High-precision millimeter-level survey standard ground truth references will be acquired for indoor and outdoor test sites and applied for the evaluations, to assist quantitative benchmarks about the robustness and the positioning accuracies of different solutions using absolute and relative sensors. The outcomes of this project will help both researchers and practitioners to learn their capacities and to select suitable sensors and solutions in their applications. The outcomes of the project will be reported as conference papers in workshops and as research papers in open-access format, to broadcast the project findings to a wide audience.
Publishing dataset guideline: gaps and trends in research data management in the ISPRS community
PI: D. Iwaszczuk (Technical University Darmstadt, Germany)
The availability of data is becoming more and more important in many fields of research, however freely available and easy to find datasets are still scarce. This creates the need for a common dataset publication principle to improve interoperability and reusability. The FAIR principle is able to help with these goals, as well as enable better searching and easier access for scientific data. In summary, we are developing a guideline based on the aforementioned FAIR principle to help with the publication of new datasets and standardize the processes. These processes include the selection of metadata, e.g. keywords, which are applied to newly released datasets, but can be adapted for older datasets as well, and the selection of a suitable dataset repository. Therefore, it is our goal to analyze the current metadata used in the ISPRS community and create a metadata scheme based on these findings. In addition, we aim to determine a suitable dataset repository for the specific use-case of datasets for the photogrammetry and remote sensing domain. Ultimately, it is our goal to provide the tools to make publishing as easy and uniform as possible and, by that, also improve the discoverability of useful datasets for the ISPRS community.
Figure 1. Relationship between metadata, data repositories and the Bemeda search tool. Within this project a guideline for the publication of datasets is primarily being written, which is compliant with the FAIR principle.
BeBaOI: Benchmark and Baseline Methods for determining Overlapping Images
PIs: X. Wang, Wuhan University, China, & Y. Feng, Technical University of Munich, Germany
CoIs: R. Hänsch (German Aerospace Center (DLR), Germany), Z. Zhan (Wuhan University, China), M. Li (Nanjing University of Aeronautics and Astronautics, China), M. Gruber (Vexcel Imaging GmbH, Austria), C. Heipke (Leibniz University Hannover, Germany)
Figure 1. The graphical abstract of BeBaOI.
Nowadays, images can be easily accessed with very little effort (such as, crowdsourced images from social media, e.g., Flickr, Instagram etc.). Although these are typically not for photogrammetric purposes, it is often of great interest to carry out 3D reconstruction or measuring tasks on these abundant pictures.
The starting step of 3D reconstruction from images is to find overlapping image pairs for image matching, which is computationally expensive particularly for very large set of unordered images. In recent years, deep learning has achieved great success in many fields including photogrammetry and remote sensing. It can also be used to address the problem described above.
The main goals of this project are:
- To generate and publish a benchmark with overlapping image pairs from various datasets (such as, crowdsourced, close-range and aerial images etc.) which can be used: (a) for model training when researchers try to explore a deep learning-based method and (b) for the evaluation of relevant methods from computer vision, robotics and photogrammetry;
- To investigate an end-to-end network architecture based on CNN to predict whether two given images overlap or not;
- Based on the global features extracted from the trained model, to develop vocabulary tree indexing structures which act as a dictionary for fast and accurate retrieval of the target image’s nearest neighbours;
The network architecture investigated, the vocabulary tree developed and the corresponding webinars will be made freely available to everyone in the ISPRS community and researchers in related fields.
NAUTILUS uNder And throUgh waTer datasets for geospatIaL stUdieS
PI: E. Nocerino, University of Sassari, Italy
CoIs: F. Menna (Bruno Kessler Foundation, Italy), D. Skarlatos (Cyprus University of Technology, Cyprus), C. Balletti (Università Iuav di Venezia, Italy), G. Mandlburger (TU Wien, Austria), P. Agrafiotis (National Technical University of Athens, Greece), F. Chiabrando (Politecnico di Torino, Italy), Andrea Lingua (Politecnico di Torino, Italy)
Figure 1. The Nautilus project graphical abstract.
Benchmark datasets have become increasingly widespread in the scientific community as a method of comparison, validation and improvement of theories and techniques, thanks also to more and more affordable means for sharing. While this holds true for test sites and data collected above the water, publicly accessible benchmark activities for geospatial analyses in the underwater environment are not very common. Among several reasons, the application of geomatic techniques underwater is still challenging and very expensive, especially when dealing with deep water and offshore operations. Moreover, benchmarking requires ground truth data for which, in water, several open issues exist, both geometric and radiometric. Recognising this scientific and technological challenge, the NAUTILUS (uNder And throUgh waTer datasets for geospatIaL stUdieS) project wants to set up a series of preparatory activities leading to the creation of a multi-sensor/cross-modality benchmark dataset. The project will therefore be structured into the following three activities (Figure 1): (i) conducting a survey through a questionnaire and interviews to collect actual needs and gaps in through and under the water geospatial applications, (ii) launching a unique publicly available database collecting already existing datasets scattered across the web and literature, (iii) designing and identifying proper test site(s) and methodologies to deliver to the extended underwater community a brand-new multi-sensor/cross-modality benchmark dataset. The outputs of the project will benefit researchers and practitioners in underwater measurements related domains, as they will have access to a comprehensive tool providing a synthesis of open questions and data already available. Moreover, past research efforts to collect and publish datasets will receive additional credit and visibility. Finally, the design of a brand-new multi-sensor/cross-modality benchmark dataset will respond in a proven manner to the needs and gaps brought to light by the community itself.
Benchmarking of publicly available software solutions for close-range point cloud processing of forest ecosystems
PIs: C. Cabo, University of Oviedo, Spain, & Xinlian Liang, Wuhan University, China
CoIs: K. Calders (Ghent University, Belgium), M. Eichhorn (University College Cork, Ireland), M. Hallous (TU Wien, Austria), E. Lines (University of Cambridge, UK), S. Marselis (Leiden University, Netherlands), M. Mokroš (Czech University of Life Sciences, Czech Republic), A. Murtiyoso (ETH Zürich, Switzerland), S. Puliti (NIBIO, Norway), N. Saarinen (University of Eastern Finland, Finland), K. Stereńczak (Forest Research Institute, Poland), C. Torresan (CNR, Italy), Y. Wang (Finnish Geospatial Research Institute, Finland)
Although recent advances in close-range 3D technologies have greatly increased the availability of data for forest measurements, standardised procedures for processing and extracting information from forest point clouds are lacking. A large research community is working on algorithms that can automate forest mapping and monitoring from close-range point clouds.
Publicly available implementations of such algorithms are still scarce, however, and there is no comprehensive resource of either available software or rigorous comparison of their performance. This means that potential users face a lack of clarity on the different options available, or their pros and cons.
This project aims to compile and evaluate the performance of existing software, algorithms and implementations designed for forest mapping and monitoring with terrestrial point clouds. It will specifically focus on publicly available software solutions, regardless of their license type (free, open-source, commercial), or implementation (standalone software, libraries, packages, scripts).
We will start with a preliminary list of all software solutions identified as relevant by our research team and collaborators, and new additions are expected during the project. The software solutions will be assessed and compared, including installation and running requirements and instructions. Further, their performance will be tested using existing benchmark data from a variety of forest plots and stand conditions. Key metrics including tree location, diameter, height, and stem volume will be assessed and reported alongside processing time with commercial-grade computers.
We will make the outputs of our benchmarking exercise available in a scientific article, a public database, and short overview videos.
Geospatial data base for exposomics
PI: M. Boulos, University of Lisbon, Portugal
CoIs: M. Iyyanki (JN Technological University Hyderabad, India), A. Dewan (Curtin University, Australia), B. Bwambale (Mountains of the Moon University, Uganda)
Predisposition and development of various diseases, communicable, such as malaria and dengue fever, and non-communicable, such as diabetes, cardiovascular diseases, various types of cancer and mental health problems, involve a complex interplay between genetic factors (the genome) on the one hand and environmental and lifestyle parameters that populations are exposed to (the exposome) on the other hand. When combined with other relevant data, remote sensing data from various sources/products and of different types can help us better map and investigate the latter (exposomic determinants of disease/population-level exposures). However, these data sources and types remain a largely untapped resource for many researchers in the field, who are not familiar with the potential and value of these data and the unique insights that can be revealed by using them. Examples of such data obtained via remote sensing include data about air pollutants, land cover, green space, nocturnal outdoor light pollution and noise pollution, among others. The aim of this project is to develop and disseminate a much-needed comprehensive metadata catalogue of Earth observation data sources/products and types that are relevant to human health research. The searchable catalogue will take the form of a dedicated Web portal that will be provided as a free service to interested researchers worldwide. It is expected that the portal will enable more researchers and studies to discover and use remote sensing data (about population-level exposures to disease determinants) to reveal fresh insights that could improve our understanding of the aetiology, pathogenesis and spread of relevant diseases, and hence contribute to the development of better-optimised prevention and management programmes to tackle them.
Integrating IndoorGML with outdoors: Automatic routing graph generation for indoor‐outdoor transitional space for seamless navigation
PI: Z. Wang, South China University of Technology, China
CoIs: M. Mostafavi (Université Laval, Canada), K. Khoshelham (University of Melbourne, Australia), L. Vilariño (Universidade de Vigo, Spain), S. Zlatanova, (UNSW, Australia), K.-J. Li (Pusan National University, Korea)
With the fast expansion of modern cities, the complexity of urban environments has significantly increased, creating a need for assistance for seamless indoor‐outdoor navigation. To meet this need, a number of standards and methods have emerged. Among them, IndoorGML is a well‐developed standard with the focus on indoor location‐based services. This standard has already been accepted by the Open Geospatial Consortium (OGC) and is now under active development. Although some mechanisms in IndoorGML have been defined to enable integration of indoor and outdoor networks, there are still no concrete guidelines for determination of indoor‐outdoor connections. It also lacks solid scientific foundations and efficient tools to extract the connecting nodes and edges that link indoor and outdoor spaces. To address this gap, in this scientific initiative we focus on connection of indoor and outdoor spaces and aim to provide a tool to automatically construct navigation graphs of the indoor‐outdoor transitional space to support seamless integration of indoor‐outdoor navigation. We expect that the developments from this project will benefit the IndoorGML ecosystem and greatly advance the capability of IndoorGML in representing navigable space and in supporting location-based services.