جست‌وجوی استاد و پژوهشگر

• Visual Object Recognition
• Learning from Small and Imbalanced Data
• Fine-grained Recognition
• +۵ مورد دیگر

Dr. Paul Bodesheim serves as a Postdoctoral Researcher and Lecturer in the Computer Vision Group at Friedrich Schiller University Jena's Department of Mathematics and Computer Science. He is also a member of ELLIS (European Laboratory for Learning and Intelligent Systems) and ELLIS Unit Jena. His academic journey began with Computer Science studies at Friedrich Schiller University Jena, focusing on Digital Image Processing and Computer Vision, followed by PhD research on "Discovering unknown visual objects with novelty detection techniques." Dr. Bodesheim's research interests center on bridging computer vision with biodiversity applications. His work spans visual object recognition, fine-grained recognition techniques specifically applied to biodiversity research, novelty detection and open set recognition, and active learning approaches for lifelong learning systems. He has developed approaches that address challenges of learning from small and imbalanced datasets, which are particularly valuable in ecological monitoring where data collection can be challenging. His publication record reveals a strong trend connecting computer vision methodologies with biodiversity monitoring applications. A significant portion of his recent work focuses on automated visual monitoring systems for insects and mammals, particularly using camera traps for biodiversity assessment. His research demonstrates how techniques like deep learning, few-shot learning, and uncertainty quantification can be effectively applied to ecological challenges such as species identification and population monitoring. Best Paper Award at DeLTA 2024 (Few-Shot Learning with Novelty Detection) Best Paper Award at Anomaly Detection Workshop of ICML 2016 Best Poster Award at FEAST Workshop of ICPR 2014 Best Paper Honorable Mention Award at ACCV 2012 Dr. Bodesheim has supervised numerous theses across bachelor's, master's, and diploma levels, focusing on applications of computer vision to biodiversity monitoring. His research is supported by various projects including LEPMON (Monitoring Biodiversity of Moths), InsectAI (EU COST Action Network), and previously BACI and AMMOD projects. He serves as a reviewer for prestigious journals and conferences including IEEE TPAMI, JMLR, and CVPR workshops. He leads the Computer Vision and Machine Learning team within the Computer Vision Group and contributes to the development of the AMMOD (Automated Multisensor station for Monitoring of species Diversity) system, which integrates multiple sensor technologies for comprehensive biodiversity monitoring. His work demonstrates a strong commitment to developing practical computer vision solutions for pressing ecological challenges.

• Precision Horticulture
• Spectro-optical Measurement Methods
• LiDAR and Hyperspectral Sensing
• +۴ مورد دیگر

Manuela Zude-Sasse is a Research Professor at the Leibniz Institute for Agricultural Engineering and Bioeconomy (ATB) in Potsdam, Germany, and former Professor at Beuth University of Applied Sciences Berlin (2009–2017). As Working Group Leader for Precision Horticulture, she focuses on spectro-optical measurement methods (LiDAR, hyperspectral analysis) for fruit quality assessment, canopy modeling, and data science applications in bioeconomy. M.Sc. in Chemistry/International Agronomy (1996, TU Berlin) Ph.D. in Horticulture summa cum laude (1999, TU Berlin) Habilitation in Applied Plant Physiology (2004, Humboldt University) Her research spans Precision Fruit Production , Plant Phenotyping , and 3D Sensor Integration , with projects like CrackSense (fruit cracking prediction) and horDIGrow (resource-efficient horticulture). She employs LiDAR, hyperspectral imaging, and time-resolved fluorescence to analyze temperate and tropical fruits. Recent publications in Plant Phenomics and Horticulturae demonstrate her work on spatial chlorophyll estimation via LiDAR and fruit water stress indices. Her studies in the Journal of Food Engineering (2024) and Postharvest Biology and Technology (2023) highlight machine learning applications for ripeness detection and 3D canopy analysis. Technology Transfer Award (State of Brandenburg, 2003) Silver Medal for Innovation (Agritechnica, 2017) She leads the SMART Farming Technology Research Center (SFTRC) collaboration in Malaysia and serves on editorial boards for Plant Phenomics , International Agrophysics , and Biosystems Engineering . Her 3D point cloud methodologies enable non-contact fruit biomechanics and nutrient management studies.

• Geological Remote Sensing
• Hyperspectral Imaging
• Mineral Exploration
• +۳ مورد دیگر

Dr. Richard Gloaguen serves as Head of the Exploration Department at the Helmholtz Institute Freiberg for Resource Technology (HZDR), part of the Helmholtz-Zentrum Dresden-Rossendorf. His work focuses on advancing geospatial technologies and hyperspectral imaging for sustainable resource management. Key areas include mineral exploration, environmental monitoring of mining sites, and AI-driven analysis of geological data. Research interests emphasize integrating remote sensing, machine learning, and robotics for applications in resource technology, including hyperspectral imaging of drill cores, UAV-based geophysical surveys, and recycling stream characterization. He leads projects such as MOSMIN (multiscale mining observation), MULSEDRO (drone-based mineral exploration), and the development of open-source tools like the HYDE hyperspectral denoising package. His recent publications highlight innovations in 3D hyperspectral point cloud segmentation, satellite-based environmental monitoring of mine areas, and benchmark datasets for material classification. He collaborates globally on initiatives like the RAMSES-4-CE project for e-waste sensor networks and the Open Geology Database (OGD) platform. Dr. Gloaguen’s team develops autonomous robotic systems for underground mining mapping and has pioneered methods for real-time hyperspectral data processing during core logging. His work bridges geoscience, engineering, and computer science to address challenges in sustainable resource extraction and recycling.

• Plant Metabarcoding
• Population Genetics
• Biodiversity Research
• +۵ مورد دیگر

Prof. Dr. Birgit Gemeinholzer is a Professor at the University of Kassel, where she serves as Head of Working Group and Chair Holder in the Department of Botany within the Institute of Biology (FB 10). Her academic journey began with horticulture studies at the Berlin University of Applied Sciences, followed by a Master of Science at the University and Royal Botanic Gardens Edinburgh. She earned her PhD at the University of Heidelberg focusing on Solanaceae phylogeny, held postdoctoral positions at IPK-Gatersleben, and worked as Research Associate at the Botanical Garden and Botanical Museum Berlin-Dahlem. Prior to her current position at Kassel, she served as Academic Councillor at Justus Liebig University of Giessen, where she completed her habilitation in plant systematics and biodiversity research and was appointed extraordinary professor in 2017. Prof. Gemeinholzer's research focuses primarily on plant metabarcoding, population genetic analyses of endangered plants, and networking of biological data. Her work bridges molecular techniques with ecological and conservation applications, particularly in understanding plant-insect interactions, genetic diversity in threatened species, and the development of biodiversity monitoring systems. She has made significant contributions to DNA barcoding methodologies, metabarcoding applications for environmental monitoring, and the conservation genetics of endangered plant species. Her research integrates cutting-edge molecular approaches with traditional botanical knowledge to address pressing conservation challenges. Analysis of her recent publications reveals a strong emphasis on developing and applying molecular techniques for biodiversity assessment and conservation. Her work spans from fundamental methodological improvements in DNA metabarcoding to applied studies on plant-pollinator interactions, genetic consequences of habitat fragmentation, and the development of automated biodiversity monitoring systems. She frequently collaborates across disciplines, working with ecologists, data scientists, and conservation practitioners to translate molecular findings into practical conservation applications. Her research shows a clear trajectory toward integrating artificial intelligence with molecular data for more comprehensive ecosystem understanding. Prof. Gemeinholzer has been actively involved in major research initiatives including NFDI4Biodiversity (National Research Data Infrastructure for Biodiversity), the Global Genome Biodiversity Network (GGBN), and the DNA Bank Network. She has contributed significantly to developing data standards and infrastructure for biodiversity research, particularly in the areas of DNA barcoding and metabarcoding. Her work on the Disentis Roadmap for biodiversity data release demonstrates her commitment to open science and data sharing practices in biodiversity research. At the University of Kassel, Prof. Gemeinholzer leads research activities focused on plant biodiversity assessment using molecular methods. Her laboratory develops and applies metabarcoding techniques for environmental monitoring, with particular emphasis on plant-insect interactions and conservation genetics of endangered species. She collaborates extensively with other researchers across Germany and internationally, contributing to large-scale biodiversity monitoring initiatives and conservation projects. Her work bridges fundamental research in plant systematics with practical applications for nature conservation.

Stanislav Shevchukمشاهده پروفایل

پژوهشگر

• GNSS Technologies
• Multi-Sensor Data Integration
• Map Matching
• +۳ مورد دیگر

Stanislav Shevchuk is a Researcher at the Institute of Engineering Geodesy within the Faculty 6: Aerospace Engineering and Geodesy at the University of Stuttgart. He contributes to the Cluster of Excellence IntCDC, focusing on integrative computational design and construction for architecture. His contact details include a phone number (+49 711 685 84050) and physical address (Geschwister-Scholl-Str. 24D, 70174 Stuttgart, Germany). Research Project: RP 16-2 – Cyber-Physical On-Site Construction Processes using a Spider Crane Robotic Platform His expertise spans GNSS technologies , multi-sensor data integration , and map matching . He teaches exercises in Monitoring (Geomatics Engineering, Master 1st semester) and Terrestrial Multisensor Systems (Geomatics Engineering, Master 3rd semester).

Matthias Braunمشاهده پروفایل

استاد

• Glaciology
• Remote Sensing
• Geographic Information Systems
• +۷ مورد دیگر

Professor Matthias Braun is a distinguished academic in the field of physical geography, specializing in remote sensing and GIS applications for glaciology and polar research. He holds a professorship at the Institute of Geography at Friedrich-Alexander University Erlangen-Nuremberg (FAU), where he leads the Chair of Geography (Remote Sensing and GIS) and serves as Chairman of the Examination Board for B.Sc./M.Sc. Physical Geography and BA/MA Cultural Geography since 2022. His research focuses on monitoring glacier dynamics, ice sheet changes, and climate impacts in polar and mountainous regions using advanced remote sensing techniques. Professor Braun has held several significant leadership positions including Chairman of the International Doctoral Program 'Measuring and Modelling Mountain Glaciers in a Changing Climate' in the Bavarian Elite Network funded by the Bavarian Ministry of Science & Art since 2022, and Coordinator of the DFG SPP Antarctic Research since 2017. His academic journey includes an Associate Professor position at the University of Alaska Fairbanks (2010-2011) and extensive field experience leading multiple Arctic and Antarctic expeditions since 1994/95, with research stays in Alaska, South America, West & East Africa, Himalaya & Karakorum. His research interests span glaciology, remote sensing, geographic information systems, climate change impacts, land use change, polar regions, and high mountain environments. Professor Braun's work integrates microwave and optical remote sensing data from satellite and airborne platforms to derive geobiophysical parameters and their spatiotemporal variations. He employs advanced digital image processing, pattern recognition, SAR interferometry, and polarimetry techniques in his research. His laboratory maintains active participation in major research initiatives including the TanDEM-X and TanDEM-L Science Teams since 2010. Professor Braun's extensive publication record demonstrates a clear progression from foundational work on glacier monitoring to sophisticated applications of machine learning and deep learning for glacier feature extraction. His recent work focuses on calving front detection using SAR imagery, glacier velocity mapping, and integration of multi-sensor data for comprehensive glaciological analysis. Key research themes include glacier mass balance, ice sheet dynamics, supraglacial hydrology, and climate change impacts on cryospheric systems across diverse regions including Antarctica, Patagonia, the Himalayas, and the European Alps. Among his notable recognitions is the 2009 Science Award for Physical Geography from the Prof. Dr. Frithjof Voss Foundation for Geography and his Habilitation at the Mathematical-Natural Science Faculty of the University of Bonn in 2009. He serves as an Associate Editor for Frontiers in Earth Sciences – Cryospheric Sciences and reviews for numerous peer-reviewed journals. Professor Braun has mentored numerous doctoral students to completion, with recent graduates including Dr. Christian Sommer (2022), Dr. David Farias Barahona (2021), Dr. Stefan Lippl-Seifert (2020), and Dr. Peter Friedl (2019). Several students are currently completing their dissertations under his supervision. His research is supported by various funding mechanisms including the Bavarian Elite Network, DFG research programs, and international collaborations. He maintains strong connections with national and international research institutions including membership in the International Glaciological Society (IGS), German Society for Photogrammetry, Remote Sensing and Geoinformation (DGPF), German Society for Polar Research (DGP), and German Society for Geography (DGfG).

• Acoustics
• Ultrasonic Sensors
• Multisensor Systems
• +۲ مورد دیگر

Prof. Dr. Thorsten Uphues is a Professor at Coburg University of Applied Sciences, Faculty of Applied Natural Sciences and Health. He specializes in applied sensor technology and acoustics research, with current leadership in the KonDispUS project (2024-2026) developing ultrasonic multisensor systems for concentration analysis in liquid dispersions. His research focuses on: Acoustic measurement principles Ultrasonic sensor design Multisensor data fusion Concentration quantification in complex liquids Non-invasive industrial analytics Contact: Thorsten.Uphues@hs-coburg.de | ORCID iD: 0000-0003-3423-4510

• UAV photogrammetry
• Remote sensing
• Geomorphological monitoring
• +۷ مورد دیگر

Anette Eltner is a Junior Professor for Geosensor Systems at the Technical University of Dresden since 2021. Her work focuses on developing innovative methods for environmental monitoring using AI and remote sensing technologies. She leads research projects that aim to improve flood forecasting systems and monitor geomorphological changes through advanced imaging techniques. Her educational background includes: PhD in Geography from TU Dresden (2016), awarded by the German working group for geomorphology Diploma in Geography from TU Dresden (2010) with minors in Photogrammetry/Remote Sensing, Soil Science and Hydrology Professor Eltner's research spans multiple cutting-edge areas in geospatial technology and environmental science. She specializes in UAV photogrammetry and remote sensing, developing methods for precise geomorphological and hydrological monitoring. Her work integrates artificial intelligence with environmental sciences to create more accurate predictive models for natural processes. She focuses particularly on erosion processes in fragile landscapes and has pioneered techniques for spatio-temporal high resolution topography using laserscanning, structure-from-motion, and time-lapse imaging. Her innovative approach to image processing enables automatic feature detection and tracking in geographic applications, while her development of low-cost geosensor systems makes advanced monitoring accessible in resource-limited settings. Her publication record demonstrates consistent advancement from foundational photogrammetric techniques to sophisticated AI integration for real-time environmental assessment. The research shows increasing emphasis on practical flood warning applications and dynamic landscape monitoring, particularly for small waterways where traditional monitoring systems are lacking. Her notable scientific achievements include: PhD thesis award from the German working group for geomorphology (AK Geomorphologie) TUD Young Investigator status (recognizing excellent, independent junior research group leaders) Editorial board membership for Geoscientific Instrumentation, Methods and Data Systems and Photogrammetric Record Professor Eltner leads the "Artificial Intelligence for Flood Warning (KIWA)" project, evaluating camera-based water level monitoring systems along small tributaries of the Elbe River in Saxony. Her research group develops AI-supported methods to analyze water surface imagery and predict flood events in small waterways. She has secured funding for projects in Germany and internationally, including current work in Oman combining cameras and seismic sensors to monitor rare flood events in wadis. Her team is developing systems that allow sensors to communicate with each other for dynamic environmental monitoring. Her laboratory work focuses on developing cost-effective monitoring solutions using accessible technology like Raspberry Pi computers and standard cameras. She has demonstrated that these low-cost systems can effectively monitor significant landscape changes, making advanced environmental monitoring more widely available. Current projects involve creating 3D point cloud analysis methods that incorporate temporal components to better predict dynamic processes like soil erosion, rockfalls, and landslides.