The workshop be held on Septemeber 30th, 2024 and will consist of the following components:
Invited talks
A panel discussion
A presentation of the challenge winners
A poster session presenting contributed papers/abstracts
Schedule
Time
Event
8:30
Opening remarks
8:45
Invited talk 1: Devis Tuia, EFPL; Title TBA
9:05
Invited talk 2: Blair Costelloe, Max Planck Institute; Title TBA
9:25
Invited talk 3: Diego Marcos, Inria Université Côte d’Azur; Title TBA
9:50
Poster session & coffee break
10:30
FishNet challenge
10:45
Invited talk 4: Hannah Kerner, Arizona State University; Title TBA
11:05
Invited talk 5: Erin Moreland, NOAA; Title TBA
11:25
Invited talk 6: Rita Pucci, Naturalis Biodiversity Center; Title TBA
11:50
Panel discussion (hybrid)
12:50
Closing remarks
Speakers
Devis Tuia
Devis completed his PhD at University of Lausanne, Switzerland, where he studied kernel methods for hyperspectral satellite data. He then traveled the world as a postdoc, first at University of València, then at CU Boulder and finally back to EPFL. In 2014, he became assistant professor at University of Zurich, and in 2017 he moved to Wageningen University in the Netherlands, where he was chair of the Geo-Information Science and Remote Sensing Laboratory. Since September 2020, he is back to EPFL, where he leads the Environmental Computational Science and Earth Observation laboratory (ECEO) in Sion. There, he studies Earth and biodiversity from above with machine learning and computer vision.
Blair Costelloe
Dr. Blair Costelloe is a behavioral ecologist interested in the collective and antipredator behavior of large African mammals. As an EU-funded Marie Sklodowska-Curie Postdoctoral Fellow, she led the HerdHover project to develop drone- and image-based methods for studying the collective behavior of animals in their natural environments. She is currently a principle investigator on the EU-funded WildDrone project, which aims to develop new drone and image-based tracking tools for wildlife conservation missions. Her research focuses on understanding the role animal behavior in driving broader-scale ecological processes. Blair is a Project Leader at the Max Planck Institute of Animal Behavior and the Centre for the Advanced Study of Collective Behavior at the University of Konstanz in Germany. She earned her PhD in Ecology and Evolutionary Biology from Princeton University in 2014.
Diego Marcos
Diego Marcos is a tenure-track, junior professor at Inria Université Côte d’Azur in France, specializing in developing machine learning and computer vision methods to solve environmental and Earth observation problems. His research interests include creating more interpretable computer vision methods for species identification and building species distribution models using citizen science and Earth observation data. He holds a PhD from Wageningen University and an MSc in Computation Sciences and Engineering from EPFL in Switzerland.
Hannah Kerner
Hannah Kerner is an Assistant Professor in the School of Computing and Augmented Intelligence at Arizona State University. My research focuses on advancing the foundations and applications of machine learning to foster a more sustainable, responsible, and fair future for all. As the AI Lead for NASA’s agriculture programs, NASA Harvest and NASA Acres, she is deploying research methods in real applications across the globe; her projects have directly resulted in optimized agricultural planning, disaster response, and financial relief in various regions around the world. The impact of Kerner’s research was recognized in Forbes 30 Under 30 and the International Research Centre On Artificial Intelligence’s Top 10 projects solving problems related to the UN’s Sustainable Development Goals with AI.
Erin Moreland
Erin Moreland is a Research Zoologist with the Polar Ecosystems Program at the National Oceanic and Atmospheric Administration (NOAA), Alaska Fisheries Science Center’s Marine Mammal Laboratory. She oversees a project aimed at supporting the management of ice-associated seals in the U.S. Arctic through assessing the abundance and trends of ringed, bearded, ribbon, and spotted seals. Her responsibilities involve developing advanced survey methods which currently rely on a custom multispectral aerial imaging system paired with artificial intelligence models to detect and classify animals in the imagery in real time. Erin is the Chair of the NOAA AI Working Group and represents protected species on the Optics Strategic initiative, working to bring end-to-end AI solutions to researchers working with optical datasets across NOAA Fisheries.
Rita Pucci
Dr. Rita Pucci is a Postdoc in computer vision at the Naturalis Biodiversity center, Leiden, the Netherlands. She has conducted research in Australia and Scotland, focusing on machine-learning applications in animal behaviour analysis, underwater image manipulation, and fine-grained image classification. Currently, she is involved in the MAMBO and TETTRIS European projects at the Evolutionary Ecology group in Naturalis. In the MAMBO project, she is exploring modern techniques for monitoring biodiversity using computer vision and crowd-sourced data. In the TETTRIS project, she is working on the fine-grained classification of dark-taxa with images from museums’ collections in collaboration with the University of Hamburg.
Expert panel
The panel discussion will have a hybrid format, with some panelists present in person and others joining remotely. The panel will discuss the challenges and opportunities in the field of computer vision for ecology and conservation, with a focus on computer vision in the real world. The panelists are:
Anthony Hoogs
Dr. Hoogs leads Kitware’s Computer Vision group, which he founded when he joined Kitware in 2007. For more than two decades, he has supervised and performed research in various areas of computer vision including: event, activity and behavior recognition; motion pattern learning and anomaly detection; tracking; visual semantics; image segmentation; object recognition; and content-based retrieval. He has led dozens of projects, sponsored by commercial companies and government entities that range from basic, academic research to developing advanced prototypes, with a combined value exceeding $60M. In 2014 he served as an organizer of the National Academies National Research Council Workshop on Robust Methods for the Analysis of Images and Videos for Fisheries Stock Assessment, sponsored by NOAA, then joined the NOAA Automated Imagery Analysis Strategic Initiative Steering Committee.
Toke Høye
I am a professor in ecology at Aarhus University, Denmark. I lead a research group focused on developing and applying novel monitoring technology to questions related to species responses to environmental change. We primarily focus on insects and other invertebrates, where monitoring data is particularly limited and where species responses to environmental change is particularly pronounced. We focus on computer vision methods, which are particularly promising for global scalability and expert validation. We collaborate widely in interdisciplinary projects.
Dan Morris
Dan Morris is a researcher in the Google AI for Nature and Society program, where he works on AI tools that help conservation scientists spend less time doing boring things and more time doing conservation. This includes tools that accelerate urban forest canopy assessments and image-based wildlife surveys. Prior to joining Google, he directed the AI for Earth program at Microsoft, and prior to that he spent approximately a zillion years in the medical devices group at Microsoft Research, working on signal processing and machine learning tools for wearable devices that supported cardiovascular monitoring, fitness tracking, and gesture interaction. He received his PhD from Stanford, where he worked on haptics and physical simulation for virtual surgery.
Aurélie Shapiro
Aurélie Shapiro is an independent consultant based in Berlin, Germany providing remote sensing, GIS (Geographic Information Systems) spatial data analytics for environmental, biodiversity and sustainability projects through her company: Here+There Mapping Solutions. She is currently supporting the Food and Agriculture Organization of the United Nations (FAO) as Chief Technical Advisor supporting various projects including monitoring forest cover change to help countries manage their forest resources, obtain climate financing, and prevent future pandemics; agricultural mapping and risk assessment for deforestation reduction programs. In addition, she provides short-term consulting services for the World Bank Group to support climate change mitigation activities. She was formerly the Senior Remote Sensing Specialist for the World Wide Fund for Nature (WWF), where she developed and applied innovative satellite and aerial remote sensing for conservation and biodiversity projects worldwide. Aurélie has a phD in Natural Sciences from Humboldt Universität-zu-Berlin and a Master’s in Environmental Management from Duke University’s Nicholas School of the Environment in 2001 and a Bachelor of Science from McGill University in Canada in 1999.
