We are losing the planet's biodiversity at an unprecedented rate and in many cases, we do not even have the basic numbers. Photographs, taken by field scientists, tourists, citizen scientists, automated cameras, incidental photographers, and collected from social media are the most abundant source of data on wildlife today. To utilise this imagery fully and successfully address the biodiversity crisis and other societal challenges, we need the complementary capabilities of both humans and machines, in partnership.

Brief Bio of Prof Tanya Berger-Wolf. As one of the founders of the field of computational ecology, and recently imageomics, Tanya is leading research at the unique intersection of computer science, wildlife biology, and social sciences. She creates computational solutions to generate, collect, analyze and derive insight from data to answer questions and make decisions in ecology, environment and wildlife conservation. Tanya is a Professor of Computer Science and Engineering; Electrical and Computer Engineering; and Evolution, Ecology, and Organismal Biology at the Ohio State University, where she is also the Director of the Translational Data Analytics Institute. She is also a director and co-founder of the AI for conservation software non-profit Wild Me, home of the Wildbook project, which brings together computer vision, crowdsourcing, and conservation. It has been recently chosen by UNSECO as one of the top AI 100 projects worldwide supporting the UN Sustainable Development Goals. Tanya is a co-founder of a several big projects and fields of study. She works with many teams of brilliant people who do cool, amazing, and impactful things.

Robert Dawes from BBC Research and Development will talk about his team's fascinating collaborations with the BBC's Natural History Unit - using computer vision and machine learning to help with the production of shows such as Springwatch.

Brief Bio Robert Dawes (MEng). Robert is a Lead Research Engineer in the BBC Research & Development. He studied computer science at the University of Bristol before joining BBC R&D in 2006. He worked on set top box technologies and in the BBC iPlayer team before specialising in the application of image analysis, computer vision and tracking technologies to broadcasting. He currently leads the Visual Computing team, as part of the Production Applied Research Area, which investigate and develop tools to process, analyse and understand video – normally in real time. The team works with broadcast companies and production teams to try and create practical tools to help them with their work. This has included several years of work on sports analysis and graphics systems. In recent years, Robert has worked in collaboration with the Natural History Unit to investigate new ways to monitor and capture wildlife footage. Much of this work takes advantage of the rapidly developing field of artificial intelligence and machine learning.

Starting from the maybe provocative questions if 'science is mostly driven by ideas or by tools' (Dyson 2012) I will present one of the most difficult computer vision and machine learning scenario, namely quantifying insect behaviour in natural environments: Tiny, low contrast and fast moving objects have to be localised in cluttered and dynamic scenes resulting in visual ambiguities, frequent occlusions and the need to process huge video files with inappropriate foreground-background ratios and sparse visitation events. I will summarize some of the most prominent challenges to detect insects and quantify their in unconstrained settings and will introduce an appearance-agnostic in-field animal detection and tracking algorithm to extract accurate measurements from camera footage. I will close by presenting complementary environmental mapping approaches that yield rich contextual information, and moreover can be combined with behavioural data to achieve the urgently needed lab-level quantifications in wildlife conditions.

Brief Bio of Prof Benjamin Risse. Benjamin Risse is the head of the Computer Vision & Machine Learning Systems group at the University of Münster. He is interested in interdisciplinary research questions involving the development of novel image analysis techniques with a particular focus on the imaging hardware and algorithms for quantitative animal behaviour and sustainable development. After receiving his PhD in 2015, which was in the intersection of computer vision, machine learning and neuroscience, he was a postdoc at the University of Edinburgh in which his research was focussed artificial intelligence including insect tracking, habitat reconstruction, robotics and neurobiologically inspired algorithms. Since 2022 he is a Professor for Sustainable Development at the Institute for Geoinformatics in Muenster, Germany.

Tom will be talking about his work with drones ranging from science applications through to conservation. From flight tests in Bristol through to deployments in Central America, Papua New Guinea and even underground, he will talk about recent projects and future research directions.

Brief Bio of Prof Tom Richardson. Tom Richardson is Professor of Aerial Robotics at the University of Bristol in the UK. Passionate about aerospace engineering, he specializes in the application of modern control theory and novel sensors to UAS/Drones. He has been granted permission for BVLOS (Beyond Visual Line of Sight) operations in multiple countries and was the International Drone Safety Lead for the Multinational Deep Carbon Observatory (DCO) funded ABOVE field campaign to Papua New Guinea in 2019. Tom is a founding partner of Perceptual Robotics, has held an NPPL (pilots license) for over 15 years, and has worked with a range of industrial partners including DSTL, BAE Systems and Thales.

Understanding movement of animals is key in ecology. Tracking animals using GPS and accelerometers will not only yield understanding about the whereabouts of wildlife, also about their conservation. I illustrate this by using understanding about predator-prey interactions to develop a system to prevent poaching. I will further explore possible alternatives for GPS to follow wildlife. These examples show that AI is instrumental to developments in ecology.

Brief Bio of Prof Frank van Langevelde. Frank van Langevelde is professor and chair of the Wildlife Ecology and Conservation group at Wageningen University, The Netherlands. His research focuses broadly on ecological and evolutionary adaptations of animals to stress. Environmental stresses can constrain movement and searching for resources. As a consequence, constrained movement can result in suboptimal choices in foraging and habitat selection. This is studied in a variety of systems, varying from mammalian herbivores to insects.