Conservation Artificial Intelligence (AI) - A chool of Computer Science Seminar Talk by Dr Paul Fergus and Dr Carl Chalmers
Join us Wednesday 18 March, B12 Xu-Yafen. Refreshments will be provided
Many different species are adversely affected by poaching. In response to this escalating crisis, efforts to stop poaching using hidden cameras, drones and DNA tracking have been implemented with varying degrees of success. Limited resources, costs and logistical limitations are often the cause of most unsuccessful poaching interventions. Conservation AI is a project we have developed that aims to harness machine learning for various conservation projects. At present it is focused on detecting and classifying animals, humans, and man-made objects indicative of poaching (e.g. cars, fires).
Our work is focused the use of images from visual spectrum and thermal infrared cameras used on drones, camera traps and land based remotely controlled vehicles. The research aims to provide a user-friendly workflow that allows for near real-time detection/classification and non-real time detection/classification.
We have ongoing projects with Knowsley Safari in the UK, the Endangered Wildlife Trust in South Africa, and the Greater Mahale Ecosystem Research and Conservation team. In this talk we present the work we have done so far and the technologies implemented in our conservationai.co.uk system. In particular deep learning convolutional neural networks, tagging, modelling training and real-time model hosting using docker and tensorflow-serving.
Dr Paul Fergus is a Reader (Associate Professor) in Machine Learning. Dr Fergus’s main research interests include machine learning for detecting and predicting preterm births. He is also interested in the detection of foetal hypoxia, electroencephalogram seizure classification and bioinformatics (polygenetic obesity, Type II diabetes and multiple sclerosis). He is also currently conducting research with Mersey Care NHS Foundation Trust looking on the use of smart meters to detect activities of daily living in people living alone with Dementia by monitoring the use of home appliances to model habitual behaviours for early intervention practices and safe independent living at home.
Dr Carl Chalmers is a Senior Lecturer in the Department of Computer Science at Liverpool John Moores University. Dr Chalmers’s main research interests include the advanced metering infrastructure, smart technologies, ambient assistive living, machine learning, high performance computing, cloud computing and data visualisation. His current research area focuses on remote patient monitoring and ICT based healthcare. He is currently leading a three-year project on smart energy data and dementia in collaboration with Mersey Care NHS Trust. The current trail involves monitoring and modelling the behaviour of dementia patients to facilitate safe independent living. In addition, he is also working in the area of high-performance computing and cloud computing to support and improve existing machine learning approaches, while facilitating application integration.