update: the deadline for the below opportunity has now passed…still you can get in touch with tom if you want to study a similar topic.
Interested in urban reconstruction? Want to live in Cyprus (we’re having a very cold, wet, summer here in Leeds)? I’m co-supervising a PhD with Melinos Averkiou into urban semantic understanding. Full details here.
Summary: Semantic understanding of urban data (e.g. buildings, streets, neighborhoods) is critical for urban sensing as well as many commercial applications such as accurate antenna placement for cellular networks, flood planning, and architectural urban visualisations. Without knowing the surface properties of urban models it is impossible to calculate, for example the thermal properties of buildings or to simulate window-visibility. In this project the goal is to utilize deep neural network architectures to fuse and understand noisy urban data from multiple sources. It will study the space of urban sensors, their competencies, errors, and failure cases, resulting in a robust framework for semantic urban reconstruction. Unlike many rigid urban modeling pipelines the desired outcome is a system that is entirely modular in its selection of sensors, allowing the addition, or removal, of data sources to suit the many different situations facing real-world urban planners. The successful candidate will design and train novel deep neural networks on novel synthetic datasets, to fuse disparate data sources and create a semantically labelled 3D model of urban scale.
candidates should possess:
- An undergraduate (BSc) and postgraduate degree (MSc or MPhil) in a relevant field (e.g. Computer Science, Computer Engineering, Information Technology) from an accredited institution, preferably with emphasis on Computer Graphics / Computer Vision / Machine Learning.
- Strong coding skills in Python, Matlab, C++, C (experience with CUDA is an advantage).
- Confidence in mathematics (e.g. linear algebra, geometry processing, probabilistic methods).
- Proven experience with ML/DL frameworks e.g. TensorFlow, PyTorch, Keras, FastAI.
- Knowledge of Conda package and environment management system, Docker or Kubernetes will be considered as an advantage.
- Self-motivation, ability to work independently, and excellent problem solving skills.
- Prior publications in the area (desirable but not essential).
- Very strong written and oral English language communication skills.