Imaging Systems Laboratory at the University of Hong Kong, led by Prof. Edmund Lam, is dedicated to advanced research in computational imaging, combining aspects of electronic engineering, computer vision, and optical engineering. Its primary interests lie in the development of novel algorithms for unconventional imaging systems and leveraging AI in imaging applications.
Neuromorphic imaging is a novel area that the lab explores. It involves the use of imaging systems that mimic the human brain’s neural structure and processing methods. This field is particularly relevant for developing advanced vision systems that can efficiently process visual information, potentially leading to breakthroughs in areas like autonomous systems and robotics.
The lab has a strong focus on digital holography, a technique that captures and reconstructs holograms digitally. This includes advancements in optical scanning holography, polarization holographic spectrometry, and holographic 3D particle reconstruction. The lab’s work in this area contributes to a deeper understanding and enhanced application of holography in various fields.
The lab is actively engaged in the detection and assessment of microplastic pollution, a growing environmental concern. This involves utilizing advanced imaging techniques like digital holography combined with deep learning for efficient and accurate identification and classification of microplastics in various environments.
Research in this area encompasses a broad range of technologies aimed at improving health and wellbeing. This includes biomedical microscopy, eye imaging, and optical coherence tomography. The lab is involved in developing advanced imaging techniques and algorithms that have significant implications for medical diagnostics and treatment.
Differentiable imaging represents a foundational paradigm in computational imaging. Leveraging differentiable programming, it effectively bridges the gaps among core system components, enabling authentic co-design to move from concept to practical implementation.