PhD Studentship - Adaptive Sensor Fusion for Optimised 3D Sensing

This project will investigate a multi-sensor approach to 3D imaging, using a SPAD ToF in combination with other types of sensors, with the aim of substantially reducing power consumption. The sensor fusion and modulation of the ToF laser source will be adapted according to the sensed environmental conditions to ensure robust, power-efficient sensing. As part of the sensor fusion, lightweight neural network models will be developed for 3D reconstruction and object detection. The project will use existing sensors (SPAD, RGB, EVS, IMU) as a starting point, and develop a system around them, with closed-loop control and data fusion being implemented on a single-board computer.

The project is funded by Sony and will involve close engagement with Sony Europe Technology Development Center (EUTDC) in Trento, Italy, with the results of the project potentially informing the design of future SPAD sensors. The project would suit candidates with a background in Electronics/Computer Science and strong interest in image sensor technology and AI-based image processing, as well as a readiness to conduct physical experiments.

Please note, the position will be filled once a suitable candidate has been identified.

Further Information:

Relevant references:

[1] Della Rocca FM et al. (2020), A 128 × 128 SPAD Motion-Triggered Time-of-Flight Image Sensor with In-Pixel Histogram and Column-Parallel Vision Processor. JSSC, 55(7 doi.org/10.1109/JSSC.2020.2993722

[2] Mora-Martín G et al. (2021), High-speed object detection with a single-photon time-of-flight image sensor. Opt. Express, 29. doi.org/10.1364/OE.435619

Principal Supervisor: Dr Istvan Gyongy

Assistant Supervisor: TBC

Eligibility:

Funding:

Informal Enquiries: istvan.gyongy@ed.ac.uk

The University of Edinburgh is committed to equality of opportunity for all its staff and students, and promotes a culture of inclusivity. Please see details here: www.ed.ac.uk/equality-diversity