User:Julian
From iis-projects
Contents
Julian Moosmann
I received my B.Sc. and M.Sc. degrees in Electrical Engineering and Information Technology from the Swiss Federal Institute of Technology Zurich (ETHZ), Switzerland. At the end of my Master's I was Team Leader in the CubeSat project SAGE (Swiss Artificial Gravity Experiment) at ARIS (Akademische RaumfahrtInitiative Schweiz) where I was responsible for the development of the On-Board Computer. We were the first student team, developing the first CubeSat in the German speaking part of Switzerland. During that time, I was able to fly on a zero-G flight performing some experiments with a development-model of our CubeSat. Furthermore, I was allowed to attend the Fly your Satellite workshop at ESTEC (ESA) in the Netherlands. Furthermore, during my Master thesis and afterwards, I developed a multi-object detection network, called TinyissimoYOLO, which is by-design able to be deployed on most simplest hardware accelerators with a memory footprint requirement of less than half a Megabyte. Therefore, one is able to deploy this network on nearly all microcontrollers. Currently, I am pursuing a Ph.D in developing further computer vision algorithms for microcontrollers or Single-Board Computers (Edge devices) with a focus on event-based cameras (DVS cameras) at IIS/PBL and end-to-end ML applications on PULP systems.
Interests
My main interest is in computer vision using conventional and event-based cameras, combined with edge various edge architectures, reaching from single-board computer to microcontroller's with accelerated hardware.
- Machine Learning, Deep Neural Networks
- Accelerated ML hardware
- Computer Vision
- Embedded systems
- PCB Design
- TinyML on Microcontrollers
Contact Information
- Office: ETF F 110
- e-mail: julian.moosmann@pbl.ee.ethz.ch
- www: IIS Homepage
Projects
Available Projects
- GPT on the edge
- Testbed Design for Self-sustainable IoT Sensors
- Towards Flexible and Printable Wearables
- Modular Distributed Data Collection Platform
- Object Detection and Tracking on the Edge
- Design of a Low Power Smart Sensing Multi-modal Vision Platform
- Design of a High-performance Hybrid PTZ for Multimodal Vision Systems
Projects In Progress