DEEP- EVIoT Deep embedded vision using sparse convolutional neural networks

  • Home
  • Projects
  • DEEP- EVIoT Deep embedded vision using sparse convolutional neural networks

The main purpose of the project is to design and implement an heterogeneous platform consisting of multiple Low Power Graphic processors with deep learning algorithms acceleration capabilities. A software SDK for vision problems using optimized deep sparse coding techniques especially designed for the aforementioned platform will be provided. The significant benefits of the proposed deep eviot system extends to a very wide range of applications from industrial and surgical robotics to autonomous vehicles, smart security cameras and military applications.
Duration: 24 months
Timeline: 2019 – 2020
Project Types: National Research Projects
Funding Agency: Research and Innovation Strategies for Smart Specialisation (RIS3), Region of Western Greece, NSRF 2014-2020
URL: https://deepeviot.isi.gr
ISI Scientific Coordinator: Dr. Aris S. Lalos

Related

TRUSTEE – TRUST AND PRIVACY PRESERVING COMPUTING PLATFORM FOR CROSS-BORDER FEDERATION OF DATA
Today we live in a data-driven era with the inevitable emergence of interdisciplinary, geographically dispersed, data repositories that do not necessarily abide with existing interdisciplinary data representation standards, nor they belong to any data federation initiatives, rendering them unusable and...
ENVISION – Vision Based Navigation and Four Dimensional Scene Awareness
This project is a direct collaboration among Panasonic Automotive Systems Europe and MIPS Group (mips.isi.gr) of ISI/ATHENA and its aim is to study the feasibility of one or more re-localization techniques on a proof of concept level. More specifically, the project...
Sensor-based ego-Vehicle Re-localization and Registration Activities
This project is a direct collaboration among Panasonic Automotive Systems Europe and MIPS Group (mips.isi.gr) of ISI/ATHENA and it is focused on defining and implementing novel multimodal localization methods for Connected and Autonomous Vehicles. The project duration is 2 years....