Methods for volume inference of non-medical objects from images: A short review

B Nabitchita, NJ Gonçalves, PJ Coelho… - Journal of Ambient …, 2024 - content.iospress.com
Nowadays, the object's volume is essential for monitoring any scene. Technological
equipment is evolving, and mobile devices and other devices embed high-resolution …

Hardware-aware partitioning of convolutional neural network inference for embedded ai applications

F Kreß, J Hoefer, T Hotfilter, I Walter… - … Computing in Sensor …, 2022 - ieeexplore.ieee.org
Embedded image processing applications like multicamera-based object detection or
semantic segmentation are often based on Convolutional Neural Networks (CNNs) to …

CNNParted: An open source framework for efficient Convolutional Neural Network inference partitioning in embedded systems

F Kreß, V Sidorenko, P Schmidt, J Hoefer, T Hotfilter… - Computer Networks, 2023 - Elsevier
Applications such as autonomous driving or assistive robotics heavily rely on the usage of
Deep Neural Networks. In particular, Convolutional Neural Networks (CNNs) provide …

Embedded face recognition for personalized services in the assistive robotics

I Walter, J Ney, T Hotfilter, V Rybalkin, J Hoefer… - … Conference on Machine …, 2021 - Springer
Recently, the field of assistive robotics has drawn much attention in the health care sector. In
combination with modern machine learning-supported person recognition systems, they can …

Towards reconfigurable accelerators in hpc: Designing a multipurpose efpga tile for heterogeneous socs

T Hotfilter, F Kreß, F Kempf, J Becker… - … , Automation & Test …, 2022 - ieeexplore.ieee.org
The goal of modern high performance computing platforms is to combine low power
consumption and high throughput. Within the European Processor Initiative (EPI), such an …

[PDF][PDF] Jürgen Becker

D Grimm, T Hotfilter, G Molinar, M Stang, S Stock… - 2019 - pos.sissa.it
Machine learning and deep learning, in particular, have become increasingly important in
engineering. The technology has been around for several decades already. Whereas data …