Jens Muller

Learn More
A novel massively-parallel fine-grain architecture featuring a digital emulation of Cellular Nonlinear Networks (CNN) is presented. A virtual cellular network is processed line-by-line by a locally connected linear array of processing elements. The resulting computing system is able to execute complex CNN program code consisting of consecutive operations.(More)
In this contribution, we present an algorithm aimed at the correction of a movement artifact in thermographic images recorded during neurosurgery. It is based on Cellular Nonlinear Networks (CNN) and was designed as a first step towards a platform capable of providing intraoperative feedback to a surgeon.
In this contribution we present a CNN video processing system that takes full advantage of a digital CNN Universal Machine (CNN-UM) using the recently-introduced NERO architecture. The proposed system is fully configurable in terms of network size and data precision. Using a Xilinx Zynq-7000 SoC we implemented a network of 512 × 900 cells at 8 bit,(More)
Emulations of cellular nonlinear networks (CNN) on digital reconfigurable hardware have proved to be adequate for highly-efficient computation of massive data, exceeding the accuracy and flexibility of full-custom designs. Based on a recently-proposed architecture for the emulation of a large-scale CNN universal machine, a new real-time video processing(More)
In this demonstration a 640 × 480p video processing system is presented, taking advantage of the massively parallel processing architecture NERO to emulate CNN dynamics. The system has been implemented on a development board featuring a Xilinx Zynq SoC and is capable of processing complex CNN algorithms, as will be shown in several examples.
Neurosurgery relies strongly on medical imaging techniques. However, many state-of-the-art diagnostic tools such as computer tomography (CT) and magneto-resonance imaging (MRI) cannot be applied during ongoing surgery in general. Our aim is to realize a multi-purpose imaging platform capable of real-time assistance to the surgeon. Therefore, we apply(More)
  • 1