Piotr Dudek
YOU?
Author Swipe
View article: A General-Purpose Neuromorphic Sensor based on Spiketrum Algorithm: Hardware Details and Real-life Applications
A General-Purpose Neuromorphic Sensor based on Spiketrum Algorithm: Hardware Details and Real-life Applications Open
Spiking Neural Networks (SNNs) offer a biologically inspired computational paradigm, enabling energy-efficient data processing through spike-based information transmission. Despite notable advancements in hardware for SNNs, spike encoding …
View article: Antithyroglobulin and Antiperoxidase Antibodies Can Negatively Influence Pregnancy Outcomes by Disturbing the Placentation Process and Triggering an Imbalance in Placental Angiogenic Factors
Antithyroglobulin and Antiperoxidase Antibodies Can Negatively Influence Pregnancy Outcomes by Disturbing the Placentation Process and Triggering an Imbalance in Placental Angiogenic Factors Open
Background/Objectives: Thyroid autoimmunity (TAI) affects about 15% of women of reproductive age and can negatively affect pregnancy outcomes. One possible mechanism for pregnancy complications can be attributed to a disturbed process of p…
View article: Mapping Image Transformations Onto Pixel Processor Arrays
Mapping Image Transformations Onto Pixel Processor Arrays Open
Pixel Processor Arrays (PPA) present a new vision sensor/processor architecture consisting of a SIMD array of processor elements, each capable of light capture, storage, processing and local communication. Such a device allows visual data …
View article: Factor Machine: Mixed-signal Architecture for Fine-Grained Graph-Based Computing
Factor Machine: Mixed-signal Architecture for Fine-Grained Graph-Based Computing Open
This paper proposes the design and implementation strategy of a novel computing architecture, the Factor Machine. The work is a step towards a general-purpose parallel system operating in a non-sequential manner, exploiting processing/memo…
View article: PixelRNN: In-pixel Recurrent Neural Networks for End-to-end-optimized Perception with Neural Sensors
PixelRNN: In-pixel Recurrent Neural Networks for End-to-end-optimized Perception with Neural Sensors Open
Conventional image sensors digitize high-resolution images at fast frame rates, producing a large amount of data that needs to be transmitted off the sensor for further processing. This is challenging for perception systems operating on ed…
View article: Malodour classification with low-cost flexible electronics
Malodour classification with low-cost flexible electronics Open
View article: The impact on the cost of making high pressure die castings with multi-cavity die and vacuum assistance
The impact on the cost of making high pressure die castings with multi-cavity die and vacuum assistance Open
In view of the increasing prices of energy and charge materials, it is necessary to optimize the costs of making castings. Tests were carried out on the possibility of making castings in a pressure die with an increased number of cavities …
View article: 143961
143961 Open
The aim of the study was to select the optimal content of zirconium introduced as an alloying additive to obtain the best strength properties of Al-Si alloy.A technically important disadvantage is the tendency of silumins to form a coarse-…
View article: 143962
143962 Open
The aim of the study was to select the optimal content of zirconium introduced as an alloying additive to obtain the best strength properties of Al-Si alloy.A technically important disadvantage is the tendency of silumins to form a coarse-…
View article: An integrate-and-fire neuron circuit made from printed organic field-effect transistors
An integrate-and-fire neuron circuit made from printed organic field-effect transistors Open
Neuromorphic circuits that mimic the operation of nerve cells are promising approaches to interface with or emulate the operation of biological neural network. These types of electronic circuits have generally been realised by fabrication …
View article: On-sensor binarized CNN inference with dynamic model swapping in pixel processor arrays
On-sensor binarized CNN inference with dynamic model swapping in pixel processor arrays Open
Many types of Convolutional Neural Network (CNN) models and training methods have been proposed in recent years aiming to provide efficiency for embedded and edge devices with limited computation and memory resources. The wide variety of a…
View article: Inhibin-B and FSH Are Good Indicators of Spermatogenesis but Not the Best Indicators of Fertility
Inhibin-B and FSH Are Good Indicators of Spermatogenesis but Not the Best Indicators of Fertility Open
Biochemical markers of spermatogenesis and fertility assessment are important in the practical management of infertile males and the determination of an individual’s prognosis. We performed an analysis on 100 males with a male infertility …
View article: On-Sensor Binarized Fully Convolutional Neural Network with A Pixel Processor Array
On-Sensor Binarized Fully Convolutional Neural Network with A Pixel Processor Array Open
This work presents a method to implement fully convolutional neural networks (FCNs) on Pixel Processor Array (PPA) sensors, and demonstrates coarse segmentation and object localisation tasks. We design and train binarized FCN for both bina…
View article: Obesity-diabetes-endocrinopathy – the metabolic connection
Obesity-diabetes-endocrinopathy – the metabolic connection Open
Introduction and aim. The article outlines the mechanisms of interrelationships between obesity, type 2 diabetes, and certain disorders of the endocrine system. The paper explains how insulin resistance develops, which is a key link betwee…
View article: MantissaCam: Learning Snapshot High-dynamic-range Imaging with Perceptually-based In-pixel Irradiance Encoding
MantissaCam: Learning Snapshot High-dynamic-range Imaging with Perceptually-based In-pixel Irradiance Encoding Open
The ability to image high-dynamic-range (HDR) scenes is crucial in many computer vision applications. The dynamic range of conventional sensors, however, is fundamentally limited by their well capacity, resulting in saturation of bright sc…
View article: Direct Servo Control from In-Sensor CNN Inference with A Pixel Processor Array
Direct Servo Control from In-Sensor CNN Inference with A Pixel Processor Array Open
This work demonstrates direct visual sensory-motor control using high-speed CNN inference via a SCAMP-5 Pixel Processor Array (PPA). We demonstrate how PPAs are able to efficiently bridge the gap between perception and action. A binary Con…
View article: Bringing A Robot Simulator to the SCAMP Vision System
Bringing A Robot Simulator to the SCAMP Vision System Open
This work develops and demonstrates the integration of the SCAMP-5d vision system into the CoppeliaSim robot simulator, creating a semi-simulated environment. By configuring a camera in the simulator and setting up communication with the S…
View article: Agile reactive navigation for a non‐holonomic mobile robot using a pixel processor array
Agile reactive navigation for a non‐holonomic mobile robot using a pixel processor array Open
This paper presents an agile reactive navigation strategy for driving a non‐holonomic ground vehicle around a pre‐set course of gates in a cluttered environment using a low‐cost processor array sensor. This enables machine vision tasks to …
View article: Visual Odometry Using Pixel Processor Arrays for Unmanned Aerial Systems in GPS Denied Environments
Visual Odometry Using Pixel Processor Arrays for Unmanned Aerial Systems in GPS Denied Environments Open
Environments in which Global Positioning Systems (GPS), or more generally Global Navigation Satellite System (GNSS), signals are denied or degraded pose problems for the guidance, navigation, and control of autonomous systems. This can mak…
View article: Agile Reactive Navigation for A Non-Holonomic Mobile Robot Using A Pixel Processor Array
Agile Reactive Navigation for A Non-Holonomic Mobile Robot Using A Pixel Processor Array Open
This paper presents an agile reactive navigation strategy for driving a non-holonomic ground vehicle around a preset course of gates in a cluttered environment using a low-cost processor array sensor. This enables machine vision tasks to b…
View article: Fully Embedding Fast Convolutional Networks on Pixel Processor Arrays
Fully Embedding Fast Convolutional Networks on Pixel Processor Arrays Open
View article: A Camera That CNNs: Towards Embedded Neural Networks on Pixel Processor Arrays
A Camera That CNNs: Towards Embedded Neural Networks on Pixel Processor Arrays Open
We present a convolutional neural network implementation for pixel processor array (PPA) sensors. PPA hardware consists of a fine-grained array of general-purpose processing elements, each capable of light capture, data storage, program ex…
View article: A Camera That CNNs: Towards Embedded Neural Networks onPixel Processor Arrays
A Camera That CNNs: Towards Embedded Neural Networks onPixel Processor Arrays Open
We present a convolutional neural network implementation for pixel processor array (PPA) sensors. PPA hardware consists of a fine-grained array of general-purpose processing elements, each capable of light capture, data storage, program ex…
View article: A Camera That CNNs: Towards Embedded Neural Networks on Pixel Processor\n Arrays
A Camera That CNNs: Towards Embedded Neural Networks on Pixel Processor\n Arrays Open
We present a convolutional neural network implementation for pixel processor\narray (PPA) sensors. PPA hardware consists of a fine-grained array of\ngeneral-purpose processing elements, each capable of light capture, data\nstorage, program…
View article: Real-Time Depth From Focus on a Programmable Focal Plane Processor
Real-Time Depth From Focus on a Programmable Focal Plane Processor Open
Visual input can be used to recover the 3-D structure of a scene by estimating distances (depth) to the observer. Depth estimation is performed in various applications, such as robotics, autonomous driving, or surveillance. We present a lo…
View article: A Demonstration of Tracking using Dynamic Neural Fields on a Programmable Vision Chip
A Demonstration of Tracking using Dynamic Neural Fields on a Programmable Vision Chip Open
A demonstration is made of a programmable vision chip, containing an array of photosensors collocated with a processing circuitry and memory, implementing a Dynamic Neural Field (DNF) over a simple saliency map. The system detects and trac…
View article: A Real-time High Dynamic Range Vision System with Tone Mapping for Automotive Applications
A Real-time High Dynamic Range Vision System with Tone Mapping for Automotive Applications Open
Automated and autonomously driving vehicles capture information from the environment using vision sensors (amongst others) and process it in order to detect lane markings, pedestrians, other vehicles, or to read traffic signs. A crucial is…
View article: Practical gradient-descent for memristive crossbars
Practical gradient-descent for memristive crossbars Open
This paper discusses implementations of gradientdescent based learning algorithms on memristive crossbar arrays. The Unregulated Step Descent (USD) is described as a practical algorithm for feed-forward on-line training of large crossbar a…
View article: The Day of Judaism in the Catholic Church of Poland
The Day of Judaism in the Catholic Church of Poland Open
This master’s thesis discusses “The Day of Judaism in the Catholic Church of Poland,” a special time in the Polish Church calendar to rediscover her roots in Judaism. Thus, the aim of this study is to present the changes taking place in th…