Entity

Time filter

Source Type


Vourvoulakis J.,Democritus University of Thrace | Kalomiros J.,Technological and Educational Institute of Central Macedonia | Lygouras J.,Democritus University of Thrace
Microprocessors and Microsystems | Year: 2016

Image feature extraction constitutes a fundamental task in robotic vision applications. Scale-Invariant Feature Transform (SIFT) has been widely used as a robust method for detecting and matching features. Nevertheless, SIFT algorithm is computationally demanding and its implementation in an embedded system requires a subtle approach. In this paper, an optimized and fully pipelined architecture is proposed for real-time detection of SIFT keypoints and extraction of SIFT descriptors. The system is suitable to target robotic vision applications and it is pipelined on pixel basis. The architecture is hosted in a medium-scale Cyclone IV FPGA device clocked at 21.7 MHz and is capable of extracting a feature with its descriptor at every clock cycle, i.e. in 46 ns. This processing speed is independent of the number of features detected in the input image and it therefore represents a very high SIFT throughput, adequate for the most demanding SIFT-based robotic applications. The system can process 70 fps in VGA resolution, while it keeps power dissipation at low levels. Moreover, the proposed implementation achieves high response and repeatability values and its matching ability is directly comparable with floating point software-based SIFT implementations. Design details are given for the combinational and RAM-based circuits forming the SIFT datapath. © 2015 Elsevier B.V. All rights reserved. Source


Kalomiros J.A.,Technological and Educational Institute of Central Macedonia
Proceedings of the 2013 IEEE 7th International Conference on Intelligent Data Acquisition and Advanced Computing Systems, IDAACS 2013 | Year: 2013

High-resolution scale-space scanning is introduced as a feature-probing technique in difference-of-Gaussian detectors. Scans of the feature response are produced versus scale-space parameter σ for different window sizes, for a set of diverse images. Mean repeatability scans are used to select the filter parameters of a reliable Scale-Invariant Feature Transform (SIFT) detector. A simple and hardware-friendly feature descriptor is also proposed and is tested in relation with the proposed optimized detector. This study can guide design optimizations without degradation of the detector response, especially in real-time systems. © 2013 IEEE. Source


Kosmanis T.I.,Alexandrion Technological and Educational Institute | Rekanos I.T.,Aristotle University of Thessaloniki | Tsitsos S.P.,Technological and Educational Institute of Central Macedonia
Applied Computational Electromagnetics Society Journal | Year: 2016

The optimal geometrical design of a ceramic microwave filter according to the specifications of the downlink band of the PCS-1900 mobile communications protocol is investigated in this paper. An efficient combination of the Differential Evolution Algorithm and the Finite Element Method leads to the optimal values of four design parameters. © 2016 ACES. Source


Zampioglou D.,Technological and Educational Institute of Central Macedonia | Kalomiros J.,Technological and Educational Institute of Central Macedonia
Proceedings of the 2013 IEEE 7th International Conference on Intelligent Data Acquisition and Advanced Computing Systems, IDAACS 2013 | Year: 2013

An 'electronic nose' based on a low-cost array of gas-sensors is developed and tested for the detection of Volatile Organic Compounds (VOCs) emanated from samples of the ascomecyte Tuber or truffle. These fungi have highly appreciated gastronomical and nutritive merits and they own a variable characteristic aroma depending on their stage of maturation and place of origin. A data acquisition system is developed and the response of the gas sensors to truffle samples is monitored. Preliminary results show that an intelligent odor-discriminating system based on a gas sensor array is possible and can contribute to the identification and classification of truffles. © 2013 IEEE. Source


Zigirkas G.,Technological and Educational Institute of Central Macedonia | Kalomiros J.,Technological and Educational Institute of Central Macedonia
Proceedings of the 2015 IEEE 8th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, IDAACS 2015 | Year: 2015

A new design for an intelligent soft-start embedded controller for low-voltage three-phase induction motors is presented. The design is based on timer-driven semiconductor switching logic and on a four-rule fuzzy system, all implemented on a low-cost microcontroller. Inductive behavior is well-balanced using voltage sensing closed-loop, providing input to the fuzzy controller. The time-ramp is very predictable and independent of motor load. © 2015 IEEE. Source

Discover hidden collaborations