Current Issue : July - September Volume : 2018 Issue Number : 3 Articles : 5 Articles
Connected component analysis is one of the most fundamental steps used in several image\nprocessing systems. This technique allows for distinguishing and detecting different objects in images\nby assigning a unique label to all pixels that refer to the same object. Most of the previous published\nalgorithms have been designed for implementation by software. However, due to the large number of\nmemory accesses and compare, lookup, and control operations when executed on a general-purpose\nprocessor, they do not satisfy the speed performance required by the next generation high performance\ncomputer vision systems. In this paper, we present the design of a new Connected Component Labeling\nhardware architecture suitable for high performance heterogeneous image processing of embedded\ndesigns. When implemented on a Zynq All Programmable-System on Chip (AP-SOC) 7045 chip,\nthe proposed design allows a throughput rate higher of 220 Mpixels/s to be reached using less than\n18,000 LUTs and 5000 FFs, dissipating about 620 �¼J....
Hybrid electric vehicles are a compromise between traditional vehicles and pure electric\nvehicles and can be part of the solution to the energy shortage problem. Energy management strategies\n(EMSs) are highly related to energy utilization in HEVs� fuel economy. In this research, we have\nemployed a neuro-dynamic programming (NDP) method to simultaneously optimize fuel economy\nand battery state of charge (SOC). In this NDP method, the critic network is a multi-resolution wavelet\nneural network based on the Meyer wavelet function, and the action network is a conventional\nwavelet neural network based on the Morlet function. The weights and parameters of both networks\nare obtained by an algorithm of backpropagation type. The NDP-based EMS has been applied\nto a parallel HEV and compared with a previously reported NDP EMS and a stochastic dynamic\nprograming-based method. Simulation results under ADVISOR2002 have shown that the proposed\nNDP approach achieves better performance than both the methods. These indicate that the proposed\nNDP EMS, and the CWNN and MRWNN, are effective in approximating a nonlinear system....
Today, the demand for continuous monitoring of valuable or safety critical equipment is\nincreasing in many industrial applications due to safety and economical requirements. Therefore,\nreliable in-situ measurement techniques are required for instance in Structural Health Monitoring\n(SHM) as well as process monitoring and control. Here, current challenges are related to the processing\nof sensor data with a high data rate and low latency. In particular, measurement and analyses of\nAcoustic Emission (AE) are widely used for passive, in-situ inspection. Advantages of AE are\nrelated to its sensitivity to different micro-mechanical mechanisms on the material level. However,\nonline processing of AE waveforms is computationally demanding. The related equipment is typically\nbulky, expensive, and not well suited for permanent installation. The contribution of this paper is\nthe development of a Field Programmable Gate Array (FPGA)-based measurement system using\nZedBoard devlopment kit with Zynq-7000 system on chip for embedded implementation of suitable\nonline processing algorithms. This platform comprises a dual-core Advanced Reduced Instruction\nSet Computer Machine (ARM) architecture running a Linux operating system and FPGA fabric.\nA FPGA-based hardware implementation of the discrete wavelet transform is realized to accelerate\nprocessing the AE measurements. Key features of the system are low cost, small form factor, and low\nenergy consumption, which makes it suitable to serve as field-deployed measurement and control\ndevice. For verification of the functionality, a novel automatically realized adjustment of the working\ndistance during pulsed laser ablation in liquids is established as an example. A sample rate of 5 MHz\nis achieved at 16 bit resolution....
The high performance of FPGA (Field Programmable Gate Array) in image processing\napplications is justified by its flexible reconfigurability, its inherent parallel nature and the availability\nof a large amount of internal memories. Lately, the Stochastic Computing (SC) paradigm has been\nfound to be significantly advantageous in certain application domains including image processing\nbecause of its lower hardware complexity and power consumption. However, its viability is deemed\nto be limited due to its serial bitstream processing and excessive run-time requirement for convergence.\nTo address these issues, a novel approach is proposed in this work where an energy-efficient\nimplementation of SC is accomplished by introducing fast-converging Quasi-Stochastic Number\nGenerators (QSNGs) and parallel stochastic bitstream processing, which are well suited to leverage\nFPGA�s reconfigurability and abundant internal memory resources. the proposed approach has\nbeen tested on the Virtex-4 FPGA, and results have been compared with the serial and parallel\nimplementations of conventional stochastic computation using the well-known SC edge detection\nand multiplication circuits. Results prove that by using this approach, execution time, as well\nas the power consumption are decreased by a factor of 3.5 and 4.5 for the edge detection circuit\nand multiplication circuit, respectively....
The rapid development in low-cost sensor and wireless communication technology has\nmade it possible for a large number of devices to coexist and exchange information autonomously.\nIt has been predicted that a substantial number of devices will be able to exchange and provide\ninformation about an environment with the goal of improving our lives, under the well-known\nparadigm of the Internet of Things (IoT). One of the main applications of these kinds of devices is the\nmonitoring of scenarios. In order to improve the current wine elaboration process, this paper presents\na real-time monitoring system to supervise the status of wine casks. We have focused on a special\nkind of white wine, called Fino, principally produced in Andalusia (Southern Spain). The process by\nwhich this kind of wind is monitored is completely different from that of red wine, as the casks are not\ncompletely full and, due to the fact that they are not renewed very often, are more prone to breakage.\nA smart cork prototype monitors the structural health, the ullage, and the level of light inside the\ncask and the room temperature. The advantage of this smart cork is that it allows winemakers to\nmonitor, in real time, the status of each wine cask so that, if an issue is detected (e.g., a crack appears\nin the cask), they can act immediately to resolve it. Moreover, abnormal parameters or incorrect\nenvironmental conditions can be detected in time before the wine loses its desired qualities. The\nsystem has been tested in ââ?¬Å?Bodegas San Acacio,ââ?¬Â a winery based in Montemayor, a town in the\nnorth of Andalusia. Results show that the use of such a system can provide a solution that tracks the\nevolution and assesses the suitability of the delicate wine elaboration process in real time, which is\nespecially important for the kind of wine considered in this paper....
Loading....