首页 > 最新文献

Proceedings Fifth IEEE International Workshop on Computer Architectures for Machine Perception最新文献

英文 中文
Fast stereo matching for the VIDET system using a general purpose processor with multimedia extensions 快速立体匹配的VIDET系统使用通用处理器与多媒体扩展
L. D. Stefano, S. Mattoccia
The ever-increasing speed of current general purpose processors, together with architectural enhancements such as multimedia-oriented instruction set extensions, allow for deploying standard PC-based systems in a number of com-putationally intensive computer vision tasks. This paper de-scribes the PC-based real-time stereo vision system devel-oped within the VIDET project, which is a research project aimed at the development of a mobility aid for the visu-ally impaired. VIDET's approach consists in the conversion of depth data gathered through a stereo vision system into a 3D model perceivable by the user by means of a wire-actuated haptic interface. The developed stereo matching algorithm makes massive use of recursion and multime-dia instructions to achieve the performance figures needed to sustain user's real-time interaction with the 3D model through the haptic interface.
当前通用处理器的速度不断提高,加上架构上的增强,如面向多媒体的指令集扩展,允许在许多计算密集型的计算机视觉任务中部署标准的基于pc的系统。本文描述了在VIDET项目中开发的基于pc的实时立体视觉系统,VIDET项目是一个旨在为视障人士开发移动辅助设备的研究项目。VIDET的方法包括将通过立体视觉系统收集的深度数据转换为用户可以通过线驱动的触觉界面感知的3D模型。所开发的立体匹配算法大量使用递归和多媒体指令来实现通过触觉界面维持用户与三维模型实时交互所需的性能数字。
{"title":"Fast stereo matching for the VIDET system using a general purpose processor with multimedia extensions","authors":"L. D. Stefano, S. Mattoccia","doi":"10.1109/CAMP.2000.875995","DOIUrl":"https://doi.org/10.1109/CAMP.2000.875995","url":null,"abstract":"The ever-increasing speed of current general purpose processors, together with architectural enhancements such as multimedia-oriented instruction set extensions, allow for deploying standard PC-based systems in a number of com-putationally intensive computer vision tasks. This paper de-scribes the PC-based real-time stereo vision system devel-oped within the VIDET project, which is a research project aimed at the development of a mobility aid for the visu-ally impaired. VIDET's approach consists in the conversion of depth data gathered through a stereo vision system into a 3D model perceivable by the user by means of a wire-actuated haptic interface. The developed stereo matching algorithm makes massive use of recursion and multime-dia instructions to achieve the performance figures needed to sustain user's real-time interaction with the 3D model through the haptic interface.","PeriodicalId":282003,"journal":{"name":"Proceedings Fifth IEEE International Workshop on Computer Architectures for Machine Perception","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116970755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 42
Compressed-domain classification of texture images 纹理图像的压缩域分类
B. Wilson, M. Bayoumi
Traditional decompress-process methods for texture feature extraction consume valuable time and memory resources. This paper proposes a method for calculating wavelet energy texture features directly from a wavelet-compressed symbol stream. The proposed method requires little decompression and results in a technique that is efficient and requires less memory than traditional approaches. This reduction is accomplished through the elimination of both multiplication operations and the storage of zero-valued coefficients, which have no effect on these features. The developed algorithm has been implemented at various compression ratios, and in each case, the classification results are nearly identical to those obtained with the traditional method.
传统的纹理特征提取解压缩方法消耗了宝贵的时间和内存资源。提出了一种直接从小波压缩符号流中计算小波能量纹理特征的方法。所提出的方法只需要很少的解压缩,并且比传统方法效率更高,需要更少的内存。这种减少是通过消除乘法操作和零值系数的存储来实现的,这对这些特征没有影响。该算法在不同的压缩比下实现,每种情况下的分类结果与传统方法的分类结果几乎相同。
{"title":"Compressed-domain classification of texture images","authors":"B. Wilson, M. Bayoumi","doi":"10.1109/CAMP.2000.875994","DOIUrl":"https://doi.org/10.1109/CAMP.2000.875994","url":null,"abstract":"Traditional decompress-process methods for texture feature extraction consume valuable time and memory resources. This paper proposes a method for calculating wavelet energy texture features directly from a wavelet-compressed symbol stream. The proposed method requires little decompression and results in a technique that is efficient and requires less memory than traditional approaches. This reduction is accomplished through the elimination of both multiplication operations and the storage of zero-valued coefficients, which have no effect on these features. The developed algorithm has been implemented at various compression ratios, and in each case, the classification results are nearly identical to those obtained with the traditional method.","PeriodicalId":282003,"journal":{"name":"Proceedings Fifth IEEE International Workshop on Computer Architectures for Machine Perception","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131932313","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Multi-sensors and environment simulator for collision avoidance applications 用于避碰的多传感器和环境模拟器
S. Bouaziz, M. Fan, R. Reynaud, T. Maurin
The "PICAR" project is based on "Prometheus Prochip" experience and results. The goal is to design an embedded multi sensors collision avoidance system for automotive application. The system includes sensors like video camera, ultrasonic sensors, a PC hardware computer, a CAN/sup 2/ network and a dedicated software for signal and image processing, data fusion and AI expert system. The design of such a system is difficult under real time constraints. Therefore, a simulator is a good solution to test different parts of the system and then to help to choose the overall architecture. However simulating all the embedded architecture in real-time becomes a very complex work. It is necessary to have an environment simulator where sensors can be virtually implemented. The data are then processed leading to results without hardware costs. The designed environment software allows the simulation of physical sensors, and also the emulation of these sensors. The simulator is interfaced to the physical embedded hardware by a network bridge. So, we can emulate some sensors to experiment data processing on the physical embedded PICAR computer. This paper presents the physical smart car PICAR and its embedded system, the virtual world simulator. We explain how we can mix the virtual world (produced by virtual sensors) and real world (physical embedded system) to implement some scenarios (like automatic parking) and to validate the physical architecture. An alternate goal can be to design customized sensors.
“PICAR”项目是基于“普罗米修斯Prochip”项目的经验和成果。目标是设计一种嵌入式多传感器汽车防撞系统。该系统包括摄像机、超声波传感器、PC硬件计算机、CAN/sup 2/网络以及用于信号和图像处理、数据融合和人工智能专家系统的专用软件。在实时性的限制下,这种系统的设计是困难的。因此,模拟器是一个很好的解决方案,可以测试系统的不同部分,然后帮助选择整体架构。然而,实时模拟所有嵌入式体系结构是一项非常复杂的工作。有必要有一个环境模拟器,传感器可以虚拟实现。然后对数据进行处理,从而产生不需要硬件成本的结果。所设计的环境软件允许对物理传感器进行仿真,也可以对这些传感器进行仿真。仿真器通过网桥连接到物理嵌入式硬件。因此,我们可以模拟一些传感器,在物理嵌入式PICAR计算机上进行数据处理实验。本文介绍了物理智能汽车PICAR及其嵌入式系统虚拟世界模拟器。我们解释了如何混合虚拟世界(由虚拟传感器产生)和现实世界(物理嵌入式系统)来实现一些场景(如自动停车)并验证物理架构。另一个目标是设计定制的传感器。
{"title":"Multi-sensors and environment simulator for collision avoidance applications","authors":"S. Bouaziz, M. Fan, R. Reynaud, T. Maurin","doi":"10.1109/CAMP.2000.875968","DOIUrl":"https://doi.org/10.1109/CAMP.2000.875968","url":null,"abstract":"The \"PICAR\" project is based on \"Prometheus Prochip\" experience and results. The goal is to design an embedded multi sensors collision avoidance system for automotive application. The system includes sensors like video camera, ultrasonic sensors, a PC hardware computer, a CAN/sup 2/ network and a dedicated software for signal and image processing, data fusion and AI expert system. The design of such a system is difficult under real time constraints. Therefore, a simulator is a good solution to test different parts of the system and then to help to choose the overall architecture. However simulating all the embedded architecture in real-time becomes a very complex work. It is necessary to have an environment simulator where sensors can be virtually implemented. The data are then processed leading to results without hardware costs. The designed environment software allows the simulation of physical sensors, and also the emulation of these sensors. The simulator is interfaced to the physical embedded hardware by a network bridge. So, we can emulate some sensors to experiment data processing on the physical embedded PICAR computer. This paper presents the physical smart car PICAR and its embedded system, the virtual world simulator. We explain how we can mix the virtual world (produced by virtual sensors) and real world (physical embedded system) to implement some scenarios (like automatic parking) and to validate the physical architecture. An alternate goal can be to design customized sensors.","PeriodicalId":282003,"journal":{"name":"Proceedings Fifth IEEE International Workshop on Computer Architectures for Machine Perception","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130477174","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 4
Hardware prefetching techniques for cache memories in multimedia applications 多媒体应用中缓存存储器的硬件预取技术
R. Cucchiara, M. Piccardi, A. Prati
The workload of multimedia applications has a strong impact on cache memory performance, since the locality of memory references embedded in multimedia programs differs from that of traditional programs. In many cases, standard cache memory organization achieves poorer performance when used for multimedia. A widely explored approach to improve cache performance is hardware prefetching that allows the pre-loading of data in the cache before they are referenced. However, existing hardware prefetching approaches partially miss the potential performance improvement, since they are not tailored to multimedia locality. In this paper we propose novel effective approaches to hardware prefetching to be used in image processing programs for multimedia. Experimental results are reported for a suite of multimedia image processing programs including convolutions with kernels, MPEG-2 decoding, and edge chain coding.
多媒体应用程序的工作负载对缓存性能有很大的影响,因为多媒体程序中嵌入的内存引用的位置与传统程序不同。在许多情况下,标准缓存存储器组织在用于多媒体时性能较差。一种被广泛探索的提高缓存性能的方法是硬件预取,它允许在引用数据之前在缓存中预加载数据。然而,现有的硬件预取方法在一定程度上错过了潜在的性能改进,因为它们没有针对多媒体局部性进行定制。本文提出了一种新的有效的硬件预取方法,用于多媒体图像处理程序。本文报道了一套多媒体图像处理程序的实验结果,包括带核卷积、MPEG-2解码和边缘链编码。
{"title":"Hardware prefetching techniques for cache memories in multimedia applications","authors":"R. Cucchiara, M. Piccardi, A. Prati","doi":"10.1109/CAMP.2000.875990","DOIUrl":"https://doi.org/10.1109/CAMP.2000.875990","url":null,"abstract":"The workload of multimedia applications has a strong impact on cache memory performance, since the locality of memory references embedded in multimedia programs differs from that of traditional programs. In many cases, standard cache memory organization achieves poorer performance when used for multimedia. A widely explored approach to improve cache performance is hardware prefetching that allows the pre-loading of data in the cache before they are referenced. However, existing hardware prefetching approaches partially miss the potential performance improvement, since they are not tailored to multimedia locality. In this paper we propose novel effective approaches to hardware prefetching to be used in image processing programs for multimedia. Experimental results are reported for a suite of multimedia image processing programs including convolutions with kernels, MPEG-2 decoding, and edge chain coding.","PeriodicalId":282003,"journal":{"name":"Proceedings Fifth IEEE International Workshop on Computer Architectures for Machine Perception","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129803418","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Recovering 3-D egomotion parameters from optic flow: from structural principles to analog architectures 从光流中恢复三维自我运动参数:从结构原理到模拟架构
S. Sabatini, P. Cavalleri, F. Solari, G. Bisio
A computational architecture for direct estimation of heading direction from optic flow is proposed. By representing optic flow information as undulatory spatiotemporal patterns, global first-order differential analysis of the optic flow is reconducted to spatiotemporal filtering operations with local kernels characterized with respect to the fixation point(gaze). These operations can be mapped with high efficiency on analog architectures based on structured arrays of cells reacting collectively to spatiotemporal input stimuli. By observing the overall distribution of cells' activity, it is possible to gain information on the orientation of the heading in the retinal reference frame and on the angle between the heading and the gaze directions.
提出了一种利用光流直接估计航向的计算体系结构。通过将光流信息表示为波动的时空模式,将光流的全局一阶微分分析重新进行为具有注视点(凝视)特征的局部核的时空滤波操作。这些操作可以高效地映射到基于细胞对时空输入刺激集体反应的结构化阵列的模拟架构上。通过观察细胞活动的总体分布,可以获得视网膜参照系中头部方向的信息,以及头部与凝视方向之间的角度。
{"title":"Recovering 3-D egomotion parameters from optic flow: from structural principles to analog architectures","authors":"S. Sabatini, P. Cavalleri, F. Solari, G. Bisio","doi":"10.1109/CAMP.2000.875966","DOIUrl":"https://doi.org/10.1109/CAMP.2000.875966","url":null,"abstract":"A computational architecture for direct estimation of heading direction from optic flow is proposed. By representing optic flow information as undulatory spatiotemporal patterns, global first-order differential analysis of the optic flow is reconducted to spatiotemporal filtering operations with local kernels characterized with respect to the fixation point(gaze). These operations can be mapped with high efficiency on analog architectures based on structured arrays of cells reacting collectively to spatiotemporal input stimuli. By observing the overall distribution of cells' activity, it is possible to gain information on the orientation of the heading in the retinal reference frame and on the angle between the heading and the gaze directions.","PeriodicalId":282003,"journal":{"name":"Proceedings Fifth IEEE International Workshop on Computer Architectures for Machine Perception","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133164969","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
An FPGA architecture for high speed edge and corner detection 一种用于高速边缘和拐角检测的FPGA架构
C. Torres-Huitzil, M. Arias-Estrada
This paper presents an FPGA based architecture for high speed edge and corner detection. Applications targeted are in high speed computer vision (i.e. more than 100 images per second). The architecture design was centred on the minimization on the number of accesses to the image memory. The design is based on parallel modules with internal pipeline operation in order to improve its performance. The architecture design, FPGA resources utilization, results, and real time performance are discussed.
本文提出了一种基于FPGA的高速边缘和拐角检测体系结构。目标应用是高速计算机视觉(即每秒超过100张图像)。架构设计以最小化对图像存储器的访问次数为中心。为了提高其性能,本设计采用了并行模块和内部流水线操作。讨论了体系结构设计、FPGA资源利用率、结果和实时性能。
{"title":"An FPGA architecture for high speed edge and corner detection","authors":"C. Torres-Huitzil, M. Arias-Estrada","doi":"10.1109/CAMP.2000.875965","DOIUrl":"https://doi.org/10.1109/CAMP.2000.875965","url":null,"abstract":"This paper presents an FPGA based architecture for high speed edge and corner detection. Applications targeted are in high speed computer vision (i.e. more than 100 images per second). The architecture design was centred on the minimization on the number of accesses to the image memory. The design is based on parallel modules with internal pipeline operation in order to improve its performance. The architecture design, FPGA resources utilization, results, and real time performance are discussed.","PeriodicalId":282003,"journal":{"name":"Proceedings Fifth IEEE International Workshop on Computer Architectures for Machine Perception","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121933380","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 40
Study of a parallel CBIR implementation using MPI 基于MPI的并行CBIR实现研究
J. L. Bosque, O. D. Robles, Angel Rodríguez, L. Pastor
This paper presents a parallel implementation of a content based information retrieval (CBIR) system which deals with an image database composed of data from over 29 million bidimensional RGB images, which would be equivalent to 1.45 TB of graphical data. The application has been designed for a distributed memory multiprocessor environment, and has been implemented in a cluster of twenty five PCs using MPI. The paradigm that best fits the problem's needs is a farm based solution: a master process distributes the work load between the slave processes, and when these have finished, the master recollects the partial results computed on each slave process. In order to evaluate this solution, the experimental results have been compared with those achieved using a Silicon Graphics Origin 2000, a shared memory machine with eight processors. This paper analyzes the performances offered by both approaches from the viewpoints of speed, price and scalability, presenting the conclusions that can be extracted from the results' comparison.
本文提出了一个基于内容的信息检索(CBIR)系统的并行实现,该系统处理由2900多万张二维RGB图像组成的图像数据库,相当于1.45 TB的图形数据。该应用程序是为分布式内存多处理器环境设计的,并使用MPI在25台pc的集群中实现。最适合问题需求的范例是基于场的解决方案:主进程在从属进程之间分配工作负载,当这些进程完成时,主进程重新收集在每个从属进程上计算的部分结果。为了评估该解决方案,实验结果与使用硅图形原点2000的结果进行了比较,硅图形原点2000是一个具有8个处理器的共享内存机。本文从速度、价格和可扩展性的角度分析了两种方法所提供的性能,并从结果的比较中得出结论。
{"title":"Study of a parallel CBIR implementation using MPI","authors":"J. L. Bosque, O. D. Robles, Angel Rodríguez, L. Pastor","doi":"10.1109/CAMP.2000.875978","DOIUrl":"https://doi.org/10.1109/CAMP.2000.875978","url":null,"abstract":"This paper presents a parallel implementation of a content based information retrieval (CBIR) system which deals with an image database composed of data from over 29 million bidimensional RGB images, which would be equivalent to 1.45 TB of graphical data. The application has been designed for a distributed memory multiprocessor environment, and has been implemented in a cluster of twenty five PCs using MPI. The paradigm that best fits the problem's needs is a farm based solution: a master process distributes the work load between the slave processes, and when these have finished, the master recollects the partial results computed on each slave process. In order to evaluate this solution, the experimental results have been compared with those achieved using a Silicon Graphics Origin 2000, a shared memory machine with eight processors. This paper analyzes the performances offered by both approaches from the viewpoints of speed, price and scalability, presenting the conclusions that can be extracted from the results' comparison.","PeriodicalId":282003,"journal":{"name":"Proceedings Fifth IEEE International Workshop on Computer Architectures for Machine Perception","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117052084","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 13
A high speed flat CORDIC based neuron with multi-level activation function for robust pattern recognition 基于多级激活函数的高速平面CORDIC神经元鲁棒模式识别
Bimal Gisutham, T. Srikanthan, V. Asari
Implementing Neural Networks in hardware has been a major problem due to the complexity involved in generating non-linear functions. The high hardware costs incurred in real time applications can be substantially reduced by adopting a suitable reuse methodology of the neurons. In addition, neurons with high speed of operation are necessitated to realise hardware efficient real time pattern recognition for images with higher resolution. In this regard, the response time and area of a neuron becomes critical in realising VLSI efficient neural networks. In this paper, the digital architecture of a multiple valued logic neuron has been proposed to realise a neural network implementation for real-time pattern recognition purposes. The proposed neuron uses a multilevel sigmoidal function as the activation function. Flat CORDIC, a new variation of the CORDIC algorithm, has been employed to generate the complex multi-level activation function in a VLSI efficient manner. The proposed neuron operates with a 200 MHz clock and has significant hardware and latency savings when compared to conventional CORDIC based neurons.
由于生成非线性函数的复杂性,在硬件上实现神经网络一直是一个主要问题。采用合适的神经元重用方法可以大大降低实时应用中高昂的硬件成本。此外,为了实现对高分辨率图像的硬件高效实时模式识别,需要高速运行的神经元。在这方面,响应时间和神经元的面积成为实现超大规模集成电路高效神经网络的关键。本文提出了一种多值逻辑神经元的数字结构,以实现实时模式识别的神经网络实现。该神经元采用多级s型函数作为激活函数。扁平CORDIC是CORDIC算法的一种新变体,用于在VLSI中高效地生成复杂的多级激活函数。与传统的基于CORDIC的神经元相比,所提出的神经元以200 MHz的时钟运行,具有显着的硬件和延迟节省。
{"title":"A high speed flat CORDIC based neuron with multi-level activation function for robust pattern recognition","authors":"Bimal Gisutham, T. Srikanthan, V. Asari","doi":"10.1109/CAMP.2000.875962","DOIUrl":"https://doi.org/10.1109/CAMP.2000.875962","url":null,"abstract":"Implementing Neural Networks in hardware has been a major problem due to the complexity involved in generating non-linear functions. The high hardware costs incurred in real time applications can be substantially reduced by adopting a suitable reuse methodology of the neurons. In addition, neurons with high speed of operation are necessitated to realise hardware efficient real time pattern recognition for images with higher resolution. In this regard, the response time and area of a neuron becomes critical in realising VLSI efficient neural networks. In this paper, the digital architecture of a multiple valued logic neuron has been proposed to realise a neural network implementation for real-time pattern recognition purposes. The proposed neuron uses a multilevel sigmoidal function as the activation function. Flat CORDIC, a new variation of the CORDIC algorithm, has been employed to generate the complex multi-level activation function in a VLSI efficient manner. The proposed neuron operates with a 200 MHz clock and has significant hardware and latency savings when compared to conventional CORDIC based neurons.","PeriodicalId":282003,"journal":{"name":"Proceedings Fifth IEEE International Workshop on Computer Architectures for Machine Perception","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115702180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 14
Examples of image processing to benefit from an asynchronous implementation 图像处理的例子,以受益于异步实现
E. Senn, B. Zavidovique
This paper describes how asynchronous techniques make easier timing in an image processing computer. It outlines an original machine architecture, and explains why it is asynchronous: the router circuit supports the asynchronism by itself. Its structure and behavior are sketched. Our method for self-timed design, its salient features and contributions to the typical asynchronous circuit design flow are introduced. The VLSI implementation and the cell set design, including full-custom self-timed asynchronous cells, are detailed. Measured circuit's performances are presented, as well as global processing and communication performances for different image processing algorithms. The gain from asynchronism is exhibited.
本文描述了异步技术如何使图像处理计算机中的定时变得更容易。它概述了一个原始的机器架构,并解释了为什么它是异步的:路由器电路本身支持异步。简述了它的结构和行为。介绍了我们的自定时设计方法,它的主要特点和对典型异步电路设计流程的贡献。详细介绍了VLSI实现和单元集设计,包括全自定义自定时异步单元。给出了测量电路的性能,以及不同图像处理算法的全局处理和通信性能。显示了异步的增益。
{"title":"Examples of image processing to benefit from an asynchronous implementation","authors":"E. Senn, B. Zavidovique","doi":"10.1109/CAMP.2000.875986","DOIUrl":"https://doi.org/10.1109/CAMP.2000.875986","url":null,"abstract":"This paper describes how asynchronous techniques make easier timing in an image processing computer. It outlines an original machine architecture, and explains why it is asynchronous: the router circuit supports the asynchronism by itself. Its structure and behavior are sketched. Our method for self-timed design, its salient features and contributions to the typical asynchronous circuit design flow are introduced. The VLSI implementation and the cell set design, including full-custom self-timed asynchronous cells, are detailed. Measured circuit's performances are presented, as well as global processing and communication performances for different image processing algorithms. The gain from asynchronism is exhibited.","PeriodicalId":282003,"journal":{"name":"Proceedings Fifth IEEE International Workshop on Computer Architectures for Machine Perception","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125272409","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Parallel segmentation based on topology with the associative net model 基于关联网络模型的拓扑并行分割
D. Dulac, Gilles Bertrand, S. Guezguez
This paper presents an implementation of a topological segmentation on a SIMD massively parallel computer based on reconfigurability and asynchronism: Associative Mesh. This architecture provides powerful computational primitives that can apply an associative operator over the connex sets of a graph. So, basic primitives combine communications and computations. These primitives can be easily and efficiently realised in hardware by means of asynchronous operations and are adapted to a large number of image analysis primitives. We try to show the adequacy of Associative Mesh computing model with the different data movements that are generated by the several approaches of the image analysis. We are interested here with a new approach: image topology. We indicate how to get an homotopic kernel and a leveling kernel with parallel algorithms. Such kernels may be seen as "ultimate" topological simplifications of an image. This kind of image is similar to a very good split because it is based on topological information of image. We show one example of merge: we implement a method segmenting without the need of defining and tuning parameters.
本文提出了一种基于可重构性和异步性的拓扑分割在SIMD大规模并行计算机上的实现:关联网格。该体系结构提供了强大的计算原语,可以在图的连接集上应用关联运算符。因此,基本原语结合了通信和计算。这些原语可以通过异步操作在硬件中轻松有效地实现,并且适用于大量的图像分析原语。我们试图通过图像分析的几种方法产生的不同数据移动来显示关联网格计算模型的充分性。我们感兴趣的是一种新方法:图像拓扑。给出了如何用并行算法得到一个同伦核和一个均衡核。这样的核可以看作是图像的“终极”拓扑简化。这种基于图像拓扑信息的图像分割方法类似于一种很好的分割方法。我们展示了一个合并的例子:我们实现了一个方法分段,而不需要定义和调优参数。
{"title":"Parallel segmentation based on topology with the associative net model","authors":"D. Dulac, Gilles Bertrand, S. Guezguez","doi":"10.1109/CAMP.2000.875963","DOIUrl":"https://doi.org/10.1109/CAMP.2000.875963","url":null,"abstract":"This paper presents an implementation of a topological segmentation on a SIMD massively parallel computer based on reconfigurability and asynchronism: Associative Mesh. This architecture provides powerful computational primitives that can apply an associative operator over the connex sets of a graph. So, basic primitives combine communications and computations. These primitives can be easily and efficiently realised in hardware by means of asynchronous operations and are adapted to a large number of image analysis primitives. We try to show the adequacy of Associative Mesh computing model with the different data movements that are generated by the several approaches of the image analysis. We are interested here with a new approach: image topology. We indicate how to get an homotopic kernel and a leveling kernel with parallel algorithms. Such kernels may be seen as \"ultimate\" topological simplifications of an image. This kind of image is similar to a very good split because it is based on topological information of image. We show one example of merge: we implement a method segmenting without the need of defining and tuning parameters.","PeriodicalId":282003,"journal":{"name":"Proceedings Fifth IEEE International Workshop on Computer Architectures for Machine Perception","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114691387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 5
期刊
Proceedings Fifth IEEE International Workshop on Computer Architectures for Machine Perception
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1