发布求助
文献互助 智能选刊 最新文献

Proceedings of Conference on Computer Architectures for Machine Perception最新文献

筛选
英文 中文
An efficient digital architecture for character recognition 一种高效的字符识别数字体系结构
Proceedings of Conference on Computer Architectures for Machine Perception Pub Date : 1995-09-18 DOI: 10.1109/CAMP.1995.521031
M. Gioiello, F. Sorbello, A. Tarantino, G. Vassallo
{"title":"An efficient digital architecture for character recognition","authors":"M. Gioiello, F. Sorbello, A. Tarantino, G. Vassallo","doi":"10.1109/CAMP.1995.521031","DOIUrl":"https://doi.org/10.1109/CAMP.1995.521031","url":null,"abstract":"We introduce a new digital neural architecture designed for automatic hand-written characters recognition. The architecture implements a two-layer perceptron off-line trained by conjugate gradient descent algorithm and the final weights are quantized and stored in a RAM. The architecture was developed and tested using the VHDL Alliance 2.0 CAD System simulator: it is easy to implement using standard VLSI technologies and may be used to deal with multi-level inputs.","PeriodicalId":277209,"journal":{"name":"Proceedings of Conference on Computer Architectures for Machine Perception","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116504175","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
Implementation of low level image processing algorithms on a reconfigurable perception system 在可重构感知系统上实现低级图像处理算法
Proceedings of Conference on Computer Architectures for Machine Perception Pub Date : 1995-09-18 DOI: 10.1109/CAMP.1995.521054
M. Méribout, K. Hou
{"title":"Implementation of low level image processing algorithms on a reconfigurable perception system","authors":"M. Méribout, K. Hou","doi":"10.1109/CAMP.1995.521054","DOIUrl":"https://doi.org/10.1109/CAMP.1995.521054","url":null,"abstract":"The development of VLSI technology allows an increase of the computing power of intelligent machines treating complex applications with a low cost. However, in spite of the success which has been achieved in many specific areas, vision problems are often ill defined, ill posed or computationally intractable (A. Rosenfield, 1993). This constrains the designers to limit the domain of applications for applying adequate computer power which can be inefficient if more powerful algorithms against new constraints come into view. We present a low cost perception system that performs a number of algorithms, such as a real time edge detection and motion estimation and high speed image compression. The main robustness features of the system are its flexibility, reconfigurability, extensibility and modularity, making it easily suited to a large field of applications. The design is based on the needs of every level of image processing in communication, power computing, input data flow and storage features.","PeriodicalId":277209,"journal":{"name":"Proceedings of Conference on Computer Architectures for Machine Perception","volume":"211 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123268054","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: 8
A miniature retina-based AGV called VAMPIRE 一种名为“吸血鬼”的微型视网膜AGV
Proceedings of Conference on Computer Architectures for Machine Perception Pub Date : 1995-09-18 DOI: 10.1109/CAMP.1995.521016
L. Carnapete, P. Nguyen, R. Nguyen, T. Bernard
{"title":"A miniature retina-based AGV called VAMPIRE","authors":"L. Carnapete, P. Nguyen, R. Nguyen, T. Bernard","doi":"10.1109/CAMP.1995.521016","DOIUrl":"https://doi.org/10.1109/CAMP.1995.521016","url":null,"abstract":"From a robot vision point of view, none of the individual visual operators presented features much originality. However they all make up a complete perceptual task, allowing a miniature vehicle to follow a specific textured target. Furthermore, most of them are performed inside a programmable artificial retina that fits, together with its controller, within a few cm/sup 3/ and make the vehicle a miniature autonomous one. After a presentation of the scientific motivations, we describe the whole process and its implementation and we take the opportunity through the elementary steps to illustrate the generic issues of such retina based vision systems.","PeriodicalId":277209,"journal":{"name":"Proceedings of Conference on Computer Architectures for Machine Perception","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121719757","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: 6
An experiment of surface recognition by neural trees 基于神经树的表面识别实验
Proceedings of Conference on Computer Architectures for Machine Perception Pub Date : 1995-09-18 DOI: 10.1109/CAMP.1995.521070
S. Iverson, O. Johnson, G. G. Pieroni
{"title":"An experiment of surface recognition by neural trees","authors":"S. Iverson, O. Johnson, G. G. Pieroni","doi":"10.1109/CAMP.1995.521070","DOIUrl":"https://doi.org/10.1109/CAMP.1995.521070","url":null,"abstract":"The recognition process of objects represented by range data is based on the description of their surfaces. The most popular method for doing that consists in decomposing the surface into regions holding the same differential properties. After successfully performing that task, a high level vision procedure for relating the various morphological segments has to be constructed. The decomposition of the surface is generally performed by calculating the functions K and H in any point and labeling the surface pixels according to the values of those functions. This paper describes the main lines of a surface recognition system based on computing structures called neural trees. Encodings of local samples of surfaces are used as input to a neural tree generator which is subsequently used to forecast global contours from local samples. Various noise levels are used in the training exercise. Experiments in varying the training order, the tree structure and the surface sampling method are performed in order to determine the resilience of such structures as global recognizers. Tree fan-out is studied in some detail. Binary and multi-class tree organizations are studied as well as a hybrid tree structure which combines sub-nets which perform n-way classification followed by binary sub-nets which deal with classified and misclassified patterns.","PeriodicalId":277209,"journal":{"name":"Proceedings of Conference on Computer Architectures for Machine Perception","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125303666","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: 2
Obstacle avoidance and motion-induced navigation 避障和运动诱导导航
Proceedings of Conference on Computer Architectures for Machine Perception Pub Date : 1995-09-18 DOI: 10.1109/CAMP.1995.521063
A. Yakovleff, D. Abbott, X. T. Nguyen, K. Eshraghian
{"title":"Obstacle avoidance and motion-induced navigation","authors":"A. Yakovleff, D. Abbott, X. T. Nguyen, K. Eshraghian","doi":"10.1109/CAMP.1995.521063","DOIUrl":"https://doi.org/10.1109/CAMP.1995.521063","url":null,"abstract":"In nature, the visual detection of motion appears to be used in a variety of tasks, ranging from collision avoidance to posture maintenance. Many insects seem to rely primarily on information provided by an array of elementary movement detectors in order to navigate. Moreover, experimental evidence suggests that motion information is interpreted at an early stage of the insect visual system, and may be closely linked to motor control. A motion detector, whose design is based on some of the characteristics of the insect visual system, has been implemented on a single VLSI chip. This paper shows the manner in which motion information, provided by the chip in real-time, may be utilised by the control system of an autonomous vehicle in low-level perceptual tasks.","PeriodicalId":277209,"journal":{"name":"Proceedings of Conference on Computer Architectures for Machine Perception","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128937267","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: 18
A VLSI chip for computing the medial axis transform of an image 一种用于计算图像中轴变换的VLSI芯片
Proceedings of Conference on Computer Architectures for Machine Perception Pub Date : 1995-09-18 DOI: 10.1109/CAMP.1995.521017
N. Ranganathan, K. B. Doreswamy
{"title":"A VLSI chip for computing the medial axis transform of an image","authors":"N. Ranganathan, K. B. Doreswamy","doi":"10.1109/CAMP.1995.521017","DOIUrl":"https://doi.org/10.1109/CAMP.1995.521017","url":null,"abstract":"We describe a new special purpose VLSI architecture for computing the medial axis transform of an image. The architecture is systolic and is based on an algorithm that achieves a high degree of parallelism. The proposed algorithm computes the skeleton of multiple objects in an image in linear time by making 2 scans over the 4 distance transform of the image. The algorithm is mapped onto a linear systolic array of simple processing elements (PEs) and for an N/spl times/N image, the architecture requires N PE's. The entire array can be realized in a single VLSI chip. The proposed hardware can perform thinning on a 512/spl times/512 image in 2.59 msec and on a 256/spl times/256 image in 0.327 msec. A prototype CMOS VLSI chip implementing the proposed architecture has been designed and verified.","PeriodicalId":277209,"journal":{"name":"Proceedings of Conference on Computer Architectures for Machine Perception","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132812892","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: 8
Real-time quantized optical flow 实时量化光流
Proceedings of Conference on Computer Architectures for Machine Perception Pub Date : 1995-09-18 DOI: 10.1109/CAMP.1995.521028
Ted Camus
{"title":"Real-time quantized optical flow","authors":"Ted Camus","doi":"10.1109/CAMP.1995.521028","DOIUrl":"https://doi.org/10.1109/CAMP.1995.521028","url":null,"abstract":"Algorithms based on the correlation of image patches can be robust in practice but are computationally intensive due to the computational complexity of their search-based nature. Performing the search over time instead of over space is linear in nature, rather than quadratic, and results in a very efficient algorithm. This, combined with implementations which are highly efficient on standard computing hardware, yields performance of over 5 frames per second on a scientific workstation. Although the resulting velocities are quantized with resulting quantization error, they have been shown to be sufficiently accurate for many robotic vision tasks such as time-to-collision and robotic navigation. Thus, this algorithm is highly suitable for real-time robotic vision research.","PeriodicalId":277209,"journal":{"name":"Proceedings of Conference on Computer Architectures for Machine Perception","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128145367","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: 111
A fast asynchronous algorithm for linear feature extraction on IBM SP-2 基于IBM SP-2的快速异步线性特征提取算法
Proceedings of Conference on Computer Architectures for Machine Perception Pub Date : 1995-09-18 DOI: 10.1109/CAMP.1995.521053
Yongwha Chung, V. Prasanna, Cho-Li Wang
{"title":"A fast asynchronous algorithm for linear feature extraction on IBM SP-2","authors":"Yongwha Chung, V. Prasanna, Cho-Li Wang","doi":"10.1109/CAMP.1995.521053","DOIUrl":"https://doi.org/10.1109/CAMP.1995.521053","url":null,"abstract":"We present a fast parallel implementation of linear feature extraction on IBM SP-2. We first analyze the machine features and the problem characteristics to understand the overheads in parallel solutions to the problem. Based on these, we propose an asynchronous algorithm which enhances processor utilization and overlaps communication with computation by maintaining algorithmic threads in each processing node. Our implementation shows that, given a 512/spl times/512 image, the linear feature extraction task can be performed in 0.065 seconds on a SP-2 having 64 processing nodes. A serial implementation takes 3.45 seconds on a single processing node of SP-2. A previous implementation on CM-5 takes 0.1 second on a partition of 512 processing nodes. Experimental results on various sizes of images using 4, 8, 16, 32, and 64 processing nodes are also reported.","PeriodicalId":277209,"journal":{"name":"Proceedings of Conference on Computer Architectures for Machine Perception","volume":"44 8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132076524","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: 15
Software data prefetching to reduce data reloading overhead 软件数据预取，减少数据重新加载开销
Proceedings of Conference on Computer Architectures for Machine Perception Pub Date : 1995-09-18 DOI: 10.1109/CAMP.1995.521039
Se-Jin Hwang, Myong-Soon Park
{"title":"Software data prefetching to reduce data reloading overhead","authors":"Se-Jin Hwang, Myong-Soon Park","doi":"10.1109/CAMP.1995.521039","DOIUrl":"https://doi.org/10.1109/CAMP.1995.521039","url":null,"abstract":"In this paper, we propose a software data prefetching mechanism to insert prefetching instructions efficiently into a loop. Proposed mechanism analyzes the array reference pattern, and inserts prefetching instructions into the loop according to the results of the analysis. Analyzing the loop, it considers cache size and the number of array elements that will be used to exploit reuse property. However, in case that it is hard to benefit by the reuse due to the large number of array elements, proposed mechanism reorganizes the loop properly to reduce the overhead of reloading array elements that had been pushed out from the cache.","PeriodicalId":277209,"journal":{"name":"Proceedings of Conference on Computer Architectures for Machine Perception","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128672957","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
Scheduling of low level computer vision algorithms on networks of heterogeneous machines 基于异构机器网络的低级计算机视觉算法调度
Proceedings of Conference on Computer Architectures for Machine Perception Pub Date : 1995-09-18 DOI: 10.1109/CAMP.1995.521059
A. Nolan, B. Everding, W. Wee
{"title":"Scheduling of low level computer vision algorithms on networks of heterogeneous machines","authors":"A. Nolan, B. Everding, W. Wee","doi":"10.1109/CAMP.1995.521059","DOIUrl":"https://doi.org/10.1109/CAMP.1995.521059","url":null,"abstract":"Defining an optimal schedule for arbitrary algorithms on a network of heterogeneous machines is an NP complete problem. By focusing on data parallel deterministic neighborhood computer vision algorithms, a minimum time schedule can be defined in polynomial time. The scheduling model allows for any speed machine to participate in the concurrent computation but makes the assumption of a master/slave control mechanism using a linear communication network. Several vision algorithms are presented which adhere to the scheduling model. The theoretical speedup of these algorithms is discussed and empirical data is presented and compared to theoretical results.","PeriodicalId":277209,"journal":{"name":"Proceedings of Conference on Computer Architectures for Machine Perception","volume":"158 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116110919","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
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
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
请完成安全验证×
相关产品
×
本文献相关产品
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信