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
Human-computer interaction based on eye movement tracking 基于眼动跟踪的人机交互
Proceedings of Conference on Computer Architectures for Machine Perception Pub Date : 1995-09-18 DOI: 10.1109/CAMP.1995.521048
C. Colombo, A. del Bimbo, S. De Magistris
{"title":"Human-computer interaction based on eye movement tracking","authors":"C. Colombo, A. del Bimbo, S. De Magistris","doi":"10.1109/CAMP.1995.521048","DOIUrl":"https://doi.org/10.1109/CAMP.1995.521048","url":null,"abstract":"An advanced approach to man-machine interaction is proposed, in which computer vision techniques are used for interpreting user actions. The key idea of the approach is the combined use of head motions for visual navigation and eye pupil positions for context switching within the graphical human-computer interface. This allows a partial decoupling of the visual models used for tracing eye features, with beneficial effects on both computational speed and adaptation to user characteristics. The applications range from navigation and selection in virtual reality and multimedia systems, to aids for the disabled and the monitoring of typical user actions in front of advanced terminals. The feasibility of the approach is tested and discussed in the case of a virtual reality application, the virtual museum.","PeriodicalId":277209,"journal":{"name":"Proceedings of Conference on Computer Architectures for Machine Perception","volume":"51 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":"122929541","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: 22
Real time visualization of digital elevation model on parallel architecture 并行结构上数字高程模型的实时可视化
Proceedings of Conference on Computer Architectures for Machine Perception Pub Date : 1995-09-18 DOI: 10.1109/CAMP.1995.521035
J.-L. Basille, Jean-Paul Carrara, P. Fernandez
{"title":"Real time visualization of digital elevation model on parallel architecture","authors":"J.-L. Basille, Jean-Paul Carrara, P. Fernandez","doi":"10.1109/CAMP.1995.521035","DOIUrl":"https://doi.org/10.1109/CAMP.1995.521035","url":null,"abstract":"This paper shows that digital elevation model's visualization may be performed on a line processor with performances satisfying actual real-time constraints. Two treatments must be distinguished to obtain the final result: first, an image transform which allows us to choose the positioning of the observer beside the scene and the distance from the observer to the scene, finally an image projection which allows us to choose elevation of this observer. In order to parallelize it on the line processor SYMPATI 2 we take advantage of its access capabilities for processing the image either in a row by row or in a column by column fashion. These capabilities allow us to decompose image transforms into 2 steps. The first one performs an x-constant transform, the second one a y-constant transform. This decomposition makes it possible to obtain very attractive processing times in comparison with those provided by wired operators.","PeriodicalId":277209,"journal":{"name":"Proceedings of Conference on Computer Architectures for Machine Perception","volume":"2 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":"128705425","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
A VLSI architecture for 2D object classification based on tree matching 一种基于树匹配的二维目标分类VLSI体系结构
Proceedings of Conference on Computer Architectures for Machine Perception Pub Date : 1995-09-18 DOI: 10.1109/CAMP.1995.521030
M. Schaffer, T. Chen
{"title":"A VLSI architecture for 2D object classification based on tree matching","authors":"M. Schaffer, T. Chen","doi":"10.1109/CAMP.1995.521030","DOIUrl":"https://doi.org/10.1109/CAMP.1995.521030","url":null,"abstract":"This paper presents a real-time classification algorithm for 2D object contours using a multi-resolution tree model which is implemented in a modular VLSI architecture. The hardware implementation takes advantage of pipelining, parallelism, and the speed of VLSI technology to perform real-time object classification. Using the multi-resolution tree model, the classification algorithm is invariant under 2D similarity transformations and recognizes the visible portions of occluded objects. The VLSI classification system is implemented in 0.8 /spl mu/m CMOS and is capable of performing 34000 matchings per second.","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":"128745990","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
Mapping schemes for sequential image processing algorithms 序列图像处理算法的映射方案
Proceedings of Conference on Computer Architectures for Machine Perception Pub Date : 1995-09-18 DOI: 10.1109/CAMP.1995.521038
L. Cordella, A. d’Acierno, C. de Stefano, M. Vento
{"title":"Mapping schemes for sequential image processing algorithms","authors":"L. Cordella, A. d’Acierno, C. de Stefano, M. Vento","doi":"10.1109/CAMP.1995.521038","DOIUrl":"https://doi.org/10.1109/CAMP.1995.521038","url":null,"abstract":"Two mapping schemes for the parallel implementation of a wide class of intrinsically sequential image processing algorithms are proposed. Their theoretical efficiency is discussed, and the convenience of using each of them evaluated as a function of the image size. Experimental results obtained on a commercial massively parallel computer are illustrated and compared with those achieved with the sequential implementation of the algorithm.","PeriodicalId":277209,"journal":{"name":"Proceedings of Conference on Computer Architectures for Machine Perception","volume":"47 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":"123761241","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
Skewed symmetry detection of closed contours based on their geometric properties 基于闭合轮廓几何特性的偏斜对称检测
Proceedings of Conference on Computer Architectures for Machine Perception Pub Date : 1995-09-18 DOI: 10.1109/CAMP.1995.521034
Wei Wen, Baozong Yuan
{"title":"Skewed symmetry detection of closed contours based on their geometric properties","authors":"Wei Wen, Baozong Yuan","doi":"10.1109/CAMP.1995.521034","DOIUrl":"https://doi.org/10.1109/CAMP.1995.521034","url":null,"abstract":"Symmetry is one of apparent features of objects in both the man-made world and nature. In computer vision, finding axes of skewed symmetry is an important task. This paper presents a new algorithm for detecting the skewed symmetry axes of closed contours according to their geometric properties obtained before. The algorithm runs in linear time in the number of contour points without knowing the number of axes of skewed symmetry in advance. The experimental results show that the method we propose is reliable, accurate and quick. The contribution of the paper has many great meanings in recognizing the symmetry of 3-D objects and recovering their structure.","PeriodicalId":277209,"journal":{"name":"Proceedings of Conference on Computer Architectures for Machine Perception","volume":"11 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":"126972213","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
Artificial life and evolutionary computing in machine perception 机器感知中的人工生命和进化计算
Proceedings of Conference on Computer Architectures for Machine Perception Pub Date : 1995-09-18 DOI: 10.1109/CAMP.1995.521067
J. Heudin
{"title":"Artificial life and evolutionary computing in machine perception","authors":"J. Heudin","doi":"10.1109/CAMP.1995.521067","DOIUrl":"https://doi.org/10.1109/CAMP.1995.521067","url":null,"abstract":"This paper introduces the foundational principles of artificial life and describes two complementary classifications of related research programs. Then, it gives an organizational definition of \"minimal\" life which points out some required features for synthesizing artificial systems with lifelike behaviors. After suggesting interactions between artificial life and machine perception, it emphasizes three promising research trends: evolvable algorithms for perception, collective perception and intelligence, evolvable hardware devices and sensors.","PeriodicalId":277209,"journal":{"name":"Proceedings of Conference on Computer Architectures for Machine Perception","volume":"18 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":"122311618","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: 7
Enhanced mesh-connected computers for image processing applications 用于图像处理应用的增强网状连接计算机
Proceedings of Conference on Computer Architectures for Machine Perception Pub Date : 1995-09-18 DOI: 10.1109/CAMP.1995.521062
M. Hamdi
{"title":"Enhanced mesh-connected computers for image processing applications","authors":"M. Hamdi","doi":"10.1109/CAMP.1995.521062","DOIUrl":"https://doi.org/10.1109/CAMP.1995.521062","url":null,"abstract":"The Reconfigurable Array with Spanning Optical Buses (RASOB) has recently been introduced as an efficient enhanced mesh connected parallel computer. RASOB combines some of the advantageous characteristics of reconfigurable meshes and meshes with optical pipelined buses. We use this computing model for the efficient design of fundamental image processing applications. In order to fully assess the potential of RASOB, the image processing applications chosen range from low level processing (convolution, histogramming) where only neighborhood communications are needed to high level processing (connected component labeling, computational geometry) where global communications are needed.","PeriodicalId":277209,"journal":{"name":"Proceedings of Conference on Computer Architectures for Machine Perception","volume":"13 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":"134052700","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
Knowledge construction and interpretation of the objects based on 2D representation image in a machine perception 机器感知中基于二维表示图像的对象知识构建与解释
Proceedings of Conference on Computer Architectures for Machine Perception Pub Date : 1995-09-18 DOI: 10.1109/CAMP.1995.521027
M. Nour, N. Benameur, K. Ouriachi
{"title":"Knowledge construction and interpretation of the objects based on 2D representation image in a machine perception","authors":"M. Nour, N. Benameur, K. Ouriachi","doi":"10.1109/CAMP.1995.521027","DOIUrl":"https://doi.org/10.1109/CAMP.1995.521027","url":null,"abstract":"The image represents an information structure of an extreme complexity. We present a method for symbolic and structured description with several levels of abstraction. The application area concerns the construction and interpretation knowledge on 3D objects in a machine perception. The knowledge representation and scenes interpretation tasks based on 2D image used \"Perceived Aspects Tables\" and \"Quality Tables\" proposed by our vision system. The necessary knowledge to this task are formalised. Then, we resolve the main interpretation problem, the control and the identification of objects, thanks to the approach called: \"Prediction-Checking of Hypotheses\". The representation, which is suggested, is based on the \"Frames\" Model. With this end in view, an organisation system of perception and scenes interpretation tasks in order to maintain a coherent representation of a structured and evolutive environment is designed. The released concepts and the proposed system are realised in a LE-LISP Object Oriented environment based on the SHIRKA knowledge representation system.","PeriodicalId":277209,"journal":{"name":"Proceedings of Conference on Computer Architectures for Machine Perception","volume":"127 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":"115886571","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
A scalable architecture for discrete wavelet transform 离散小波变换的可扩展结构
Proceedings of Conference on Computer Architectures for Machine Perception Pub Date : 1995-09-18 DOI: 10.1109/CAMP.1995.521018
S. B. Syed, M. Bayoumi
{"title":"A scalable architecture for discrete wavelet transform","authors":"S. B. Syed, M. Bayoumi","doi":"10.1109/CAMP.1995.521018","DOIUrl":"https://doi.org/10.1109/CAMP.1995.521018","url":null,"abstract":"We present the design and prototyping of an efficient systolic architecture which performs both forward and inverse discrete wavelet transform. The proposed architecture consists of a linear array of processing elements, each of which has an adder and a multiplier and fixed number of I/O channels. The wavelet transform is computed by convolution and by mapping the computation on to a linear array of systolic processing elements. The design of the architecture has been shown to be simple, scalable and has the advantage of low I/O bandwidth. The number of processing elements is independent of the size of the input. The architecture has been prototyped using 2/spl mu/m p-well CMOS technology and has been developed in the CADENCE Edge Design Framework environment.","PeriodicalId":277209,"journal":{"name":"Proceedings of Conference on Computer Architectures for Machine Perception","volume":"7 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":"115968336","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
Parallelization of perceptual grouping on distributed memory machines 分布式存储机器上感知分组的并行化
Proceedings of Conference on Computer Architectures for Machine Perception Pub Date : 1995-09-18 DOI: 10.1109/CAMP.1995.521056
Cho-Li Wang, V. K. Prasanna, Y. Lim
{"title":"Parallelization of perceptual grouping on distributed memory machines","authors":"Cho-Li Wang, V. K. Prasanna, Y. Lim","doi":"10.1109/CAMP.1995.521056","DOIUrl":"https://doi.org/10.1109/CAMP.1995.521056","url":null,"abstract":"We propose architecture independent parallel algorithms for solving perceptual grouping tasks on distributed memory machines. Given an n/spl times/n image, using P processors, we show that these tasks can be performed in O(n/sup 2//P) computation time and 20/spl radic/(P)T/sub d/+8(logP)T/sub d/+(40n//spl radic/(P)+20P)/spl tau//sub d/ communication time, where T/sub d/ is the communication startup time and /spl tau//sub d/ is the transmission rate. Our implementations show that, given 7K line segments extracted from a 1K/spl times/1K image, the line grouping task can be performed in 1.115 seconds using a partition of CM-5 having 256 processing nodes and in 0.382 seconds using a 16 node Cray T3D. Our code is written in C and MPI message passing standard and can be easily ported to other high performance computing platforms.","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":"125422196","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: 7
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