Pub Date : 2002-07-22DOI: 10.1109/CNNA.2002.1035052
A. Gacsádi, T. Maghiar, V. Tiponut
In this paper a method for visual control based on images of a mobile robot in an environment with obstacles is proposed. Cellular neural networks are used here for path planning of a mobile robot, in real time.
{"title":"A CNN path planning for a mobile robot in an environment with obstacles","authors":"A. Gacsádi, T. Maghiar, V. Tiponut","doi":"10.1109/CNNA.2002.1035052","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035052","url":null,"abstract":"In this paper a method for visual control based on images of a mobile robot in an environment with obstacles is proposed. Cellular neural networks are used here for path planning of a mobile robot, in real time.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123990290","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}
Pub Date : 2002-07-22DOI: 10.1109/CNNA.2002.1035036
P. Foldesy, I. Szatmári, Á. Zarándy
Analogic CNN algorithms are combined with the special properties of a panoramic imaging device called PAL optics. The resulting system is capable to identify and track moving objects in 360 degrees field of view real-time. Image processing engine was the ALADDIN system with a 64/spl times/64 array size CNNUM chip. As the image sensor, we tested the optical input of the CNNUM chip in one experiment, and in other cases, we used a regular camera.
{"title":"Moving object tracking on panoramic images","authors":"P. Foldesy, I. Szatmári, Á. Zarándy","doi":"10.1109/CNNA.2002.1035036","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035036","url":null,"abstract":"Analogic CNN algorithms are combined with the special properties of a panoramic imaging device called PAL optics. The resulting system is capable to identify and track moving objects in 360 degrees field of view real-time. Image processing engine was the ALADDIN system with a 64/spl times/64 array size CNNUM chip. As the image sensor, we tested the optical input of the CNNUM chip in one experiment, and in other cases, we used a regular camera.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121908902","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}
Pub Date : 2002-07-22DOI: 10.1109/CNNA.2002.1035076
M. Yalçin, J. Vandewalle
Image authentication and integrity have become an important issue for multimedia applications since digital images may be easily modified and perfectly reproduced. This paper addresses the protection of image authentication and integrity on CNN-UM. Watermarking and cryptographic hash functions are techniques used for this protection. We propose two methods using each technique, spatial domain fragile watermarking and a novel unkeyed hash function named Cellhash2D.
{"title":"Fragile watermarking and unkeyed hash function implementation for image authentication on CNN-UM","authors":"M. Yalçin, J. Vandewalle","doi":"10.1109/CNNA.2002.1035076","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035076","url":null,"abstract":"Image authentication and integrity have become an important issue for multimedia applications since digital images may be easily modified and perfectly reproduced. This paper addresses the protection of image authentication and integrity on CNN-UM. Watermarking and cryptographic hash functions are techniques used for this protection. We propose two methods using each technique, spatial domain fragile watermarking and a novel unkeyed hash function named Cellhash2D.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114999501","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}
Pub Date : 2002-07-22DOI: 10.1109/CNNA.2002.1035067
T. Roska
Computational complexity and computer complexity issues are studied in different architectural settings. Three mathematical machines are considered: the universal machine on integers (UMZ), the universal machine on reals (UMR) and the universal machine on flows (UMF). The three machines induce different kinds of computational difficulties: combinatorial, algebraic, and dynamic, respectively. After a broader overview of computational complexity issues, it is shown, following the reasoning related the UMR, that in many cases the size is not the most important parameter related to computational complexity. Emerging new computing and computer architectures as well as their physical implementation suggest a new look at computational and computer complexities. The new analogic cellular array computer paradigm based on the CNN Universal Machine (generalized to UMF), and its physical implementation in CMOS and optical technologies, proves experimentally the relevance of the role of accuracy and problem parameter role in computational complexity, as well as the need of rigorous definition of computational complexity for UMF. It is also shown that choosing the spatial temporal elementary instructions, as well as taking into account the area and power dissipation, these choices inherently influence computational complexity and computer complexity, respectively. Comments related to biology relevance of the UMF are presented in relation to complexity theory. It is shown that algorithms using spatial-temporal continuous elementary instructions (a-recursive functions) represent not only a new world in computing, but also a more general type of logic inferencing.
{"title":"Computational and computer complexity of analogic cellular wave computers","authors":"T. Roska","doi":"10.1109/CNNA.2002.1035067","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035067","url":null,"abstract":"Computational complexity and computer complexity issues are studied in different architectural settings. Three mathematical machines are considered: the universal machine on integers (UMZ), the universal machine on reals (UMR) and the universal machine on flows (UMF). The three machines induce different kinds of computational difficulties: combinatorial, algebraic, and dynamic, respectively. After a broader overview of computational complexity issues, it is shown, following the reasoning related the UMR, that in many cases the size is not the most important parameter related to computational complexity. Emerging new computing and computer architectures as well as their physical implementation suggest a new look at computational and computer complexities. The new analogic cellular array computer paradigm based on the CNN Universal Machine (generalized to UMF), and its physical implementation in CMOS and optical technologies, proves experimentally the relevance of the role of accuracy and problem parameter role in computational complexity, as well as the need of rigorous definition of computational complexity for UMF. It is also shown that choosing the spatial temporal elementary instructions, as well as taking into account the area and power dissipation, these choices inherently influence computational complexity and computer complexity, respectively. Comments related to biology relevance of the UMF are presented in relation to complexity theory. It is shown that algorithms using spatial-temporal continuous elementary instructions (a-recursive functions) represent not only a new world in computing, but also a more general type of logic inferencing.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129639012","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}
Pub Date : 2002-07-22DOI: 10.1109/CNNA.2002.1035043
Z. Galias, M. Ogorzałek
In this paper we investigate the influence of system non-uniformity on the existence and stability of synchronous motion in an array of bi-directionally coupled electronic circuits. In computer simulations we find the level of nonuniformity for which synchronous behavior is sustained. We also present several examples of attractors, which appear when the synchronous motions is no longer stable.
{"title":"Influence of system non-uniformity on dynamic phenomena in arrays of coupled nonlinear networks","authors":"Z. Galias, M. Ogorzałek","doi":"10.1109/CNNA.2002.1035043","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035043","url":null,"abstract":"In this paper we investigate the influence of system non-uniformity on the existence and stability of synchronous motion in an array of bi-directionally coupled electronic circuits. In computer simulations we find the level of nonuniformity for which synchronous behavior is sustained. We also present several examples of attractors, which appear when the synchronous motions is no longer stable.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129726516","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}
Pub Date : 2002-07-22DOI: 10.1109/CNNA.2002.1035078
K. Doris, V. Mladenov, H. Hegt, A. V. van Roermund
In this paper a link is made between dynamics and propagation in a chain of resistively coupled cells and the behavior of positive feedback comparators which are the primary blocks in analog to digital converters (ADC). It is pointed out that both behaviors can be explained with the same nonlinear dynamics. It turns out that an important property of the common unique cell is a two stable equilibria characteristic, inherent in some positive feedback systems. This characteristic is presented in the case of latched comparators. The dynamics of a comparator and a chain of comparators are also considered.
{"title":"Nonlinear dynamics and propagation in positive feedback comparators for A/D Converters","authors":"K. Doris, V. Mladenov, H. Hegt, A. V. van Roermund","doi":"10.1109/CNNA.2002.1035078","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035078","url":null,"abstract":"In this paper a link is made between dynamics and propagation in a chain of resistively coupled cells and the behavior of positive feedback comparators which are the primary blocks in analog to digital converters (ADC). It is pointed out that both behaviors can be explained with the same nonlinear dynamics. It turns out that an important property of the common unique cell is a two stable equilibria characteristic, inherent in some positive feedback systems. This characteristic is presented in the case of latched comparators. The dynamics of a comparator and a chain of comparators are also considered.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122950776","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}
Pub Date : 2002-07-22DOI: 10.1109/CNNA.2002.1035099
M. ter Brugge, J. Nijhuis, L. Spaanenburg
Mathematical morphology is a powerful means to specify image manipulations; discrete-time cellular neural networks (DT-CNN) is the fast realization. The attractive combination has been sufficiently shown for simple problems but tends to fail in efficiency for more complex ones. The paper introduces a complement and argument swap (CAS) equivalence that allows to solve an image processing problem through a small library of representative efficient designs.
{"title":"Composite morphological functions for DT-CNNs","authors":"M. ter Brugge, J. Nijhuis, L. Spaanenburg","doi":"10.1109/CNNA.2002.1035099","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035099","url":null,"abstract":"Mathematical morphology is a powerful means to specify image manipulations; discrete-time cellular neural networks (DT-CNN) is the fast realization. The attractive combination has been sufficiently shown for simple problems but tends to fail in efficiency for more complex ones. The paper introduces a complement and argument swap (CAS) equivalence that allows to solve an image processing problem through a small library of representative efficient designs.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116556403","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}
Pub Date : 2002-07-22DOI: 10.1109/CNNA.2002.1035069
Abdallah Nshare, Jacques-Olivier Klein, A. Dupret
In this paper, a high accuracy analog random access memory (ARAM) for programmable vision chips is addressed. In the context of a large retina, the main sources of error are analyzed. Several architectures are presented and compared. The design of an improved ARAM is detailed.
{"title":"Improved ARAM for PARIS, an original programmable vision chip","authors":"Abdallah Nshare, Jacques-Olivier Klein, A. Dupret","doi":"10.1109/CNNA.2002.1035069","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035069","url":null,"abstract":"In this paper, a high accuracy analog random access memory (ARAM) for programmable vision chips is addressed. In the context of a large retina, the main sources of error are analyzed. Several architectures are presented and compared. The design of an improved ARAM is detailed.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124121292","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}
Pub Date : 2002-07-22DOI: 10.1109/CNNA.2002.1035063
P. Arena, A. Basile, L. Fortuna, A. Virzì
Robot locomotion control passes through a series of sensors that, according to information from the environment, allow the robot to adapt, in real time, its locomotion scheme or trajectory. When the goal of the robot is to reach a target in a non-structured environment the best approach is visual control realized by a fast image processing system. Fast parallel image processing of the CNN-UM cP4000 chip prototype permits one to obtain good performance, even in a real time control problem. The robot controlled by the implemented CNN visual feedback has a hexapod configuration and its locomotion system is also implemented by a multi-layer CNN structure. In this paper a CNN approach for both locomotion generation and visual control of the bio-inspired robot is presented.
{"title":"Visual feedback by using a CNN chip prototype system","authors":"P. Arena, A. Basile, L. Fortuna, A. Virzì","doi":"10.1109/CNNA.2002.1035063","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035063","url":null,"abstract":"Robot locomotion control passes through a series of sensors that, according to information from the environment, allow the robot to adapt, in real time, its locomotion scheme or trajectory. When the goal of the robot is to reach a target in a non-structured environment the best approach is visual control realized by a fast image processing system. Fast parallel image processing of the CNN-UM cP4000 chip prototype permits one to obtain good performance, even in a real time control problem. The robot controlled by the implemented CNN visual feedback has a hexapod configuration and its locomotion system is also implemented by a multi-layer CNN structure. In this paper a CNN approach for both locomotion generation and visual control of the bio-inspired robot is presented.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125169939","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}
Pub Date : 2002-07-22DOI: 10.1109/CNNA.2002.1035054
P. Ecimovic, J. Wu
We design a cellular neural network model with state-dependent delay to perform delay-driven contrast enhancement on continuous image sequences, e.g., in moving image data. We report here some preliminary results of a simulation of this system using a recently-released algorithm for solving systems of delay differential equations containing state-dependent delays.
{"title":"Delay-driven contrast enhancement using a cellular neural network with state-dependent delay","authors":"P. Ecimovic, J. Wu","doi":"10.1109/CNNA.2002.1035054","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035054","url":null,"abstract":"We design a cellular neural network model with state-dependent delay to perform delay-driven contrast enhancement on continuous image sequences, e.g., in moving image data. We report here some preliminary results of a simulation of this system using a recently-released algorithm for solving systems of delay differential equations containing state-dependent delays.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128189297","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}