Pub Date : 2006-12-01DOI: 10.1109/ICARCV.2006.345109
S. Hara
The author's previous study proposed an efficient design method of time-varying gain type controller using the solutions of time-varying Riccati equations (TVREs) and its application to positioning control of vibration systems. This method generates the solutions of a TVRE and the responses of a controlled object simultaneously. The time-varying gains are obtained by realtime computations in actual implementations. This feature is convenient for the realization of some adaptive control. However, such a control method has not been fully addressed yet. This study discusses an adaptive nonstationary control (ANSC) method based on the feature of the previous study. We select a flexible structure installed on an X-Y table as a controlled object example. Its positioning and residual vibration reduction are the purposes of the application in this paper. The effectiveness of the ANSC method is verified by numerical calculations and experiments.
{"title":"Adaptive Nonstationary Control Using Solutions of Time-Varying Riccati Equations-Its Application to Positioning Control of Vibration Systems","authors":"S. Hara","doi":"10.1109/ICARCV.2006.345109","DOIUrl":"https://doi.org/10.1109/ICARCV.2006.345109","url":null,"abstract":"The author's previous study proposed an efficient design method of time-varying gain type controller using the solutions of time-varying Riccati equations (TVREs) and its application to positioning control of vibration systems. This method generates the solutions of a TVRE and the responses of a controlled object simultaneously. The time-varying gains are obtained by realtime computations in actual implementations. This feature is convenient for the realization of some adaptive control. However, such a control method has not been fully addressed yet. This study discusses an adaptive nonstationary control (ANSC) method based on the feature of the previous study. We select a flexible structure installed on an X-Y table as a controlled object example. Its positioning and residual vibration reduction are the purposes of the application in this paper. The effectiveness of the ANSC method is verified by numerical calculations and experiments.","PeriodicalId":415827,"journal":{"name":"2006 9th International Conference on Control, Automation, Robotics and Vision","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129944055","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 : 2006-12-01DOI: 10.1109/ICARCV.2006.345198
T. Tsuda, Makoto Okuda, K. Mutou, Y. Nishida
We developed an automatic tracking system camera for TV program production that is capable of making stable shots by detecting the performers' facial positions. This system can make tracking shots as specified by the user, by using a subject detection module in which input images are simultaneously processed by several image-processing algorithms installed in PCs on a local network. The robot camera is driven with a feedback control for correcting face positions in an image and a speed control for responding to the subject's movement. An experiment on automatic shooting of moving performers confirmed that this camera system can shoot "viewer-friendly" images, i.e., images without large vibrations that affect a subject's position in an image
{"title":"Automatic tracking camera system utilizing the position of faces in the shot image","authors":"T. Tsuda, Makoto Okuda, K. Mutou, Y. Nishida","doi":"10.1109/ICARCV.2006.345198","DOIUrl":"https://doi.org/10.1109/ICARCV.2006.345198","url":null,"abstract":"We developed an automatic tracking system camera for TV program production that is capable of making stable shots by detecting the performers' facial positions. This system can make tracking shots as specified by the user, by using a subject detection module in which input images are simultaneously processed by several image-processing algorithms installed in PCs on a local network. The robot camera is driven with a feedback control for correcting face positions in an image and a speed control for responding to the subject's movement. An experiment on automatic shooting of moving performers confirmed that this camera system can shoot \"viewer-friendly\" images, i.e., images without large vibrations that affect a subject's position in an image","PeriodicalId":415827,"journal":{"name":"2006 9th International Conference on Control, Automation, Robotics and Vision","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128256343","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 : 2006-12-01DOI: 10.1109/ICARCV.2006.345387
H. Yuan, Yebo Yang, Ying Chen
Convergence of technologies in the Internet and the field of expert systems have offered new ways of sharing and distributing knowledge. In this paper, we present one research into the development of a Web-based expert system for crab farming, using the XF6.2 development platform. This expert system can provide tele-diagnosis and treatment services to crab farmers with access to the Internet. Experiments with the system have provided convincing evidence of the system's capacity to process the domain knowledge and provide both effective treatments and accurate diagnoses of crab diseases. The Web-based system is ready to be formally launched and hosted in China
{"title":"Crab-Expert: a Web-Based ES for Crab Farming","authors":"H. Yuan, Yebo Yang, Ying Chen","doi":"10.1109/ICARCV.2006.345387","DOIUrl":"https://doi.org/10.1109/ICARCV.2006.345387","url":null,"abstract":"Convergence of technologies in the Internet and the field of expert systems have offered new ways of sharing and distributing knowledge. In this paper, we present one research into the development of a Web-based expert system for crab farming, using the XF6.2 development platform. This expert system can provide tele-diagnosis and treatment services to crab farmers with access to the Internet. Experiments with the system have provided convincing evidence of the system's capacity to process the domain knowledge and provide both effective treatments and accurate diagnoses of crab diseases. The Web-based system is ready to be formally launched and hosted in China","PeriodicalId":415827,"journal":{"name":"2006 9th International Conference on Control, Automation, Robotics and Vision","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128678989","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 : 2006-12-01DOI: 10.1109/ICARCV.2006.345191
Liang Yu, Zhao Xi-Nan, Zhang Li-Bing
A discrete event risk model based on asymmetric stock return models was investigated in this paper. In this model, discrete event risk was described by random jump-diffusion process and the asymmetric effect was described by GJR-GARCH (generalized autoregression conditional heteroscedasticity) model. The model's parameters were estimated by simulated annealing algorithm. By simulation method, the distribution of intending return and the interval estimation value was obtained. The empirical study on index of Shanghai and Shenzhen security markets shows it's reasonable and necessary to incorporate discrete event risk to asymmetric stock return model
{"title":"Studies of Stock Market Discrete Event Risk Based on Asymmetric Effect Models","authors":"Liang Yu, Zhao Xi-Nan, Zhang Li-Bing","doi":"10.1109/ICARCV.2006.345191","DOIUrl":"https://doi.org/10.1109/ICARCV.2006.345191","url":null,"abstract":"A discrete event risk model based on asymmetric stock return models was investigated in this paper. In this model, discrete event risk was described by random jump-diffusion process and the asymmetric effect was described by GJR-GARCH (generalized autoregression conditional heteroscedasticity) model. The model's parameters were estimated by simulated annealing algorithm. By simulation method, the distribution of intending return and the interval estimation value was obtained. The empirical study on index of Shanghai and Shenzhen security markets shows it's reasonable and necessary to incorporate discrete event risk to asymmetric stock return model","PeriodicalId":415827,"journal":{"name":"2006 9th International Conference on Control, Automation, Robotics and Vision","volume":"19 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129027765","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 : 2006-12-01DOI: 10.1109/ICARCV.2006.345457
A. Cavalcanti, T. Hogg, B. Shirinzadeh, H. C. Liaw
This work presents chemical communication techniques for nanorobots foraging in fluid environments relevant for medical applications. Unlike larger robots, viscous forces and rapid diffusion dominate their behaviors. Examples range from modified microorganisms to nanorobots using ongoing developments in molecular computation, sensors and motors. The nanorobots use an innovative methodology to achieve decentralized control for a distributed collective action in the combat of cancer. A communication approach is described in the context of recognize a single tumor cell in a small venule as a target for medical treatment. Thus, a higher gradient of signal intensity of E-cadherin is used as chemical parameter identification in guiding nanorobots to identify malignant tissues. A nanorobot can effectively use chemical communication to improve intervention time to identify tumor cells
{"title":"Nanorobot Communication Techniques: A Comprehensive Tutorial","authors":"A. Cavalcanti, T. Hogg, B. Shirinzadeh, H. C. Liaw","doi":"10.1109/ICARCV.2006.345457","DOIUrl":"https://doi.org/10.1109/ICARCV.2006.345457","url":null,"abstract":"This work presents chemical communication techniques for nanorobots foraging in fluid environments relevant for medical applications. Unlike larger robots, viscous forces and rapid diffusion dominate their behaviors. Examples range from modified microorganisms to nanorobots using ongoing developments in molecular computation, sensors and motors. The nanorobots use an innovative methodology to achieve decentralized control for a distributed collective action in the combat of cancer. A communication approach is described in the context of recognize a single tumor cell in a small venule as a target for medical treatment. Thus, a higher gradient of signal intensity of E-cadherin is used as chemical parameter identification in guiding nanorobots to identify malignant tissues. A nanorobot can effectively use chemical communication to improve intervention time to identify tumor cells","PeriodicalId":415827,"journal":{"name":"2006 9th International Conference on Control, Automation, Robotics and Vision","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129687644","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 : 2006-12-01DOI: 10.1109/ICARCV.2006.345315
A. Vemuri, K. Subbarao
This paper presents an online fault isolation methodology for identifying faulty components in a dynamical system. It is hypothesized that faults in a dynamical system can be suitably represented via nonlinear functions. The isolation scheme, which is implemented online, relies on adaptive nonlinear estimates of these nonlinear fault functions based on the system input output data. The nonlinear fault estimation is achieved using a radial basis function neural network (RBFNN) architecture while the fault isolation is accomplished using extrinsic curvature of the learned RBFNN model. A simple simulation example is presented to illustrate the concept
{"title":"Fault Isolation Using Extrinsic Curvature of Nonlinear Fault Models","authors":"A. Vemuri, K. Subbarao","doi":"10.1109/ICARCV.2006.345315","DOIUrl":"https://doi.org/10.1109/ICARCV.2006.345315","url":null,"abstract":"This paper presents an online fault isolation methodology for identifying faulty components in a dynamical system. It is hypothesized that faults in a dynamical system can be suitably represented via nonlinear functions. The isolation scheme, which is implemented online, relies on adaptive nonlinear estimates of these nonlinear fault functions based on the system input output data. The nonlinear fault estimation is achieved using a radial basis function neural network (RBFNN) architecture while the fault isolation is accomplished using extrinsic curvature of the learned RBFNN model. A simple simulation example is presented to illustrate the concept","PeriodicalId":415827,"journal":{"name":"2006 9th International Conference on Control, Automation, Robotics and Vision","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123852564","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 : 2006-12-01DOI: 10.1109/ICARCV.2006.345252
J. Doornik, A. Ishihara, T. Sanger
In this paper we analyze stochastic stability and boundedness of the neurophysiologically inspired feedback error learning (FEL) paradigm, a control algorithm that uses an inverse model of the plant to maximize tracking performance under uncertain conditions. FEL is analyzed in the framework of an adaptive state feedback controller. An inverse model of the plant is adaptively learned by a neural network based on basis functions, while the output of the feedback controller is used as the training signal. The nonlinear plant under consideration is described as a multidimensional SISO stochastic differential equation. The tracking error was shown to be uniformly bounded in the case where the variance of the noise on the parameter update rule was constant and the variance of the noise on the state variables was a function of the tracking error. When the system was allowed to have only noise on the states variables, with variance linear to the tracking error, then FEL was shown to be stochastically stable
{"title":"Uniform Boundedness of Feedback Error Learning for a Class of Stochastic Nonlinear Systems","authors":"J. Doornik, A. Ishihara, T. Sanger","doi":"10.1109/ICARCV.2006.345252","DOIUrl":"https://doi.org/10.1109/ICARCV.2006.345252","url":null,"abstract":"In this paper we analyze stochastic stability and boundedness of the neurophysiologically inspired feedback error learning (FEL) paradigm, a control algorithm that uses an inverse model of the plant to maximize tracking performance under uncertain conditions. FEL is analyzed in the framework of an adaptive state feedback controller. An inverse model of the plant is adaptively learned by a neural network based on basis functions, while the output of the feedback controller is used as the training signal. The nonlinear plant under consideration is described as a multidimensional SISO stochastic differential equation. The tracking error was shown to be uniformly bounded in the case where the variance of the noise on the parameter update rule was constant and the variance of the noise on the state variables was a function of the tracking error. When the system was allowed to have only noise on the states variables, with variance linear to the tracking error, then FEL was shown to be stochastically stable","PeriodicalId":415827,"journal":{"name":"2006 9th International Conference on Control, Automation, Robotics and Vision","volume":"84 2-3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123635788","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 : 2006-12-01DOI: 10.1109/ICARCV.2006.345430
T. Z. Tan, G. Ng, S. Erdogan
Uncertainty exists in various complex problems. Yet, human is able to effectively handle these uncertainties and makes appropriate decision. Thus, modeling of human uncertainty process should improve the performance of learning system in uncertain environment. A mechanism for human uncertainty monitoring is the broad and narrow generalization in category learning. This can be modeled using upper and lower membership functions, which corresponds to the broad and narrow generalizations respectively. These upper and lower membership functions can be implemented using the fuzzy rough set (FR) theory. A complementary learning fuzzy neural network (CLFNN) is a functional model of human pattern recognition. It is integrated with the human uncertainty monitoring model and the resultant FRCLFNN offers good classification performance and better representation power as it captures input, linguistic, and rough uncertainties. Experimental result supports that FRCLFNN is a competent decision support system
{"title":"A Neuropsychology-inspired Learning System for Human Uncertainty Monitoring","authors":"T. Z. Tan, G. Ng, S. Erdogan","doi":"10.1109/ICARCV.2006.345430","DOIUrl":"https://doi.org/10.1109/ICARCV.2006.345430","url":null,"abstract":"Uncertainty exists in various complex problems. Yet, human is able to effectively handle these uncertainties and makes appropriate decision. Thus, modeling of human uncertainty process should improve the performance of learning system in uncertain environment. A mechanism for human uncertainty monitoring is the broad and narrow generalization in category learning. This can be modeled using upper and lower membership functions, which corresponds to the broad and narrow generalizations respectively. These upper and lower membership functions can be implemented using the fuzzy rough set (FR) theory. A complementary learning fuzzy neural network (CLFNN) is a functional model of human pattern recognition. It is integrated with the human uncertainty monitoring model and the resultant FRCLFNN offers good classification performance and better representation power as it captures input, linguistic, and rough uncertainties. Experimental result supports that FRCLFNN is a competent decision support system","PeriodicalId":415827,"journal":{"name":"2006 9th International Conference on Control, Automation, Robotics and Vision","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121392531","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 : 2006-12-01DOI: 10.1109/ICARCV.2006.345105
Yimin Hou, Lei Guo, Xiangmin Lun
Proposed a novel image segmentation method based on Markov random field (MRF) and context information. The method introduces the relationships of observed image intensities and distance between pixels to the traditional neighborhood potential function, so that to describe the probability of pixels being classified into one class. We transform the segmentation process to maximum a posteriori (MAP) by Bayes theorem. Finally, the iterative conditional model (ICM) is used to solve the MAP problem. In the experiments, this method is compared with traditional expectation-maximization (EM) and MRF image segmentation techniques using synthetic and real images. The experiment results and SNR-CCR histogram show that the algorithm proposed is more effective for noisy image segmentation.
{"title":"A Novel MRF-Based Image Segmentation Algorithm","authors":"Yimin Hou, Lei Guo, Xiangmin Lun","doi":"10.1109/ICARCV.2006.345105","DOIUrl":"https://doi.org/10.1109/ICARCV.2006.345105","url":null,"abstract":"Proposed a novel image segmentation method based on Markov random field (MRF) and context information. The method introduces the relationships of observed image intensities and distance between pixels to the traditional neighborhood potential function, so that to describe the probability of pixels being classified into one class. We transform the segmentation process to maximum a posteriori (MAP) by Bayes theorem. Finally, the iterative conditional model (ICM) is used to solve the MAP problem. In the experiments, this method is compared with traditional expectation-maximization (EM) and MRF image segmentation techniques using synthetic and real images. The experiment results and SNR-CCR histogram show that the algorithm proposed is more effective for noisy image segmentation.","PeriodicalId":415827,"journal":{"name":"2006 9th International Conference on Control, Automation, Robotics and Vision","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121414731","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 : 2006-12-01DOI: 10.1109/ICARCV.2006.345264
K. Kinoshita, Masaya Enokidani, M. Izumida, K. Murakami
The optical flow is a useful tool for the tracking of a moving object. Estimation of the optical flow based on the gradient method is an ill-posed problem. In order to avoid this ill-posed problem, we proposed a tracking method using a one-dimensional optical flow, which is calculated on a straight line (called the calculation axis) spanning several directions. However, the motion of the observer was not considered. In this paper, we propose object tracking by a one-dimensional optical flow under a rotating observer. The apparent motion of a stationary environment object should be eliminated for calculating the one-dimensional optical flow. Hence, we introduce the detection method of a moving object by mapping, which converts the motion of a stationary environment object into a linear signal trajectory. We calculate the one-dimensional optical flow by using pixels, which belong to the moving object, to eliminate the apparent motion of the stationary environment object. In order to verify the efficacy of the proposed method, simulation is performed using synthesized images. The proposed method successfully tracks the moving object when the observer rotates at a constant angular velocity
{"title":"Tracking of a Moving Object Using One-Dimensional Optical Flow with a Rotating Observer","authors":"K. Kinoshita, Masaya Enokidani, M. Izumida, K. Murakami","doi":"10.1109/ICARCV.2006.345264","DOIUrl":"https://doi.org/10.1109/ICARCV.2006.345264","url":null,"abstract":"The optical flow is a useful tool for the tracking of a moving object. Estimation of the optical flow based on the gradient method is an ill-posed problem. In order to avoid this ill-posed problem, we proposed a tracking method using a one-dimensional optical flow, which is calculated on a straight line (called the calculation axis) spanning several directions. However, the motion of the observer was not considered. In this paper, we propose object tracking by a one-dimensional optical flow under a rotating observer. The apparent motion of a stationary environment object should be eliminated for calculating the one-dimensional optical flow. Hence, we introduce the detection method of a moving object by mapping, which converts the motion of a stationary environment object into a linear signal trajectory. We calculate the one-dimensional optical flow by using pixels, which belong to the moving object, to eliminate the apparent motion of the stationary environment object. In order to verify the efficacy of the proposed method, simulation is performed using synthesized images. The proposed method successfully tracks the moving object when the observer rotates at a constant angular velocity","PeriodicalId":415827,"journal":{"name":"2006 9th International Conference on Control, Automation, Robotics and Vision","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114363640","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：