The improved scene-based adaptive nonuniformity correction (NUC) algorithms using a neural network (NNT) approach for infrared image sequences are presented and analyzed. The retina-like neural networks using steepest...The improved scene-based adaptive nonuniformity correction (NUC) algorithms using a neural network (NNT) approach for infrared image sequences are presented and analyzed. The retina-like neural networks using steepest descent model was the first proposed infrared focal plane arrays (IRFPA) nonuniformity compensation method,which can perform parameter estimation of the sensors over time on a frame by frame basis. To increase the strength and the robustness of the NNT algorithm and to avoid the presence of ghosting artifacts,some optimization techniques,including momentum term,regularization factor and adaptive learning rate,were executed in the parameter learning process. In this paper,the local median filtering result of AX^U_ ij (n) is proposed as an alternative value of desired network output of neuron X_ ij (n),denoted as T_ ij (n),which is the local spatial average of AX^U_ ij (n) in traditional NNT methods. Noticeably,the NUC algorithm is inter-frame adaptive in nature and does not rely on any statistical assumptions on the scene data in the image sequence. Applications of this algorithm to the simulated video sequences and real infrared data taken with PV320 show that the correction results of image sequence are better than that of using original NNT approach,especially for the short-time image sequences (several hundred frames) subjected to the dense impulse noises with a number of dead or saturated pixels.展开更多
For infrared focal plane graded during signal acquisition array sensors, imagery is departicularly nonuniformity. In this paper, an adaptive nonuniformity correction technique is proposed which simultaneously estimate...For infrared focal plane graded during signal acquisition array sensors, imagery is departicularly nonuniformity. In this paper, an adaptive nonuniformity correction technique is proposed which simultaneously estimates detector-level and readout- channel-level correction parameters using neural network approaches. Firstly, an improved neural network framework is designed to compute the desired output. Secondly, an adaptive learning rate rule is used in the gain and offset parameter estimation process. Experimental results show the proposed algorithm can achieve a faster convergence speed and better stability, remove nonuniformity and track parameters drift effectively, and present a good adaptability to scene changes and nonuniformity conditions.展开更多
In this paper,three distributed and scalable nonuniform deployment algorithms in order to enhance the quality of monitoring(QoM).Mobile sensors are to be deployed around a target of interest which can be stationary or...In this paper,three distributed and scalable nonuniform deployment algorithms in order to enhance the quality of monitoring(QoM).Mobile sensors are to be deployed around a target of interest which can be stationary or moving,and to approximate a given weight function which is a measure of information or event density.The first two algorithms generate nonuniform deployments by inverse-transformations from a uniform deployment.They handle the situations of global coordinate system which is available and not with appropriate assumptions,respectively.The third algorithm,which relocates sensors to adjust inter-node distances based on the local measurements only,is suitable for general cases.The simulation results demonstrate the proposed algorithms can achieve reliable and satisfactory deployments.展开更多
A hybrid algorithm is presented for nonuniform lossy multiconductor transmission lines (MTL) connected by arbitrary linear load networks. The networks are characterized by a state-variable equation which allows a gene...A hybrid algorithm is presented for nonuniform lossy multiconductor transmission lines (MTL) connected by arbitrary linear load networks. The networks are characterized by a state-variable equation which allows a general characterization of dynamic elements in the cascade networks. The method is achieved by the finite difference-time domain (FDTD) algorithm for the MTL, and the skin effect is taken into account, the more accurate method is used to compute the skin effect. And this method is combined with the computation of the nonuniform transmission lines. Finally, several numerical examples are given, these results indicate that: the current of the lossy MTL is smaller than the lossless of the MTL; and when the load networks contain the dynamic element, the transition time of the current is longer than the MTL connected by resistance only.展开更多
Arbitrary topological curve network has no restriction in topology structure,so it has more powerful representing ability in defining complex surfaces.A complex surface modeling system is presented based on arbitrary ...Arbitrary topological curve network has no restriction in topology structure,so it has more powerful representing ability in defining complex surfaces.A complex surface modeling system is presented based on arbitrary topological curve network and the improved combined subdivision method,its functions including creating and editing curve network,and generating and modifying curve network＇s interpolated surface.This modeling system can be used to the process of products＇concept design,and its applications is also significant to the development of subdivision method.展开更多
文摘The improved scene-based adaptive nonuniformity correction (NUC) algorithms using a neural network (NNT) approach for infrared image sequences are presented and analyzed. The retina-like neural networks using steepest descent model was the first proposed infrared focal plane arrays (IRFPA) nonuniformity compensation method,which can perform parameter estimation of the sensors over time on a frame by frame basis. To increase the strength and the robustness of the NNT algorithm and to avoid the presence of ghosting artifacts,some optimization techniques,including momentum term,regularization factor and adaptive learning rate,were executed in the parameter learning process. In this paper,the local median filtering result of AX^U_ ij (n) is proposed as an alternative value of desired network output of neuron X_ ij (n),denoted as T_ ij (n),which is the local spatial average of AX^U_ ij (n) in traditional NNT methods. Noticeably,the NUC algorithm is inter-frame adaptive in nature and does not rely on any statistical assumptions on the scene data in the image sequence. Applications of this algorithm to the simulated video sequences and real infrared data taken with PV320 show that the correction results of image sequence are better than that of using original NNT approach,especially for the short-time image sequences (several hundred frames) subjected to the dense impulse noises with a number of dead or saturated pixels.
基金supported by the National Natural Science Foundation of China (61101199)the Natural Science Foundation of Jiangsu Province (K2011699)the Colleges and Universities Innovation Projects (CX08B 045Z)
文摘For infrared focal plane graded during signal acquisition array sensors, imagery is departicularly nonuniformity. In this paper, an adaptive nonuniformity correction technique is proposed which simultaneously estimates detector-level and readout- channel-level correction parameters using neural network approaches. Firstly, an improved neural network framework is designed to compute the desired output. Secondly, an adaptive learning rate rule is used in the gain and offset parameter estimation process. Experimental results show the proposed algorithm can achieve a faster convergence speed and better stability, remove nonuniformity and track parameters drift effectively, and present a good adaptability to scene changes and nonuniformity conditions.
基金Sponsored by the National Natural Science Foundation of China (Grant No. 61174016,61171197)
文摘In this paper,three distributed and scalable nonuniform deployment algorithms in order to enhance the quality of monitoring(QoM).Mobile sensors are to be deployed around a target of interest which can be stationary or moving,and to approximate a given weight function which is a measure of information or event density.The first two algorithms generate nonuniform deployments by inverse-transformations from a uniform deployment.They handle the situations of global coordinate system which is available and not with appropriate assumptions,respectively.The third algorithm,which relocates sensors to adjust inter-node distances based on the local measurements only,is suitable for general cases.The simulation results demonstrate the proposed algorithms can achieve reliable and satisfactory deployments.
文摘A hybrid algorithm is presented for nonuniform lossy multiconductor transmission lines (MTL) connected by arbitrary linear load networks. The networks are characterized by a state-variable equation which allows a general characterization of dynamic elements in the cascade networks. The method is achieved by the finite difference-time domain (FDTD) algorithm for the MTL, and the skin effect is taken into account, the more accurate method is used to compute the skin effect. And this method is combined with the computation of the nonuniform transmission lines. Finally, several numerical examples are given, these results indicate that: the current of the lossy MTL is smaller than the lossless of the MTL; and when the load networks contain the dynamic element, the transition time of the current is longer than the MTL connected by resistance only.
基金Project supported by the Fundamental Research Foundations for the Central Universities (Grant No.2009B30514)
文摘Arbitrary topological curve network has no restriction in topology structure,so it has more powerful representing ability in defining complex surfaces.A complex surface modeling system is presented based on arbitrary topological curve network and the improved combined subdivision method,its functions including creating and editing curve network,and generating and modifying curve network＇s interpolated surface.This modeling system can be used to the process of products＇concept design,and its applications is also significant to the development of subdivision method.
