In this study, an unscented particle filtering method based on an interacting multiple model (IMM) frame for a Markovian switching system is presented. The method integrates the multiple model (MM) filter with an unsc...In this study, an unscented particle filtering method based on an interacting multiple model (IMM) frame for a Markovian switching system is presented. The method integrates the multiple model (MM) filter with an unscented particle filter (UPF) by an interaction step at the beginning. The framework (interaction/mixing, filtering, and combination) is similar to that in a standard IMM filter, but an UPF is adopted in each model. Therefore, the filtering performance and degeneracy phenomenon of particles are improved. The filtering method addresses nonlinear and/or non-Gaussian tracking problems. Simulation results show that the method has better tracking performance compared with the standard IMM-type filter and IMM particle filter.展开更多
Many Bayesian learning approaches to the multi-layer perceptron(MLP) parameter optimization have been proposed such as the extended Kalman filter(EKF).This paper uses the unscented Kalman particle filter(UPF) to train...Many Bayesian learning approaches to the multi-layer perceptron(MLP) parameter optimization have been proposed such as the extended Kalman filter(EKF).This paper uses the unscented Kalman particle filter(UPF) to train the MLP in a selforganizing state space(SOSS) model.This involves forming augmented state vectors consisting of all parameters(the weights of the MLP) and outputs.The UPF is used to sequentially update the true system states and high dimensional parameters that are inherent to the SOSS model for the MLP simultaneously.Simulation results show that the new method performs better than traditional optimization methods.展开更多
Target tracking in video is a hot topic in computer vision field, which has wide applications in surveillance, robot navigation and human-machine interaction etc. Meanshift is widely used algorithm in video target tra...Target tracking in video is a hot topic in computer vision field, which has wide applications in surveillance, robot navigation and human-machine interaction etc. Meanshift is widely used algorithm in video target tracking field. The basic mean shift algorithm only considers the color of targets as the tracking characteris- tic feature, so if the appearance of the target changes greatly or there exits other objects whose color is similar to the target, the tracking process will fail. To enhance the stability and robustness of the algorithm, we introduce par- ticle filter into the tracking process. Basic particle filter has some disadvantages such as low accuracy, high computational complexity. In this paper, an improved particle filter GA-UPF was proposed, in which a new re-sampling algorithm was used to predict target centroid position. The target tracking system of binocular stereo vision is designed and implemented. Experi- mental results have shown that our algorithm can tracking object in video with high accuracy and low computational complexity.展开更多
基金Project supported by the National Natural Science Foundation ofChina (No. 60673024)the National Basic Research Program(973) of China (No. 2004CB719400)
文摘In this study, an unscented particle filtering method based on an interacting multiple model (IMM) frame for a Markovian switching system is presented. The method integrates the multiple model (MM) filter with an unscented particle filter (UPF) by an interaction step at the beginning. The framework (interaction/mixing, filtering, and combination) is similar to that in a standard IMM filter, but an UPF is adopted in each model. Therefore, the filtering performance and degeneracy phenomenon of particles are improved. The filtering method addresses nonlinear and/or non-Gaussian tracking problems. Simulation results show that the method has better tracking performance compared with the standard IMM-type filter and IMM particle filter.
基金supported by the National Natural Science Foundation of China(7092100160574058)+1 种基金the Key International Cooperation Programs of Hunan Provincial Science & Technology Department (2009WK2009)the General Program of Hunan Provincial Education Department(11C0023)
文摘Many Bayesian learning approaches to the multi-layer perceptron(MLP) parameter optimization have been proposed such as the extended Kalman filter(EKF).This paper uses the unscented Kalman particle filter(UPF) to train the MLP in a selforganizing state space(SOSS) model.This involves forming augmented state vectors consisting of all parameters(the weights of the MLP) and outputs.The UPF is used to sequentially update the true system states and high dimensional parameters that are inherent to the SOSS model for the MLP simultaneously.Simulation results show that the new method performs better than traditional optimization methods.
文摘Target tracking in video is a hot topic in computer vision field, which has wide applications in surveillance, robot navigation and human-machine interaction etc. Meanshift is widely used algorithm in video target tracking field. The basic mean shift algorithm only considers the color of targets as the tracking characteris- tic feature, so if the appearance of the target changes greatly or there exits other objects whose color is similar to the target, the tracking process will fail. To enhance the stability and robustness of the algorithm, we introduce par- ticle filter into the tracking process. Basic particle filter has some disadvantages such as low accuracy, high computational complexity. In this paper, an improved particle filter GA-UPF was proposed, in which a new re-sampling algorithm was used to predict target centroid position. The target tracking system of binocular stereo vision is designed and implemented. Experi- mental results have shown that our algorithm can tracking object in video with high accuracy and low computational complexity.
