针对车辆跟踪过程中跟踪目标丢失或者失败的情况,提出一种改进型Camshift(Continuously Adaptive Mean Shift)算法和卡尔曼滤波相结合的跟踪方法。首先,利用卡尔曼滤波器实现跟踪目标的位置估计,以克服目标被遮挡造成的跟踪失败的问题,...针对车辆跟踪过程中跟踪目标丢失或者失败的情况,提出一种改进型Camshift(Continuously Adaptive Mean Shift)算法和卡尔曼滤波相结合的跟踪方法。首先,利用卡尔曼滤波器实现跟踪目标的位置估计,以克服目标被遮挡造成的跟踪失败的问题,然后再利用改进型Camshift算法依据目标距离搜索中心的位置,对H分量创建的颜色直方图中的每个像素位进行高斯模型核函数的加权处理,并自适应计算得到最优的搜索窗口,从而改善了传统Camshift不能直接抵制噪声干扰的缺点,解决了因跟踪目标在同色背景噪声干扰下出现的丢失问题。最后通过仿真实验表明:改进型Camshift算法和卡尔曼滤波的结合有效地提高了车辆跟踪的准确性和连续性。展开更多
This paper put forward the super-resolution image algorithm based on Gauss process regression sparse solution. We establish local Gauss process regression model, to solve the feasibility problem of regression super-re...This paper put forward the super-resolution image algorithm based on Gauss process regression sparse solution. We establish local Gauss process regression model, to solve the feasibility problem of regression super-resolution problem in solving Gauss process; further use sparse algorithm, not only it can optimize the super parameter of Gauss kernel function, but also to optimize the initial entry training, so as to obtain more accurate regression Gauss process. Experimental results show that： the paper proposed algorithm can does not reduce the image reconstruction results, and it can reduce the computational complexity.展开更多
The logistic growth model with correlated additive and multiplicative Gaussian white noise is used to anedyze tumor cell population. The effects of perfectly correlated and anti-correlated noise on the stationary prop...The logistic growth model with correlated additive and multiplicative Gaussian white noise is used to anedyze tumor cell population. The effects of perfectly correlated and anti-correlated noise on the stationary properties of tumor cell population are studied. As in both cases the diffusion coefficient has zero point in real number field, some special features of the system are arisen. It is found that in cause tumor cell extinction. In the perfectly anti-correlated tumor cell population exhibit two extrema. both cases, the increase of the multiplicative noise intensity case, the stationary probability distribution as a function of展开更多
Machine learning techniques which are about the construction and study of system that can learn from data are combined with many application fields.A method on ionospheric total electron content(TEC)mapping is propose...Machine learning techniques which are about the construction and study of system that can learn from data are combined with many application fields.A method on ionospheric total electron content(TEC)mapping is proposed based on radical basis function(RBF)neural network improved by Gaussian mixture model(GMM).Due to the complicated ionospheric behavior over China,GMM is used to determine the center of basis function in the unsupervised training process.Gradient descent is performed to update the weights function on a sum of squared output error function in the supervised learning process.The TEC values from the center for orbit determination in Europe(CODE)global ionospheric maps covering the period from 2007to 2010 are used to investigate the performance of the developed network model.For independent validation,the simulated TEC values at different latitudes(20°N,30°N and 40°N)along 120°E longitude are analyzed and evaluated.The results show that the simulated TEC from the RBF network based model has good agreement with the observed CODE TEC with acceptable errors.The theoretical research indicates that RBF can offer a powerful and reliable alternative to the design of ionospheric TEC forecast technologies and thus make a significant contribution to the ionospheric modeling efforts in China.展开更多
文摘针对车辆跟踪过程中跟踪目标丢失或者失败的情况,提出一种改进型Camshift(Continuously Adaptive Mean Shift)算法和卡尔曼滤波相结合的跟踪方法。首先,利用卡尔曼滤波器实现跟踪目标的位置估计,以克服目标被遮挡造成的跟踪失败的问题,然后再利用改进型Camshift算法依据目标距离搜索中心的位置,对H分量创建的颜色直方图中的每个像素位进行高斯模型核函数的加权处理,并自适应计算得到最优的搜索窗口,从而改善了传统Camshift不能直接抵制噪声干扰的缺点,解决了因跟踪目标在同色背景噪声干扰下出现的丢失问题。最后通过仿真实验表明:改进型Camshift算法和卡尔曼滤波的结合有效地提高了车辆跟踪的准确性和连续性。
文摘This paper put forward the super-resolution image algorithm based on Gauss process regression sparse solution. We establish local Gauss process regression model, to solve the feasibility problem of regression super-resolution problem in solving Gauss process; further use sparse algorithm, not only it can optimize the super parameter of Gauss kernel function, but also to optimize the initial entry training, so as to obtain more accurate regression Gauss process. Experimental results show that： the paper proposed algorithm can does not reduce the image reconstruction results, and it can reduce the computational complexity.
基金Supported by the National Natural Science Foundation of China under Grant No. 11045004
文摘The logistic growth model with correlated additive and multiplicative Gaussian white noise is used to anedyze tumor cell population. The effects of perfectly correlated and anti-correlated noise on the stationary properties of tumor cell population are studied. As in both cases the diffusion coefficient has zero point in real number field, some special features of the system are arisen. It is found that in cause tumor cell extinction. In the perfectly anti-correlated tumor cell population exhibit two extrema. both cases, the increase of the multiplicative noise intensity case, the stationary probability distribution as a function of
基金supported by the National Natural Science Foundation of China(Grant No.41104096)
文摘Machine learning techniques which are about the construction and study of system that can learn from data are combined with many application fields.A method on ionospheric total electron content(TEC)mapping is proposed based on radical basis function(RBF)neural network improved by Gaussian mixture model(GMM).Due to the complicated ionospheric behavior over China,GMM is used to determine the center of basis function in the unsupervised training process.Gradient descent is performed to update the weights function on a sum of squared output error function in the supervised learning process.The TEC values from the center for orbit determination in Europe(CODE)global ionospheric maps covering the period from 2007to 2010 are used to investigate the performance of the developed network model.For independent validation,the simulated TEC values at different latitudes(20°N,30°N and 40°N)along 120°E longitude are analyzed and evaluated.The results show that the simulated TEC from the RBF network based model has good agreement with the observed CODE TEC with acceptable errors.The theoretical research indicates that RBF can offer a powerful and reliable alternative to the design of ionospheric TEC forecast technologies and thus make a significant contribution to the ionospheric modeling efforts in China.
