目前视频侦查工作中主要采用人工观察的方式对视频监控的内容进行分析,主观性较强,且容易受到监控视频数据量大的影响,从而导致误判、漏判以及实时性差等问题。针对上述问题,提出了一种监控视频中人体目标运动速度估计的方法,首先采用背景差分算法从监控视频中提取人体目标,然后对包含人体目标的二值图像进行数学形态学的开/闭运算后计算人体目标最小外接矩阵的中点,最后通过计算最小外接矩形中点的移动距离 ...
张洪君 +4 more
core
[Adaptive weighted fuzzy iterative learning control strategy for functional electrical stimulation integrating guiding-side surface electromyogram threshold gating and dynamic frequency adjustment]. [PDF]
Liu S +6 more
europepmc +1 more source
[X-ray-guided lung puncture navigation integrating direct linear transformation-Gauss-Newton method and marker-free registration]. [PDF]
Qian Y +5 more
europepmc +1 more source
[A deep learning-based method for rapid reconstruction and prediction of electromagnetic exposure in pacemaker patients]. [PDF]
Wei J, Tian R, Zhang R, Lu M.
europepmc +1 more source
[Motion parameter decoupling and motion constraint-driven optimization for correcting rigid motion artifacts in cone-beam computed tomography]. [PDF]
Jiang H, Wang Y, Bian Z.
europepmc +1 more source
Speed and Load Torque Estimation of Induction Motors Based on Adaptive Kalman Filtering
针对常规EKF估计结果受给定的噪声协方差阵影响较大的问题,提出了一种基于自适应卡尔曼滤波(Adaptive Kalman filtering,AEKF)来同时估计电机转速和负载转矩的方法。在用AEKF估计转速和负载转矩时,根据AEKF的要求,将电机增广随机数学模型的输入噪声与建模误差引入的噪声直接合并,等效为状态噪声;基于变换后的模型,利用状态预测残差估计状态噪声协方差阵,利用观测残差估计观测噪声协方差阵,实现了噪声协方差阵自适应变化。实验结果表明:所提方法的估计结果基本不受给定的噪声协方差阵初值影响 ...
胡静涛, 于洪霞
core
[Application effect of LLMs as decision-support tools in emergency burn treatment]. [PDF]
Yan MT, Wei JT, Jiang SY, Wu P, Wang XG.
europepmc +1 more source
[Research progress on generative adversarial network-based CBCT-to-CT synthesis with multidimensional constraints]. [PDF]
Yang W, Kang J, Keung S.
europepmc +1 more source
响应变量存在数据缺失的情况广泛出现在社会经济研究中,对响应变量存在数据缺失的回归模型提出了一个在矩估计框架下的单一的半参数估计量,这种估计量保留了参数回归估计量与非参数匹配估计量的特性,从而使得该估计量既能在响应变量被观测的子样本中保持较好的拟合性,又能够降低响应变量未被观测的子样本的估计误差,并且证明了这种估计量是一致 ...
邓明
core

