Description: 一种核密度估计，或者称作带宽选择的方法，可以估计二维尺度参数，至于多维以上的估计方法尚在开发，多维情况下个人经验好的方法是多次实验取较好值-kernel density estimation, bandwidth selection, two-dimensional scale parameter can be estimated ,for the multi-dimensional approaches are still under development, multi-dimensional cases, personal experience is to do the experiment many times Platform: |
Size: 623616 |
Author:苗晨 |
Hits:
Description: 以为高斯和密度估计，使用高斯核的非参数密度估计方法，对样本进行概率密度估计，程序中给出了窗宽的估算公式。-That the Gaussian and density estimation, using Gaussian kernel non-parametric density estimation method, the sample probability density estimates, the program gives the formula for bandwidth estimation. Platform: |
Size: 1024 |
Author:william |
Hits:
Description: 横轴和纵轴，可以将样本点表示出来。由于一般第一、二和三主成分包含的样本的信息较多，
经常选其作为横轴和纵轴。当两个样本差异不大时，他们对应的主成分的得分值差异也不会大，
所以可以凭此对样本进行分类。-The quality of the sample
depends on the accuracy of the density estimator chosen, and it needs to decide the kinds of kernel function and the value of its bandwidth and $\alpha$. Besides
there are some drawback about the relation between the value $\alpha$ and the ratio of cluster and outlier. In the future, the extension of
its techniques to data sets of very high dimensionality is possible by taking into account several properties of high-dimensional spaces. Platform: |
Size: 616448 |
Author:宋云胜 |
Hits:
Description: 针对核密度估计背景建模方法运算量大难以实时应用的问题，提出了一种基于背景直方图分布的快速核密度估计背景建模方法。选用三角核函数进行核密度估计，根据三角核带宽函数的截断效应，引入背景分布的直方图完成快速背景建模，在保证目标检测准确性的同时提高运算速度。测试实验结果验证了算法能够满足监控系统的实时性要求。-For kernel density estimation is difficult to satisfy real-time applications because of large amount of calculation, this paper
proposes a fast kernel density estimation method of background modeling based on the background histogram. Triangle kernel function
is used to estimate the kernel density. According to the triangular truncation effect of kernel-bandwidth function, background samples
histogram is built to complete the fast background modeling. The accuracy of target detection is ensured while processing speed is increased.
Experimental results prove that the algorithm satisfies the real-time requirements of surveillance systems Platform: |
Size: 1409024 |
Author: |
Hits:
Description: 二维高斯核函数重构
重构方法不依赖于参数化模型-2D Gaussian Kernel Reconstruction
fast and accurate state-of-the-art
bivariate kernel density estimator
with diagonal bandwidth matrix.
The kernel is assumed to be Gaussian.
The two bandwidth parameters are
chosen optimally without ever
using/assuming a parametric model for the data or any rules of thumb .
Unlike many other procedures, this one
is immune to accuracy failures in the estimation of
multimodal densities with widely separated modes Platform: |
Size: 4096 |
Author:zty |
Hits:
Search - kernel density bandwidth