Location:
Search - Residual taylor
Search list
Description: 本程序实现多算法协同定位中第一层数据融合，将CHAN算法结果和泰勒算法结果经过残差加权算法加权-Many algorithms implementation of this procedure in the first tier co-location data fusion, will CHAN Taylor algorithm algorithm results and the results of the weighted residual method after the weighted
Platform: |
Size: 1024 |
Author: 张靖悦 |
Hits:
Description: 本程序实现多算法协同定位中第一层数据融合，将CHAN算法结果和泰勒算法结果经过残差加权算法加权代码，已通过测试。-The program co-location multi-algorithm in the first layer data fusion, the algorithm results and Taylor algorithm CHAN results through a weighted residual weighting algorithm code has been tested.
Platform: |
Size: 1024 |
Author: |
Hits:
Description: 本程序实现多算法协同定位中第一层数据融合，将CHAN算法结结果和泰勒算法结果经过残差加权算法加权，已通过测试。
-This program is multi-algorithm for collaborative positioning of the first layer of data fusion, the CHAN algorithm knot results and Taylor algorithm results weighted residual weighting algorithm, has been tested.
Platform: |
Size: 1024 |
Author: ttian1000 |
Hits:
Description: 利用KLT跟踪算法进行兴趣点选取和跟踪。
KLT跟踪算法的原始思想是在研究不同图像之间的匹配问题时，通过计算两个平移窗口的灰度残差，并寻找最小化残差SSD(sum of square difference)来实现匹配的。但是这个过程是没有效率的，因此KLT算法进行了优化。在这个过程中，KLT算法使用泰勒展开直接计算平移矢量，而不需要通过遍历进行搜索。
-KLT tracking algorithm to select a point of interest and tracking. KLT tracking algorithm original idea is to study the matching between different images, by calculating the two translational window gray residuals and seeks to minimize the residual SSD (sum of square Difference) matching. But this process is not efficient, KLT algorithm has been optimized. In this process, the KLT algorithm uses the Taylor expansion of the direct calculation of the translation vector, without the need to search by traversing.
Platform: |
Size: 2219008 |
Author: |
Hits:
Description: 数学算法中的一种迭代方法，高斯迭代法，是使用泰勒级数展开式去近似地代替非线性回归模型，然后通过多次迭代，多次修正回归系数，使回归系数不断逼近非线性回归模型的最佳回归系数，最后使原模型的残差平方和达到最小。-Mathematical algorithms in an iterative method, Gauss iterative method, using the Taylor series expansion to approximate instead of nonlinear regression models, and then through several iterations, several amendments to the regression coefficients, so that the regression coefficients closer and closer to non-linear regression model The best regression coefficients, and finally the residual sum of squares of the original model and to a minimum.
Platform: |
Size: 1024 |
Author: meihaodi |
Hits: