顾及空间分布的改进薄板样条矢量数据几何精度降低方法

A Vector Data Geometric Accuracy Reduction Method Considering Spatial Distribution Based on the Improved Thin Plate Spline Model

随着测绘地理信息数据的共享应用成为趋势,地理数据的精度降低处理成为数据公开前不可缺少的环节。基于传统薄板样条插值的坐标偏移模型利用本身优势可以实现坐标变换从而降低数据的几何精度,但是该模型受控制点精确程度影响大,抗噪声能力弱,若控制点选取不合理则易产生要素形态畸变的问题,导致数据无法被使用。本文提出了一种顾及空间分布的改进薄板样条矢量数据精度降低方法,首先通过四叉树索引结构进行格网划分,分别在网格内选取控制点,使得选出的控制点对和原始矢量数据在空间分布特征和数量特征上一致。然后基于Tikhonov正则化思想在原始坐标偏移模型中添加正则化项,弱化控制点的约束作用,增强模型抗噪声能力。本文选取不同尺度、不同类型以及多图层数据进行精度降低测试,实验表明:(1)本文算法针对不同实验数据都可以满足自然资源部95号文公开地图精度不高于10 m的要求,模型普适性好且效率较高;(2)本文算法能有效提高模型的稳定性以及减少处理后坐标突变的问题。以南京市鼓楼区线数据为测试数据的计算结果表明,精度降低后数据空间方向一致性为99.62%,图形形态相似性为99.99%,均优于传统薄板样条模型与高斯基函数坐标偏移模型;(3)本文算法使精度降低后数据的偏移效果实现局部一致性以及全局随机性,精度降低后数据在明攻击或盲攻击的情况下精度仍能保持在10 m左右,说明坐标偏移结果不易被恢复。本研究证明提出的顾及空间分布的改进薄板样条精度降低模型兼顾处理后数据的安全性以及可用性,促进了矢量地理数据的社会化应用。

With the sharing and application of surveying and mapping geographic information data,the accuracy reduction of geographic data prior to data release has become an essential step to avoid leaks of classified highprecision data that could threaten national security.Geometric accuracy reduction is an important component of geographic data accuracy reduction,which refers to transforming the coordinates of element points and reducing the precision of the publicly available data.The traditional thin plate spline interpolation model can achieve coordinate transformation with its advantages.However,this model is easily influenced by the accuracy of control points and is not robust against noise.For example,if the control points are not selected reasonably,data morphological distortion easily occurs due to noisy control points,resulting in poor data quality.In this article,a vector data accuracy reduction method considering spatial distribution based on the improved thin plate spline model is proposed.Firstly,the grid is divided by quadtree index structure.The control points are selected in each grid,so that the selected control points are consistent with the original vector data in terms of spatial distribution and quantitative characteristics.Then,regularization terms are added to the traditional function based on Tikhonov regularization to weaken the constraint imposed by control points and enhance the anti-noise ability of the model.We choose vector geographic data with different scales and types and multi-layer vector geographic data for experiments.Results show that:(1)Based on different experimental data,our algorithm can meet the requirement that the procerssed data precision should not exceed 10 meters according to the No.95 official document from the Ministry of Natural Resources,which demonstrates the model adaptability and efficiency;(2)The algorithm can effectively improve model stability and reduce abrupt changes in coordinates.The experiment conducted on the line data of Gulou District in Nanjing shows that,the processed data exhibit a spatial directional consistency of 99.62%and a graphical morphological similarity of 99.99%,which outperforms the results based on traditional thin plate spline model and guassian radial basis function model;(3)The offset effect is locally consistent and globally random.The processed of the processed data after either direct attacking or blind attacking remains around 10 meters,indicating the difficulty of recovering processed data to original results.This research proves that the proposed model can balance data's security and availability,promoting social application of vector geographic data.