基于双目视觉的目标测距研究

为了获取目标物体在空间中的三维信息,设计了一个基于双目视觉的目标测距系统,采用张正友棋盘标定法获取相机内外参数,并采取SGBM立体匹配在VS2013环境下结合OpenCV库,对图像进行了立体匹配,生成视差图。实验表明:该系统具有良好的效果。

基于机器视觉的机器人测距研究

机器人测距技术是机器人导航、路径规划以及协作编队关键技术之一。基于透视投影几何原理,提出了单目视觉测距模型,实现物体测距。单目视觉测距模型实现了在摄像机与目标平面平行或者有夹角情况下,对目标物体距离的测量。实验结果表明,所提出的测距模型和和所用的算法,不仅避免了复杂的摄像机标定,而且测量速度快,能够实现对目标物体空间距离的精确测量。

基于单目视觉的边坡位移检测方法研究

针对边坡表面状态发生的变化检测,提出了一种新的智能检测方法。人工设置两个目标体分别作为观测点和监测点,以投影构成的位移阵与其投影阵目标质心、面积等参数的空间关系,计算出摄像距离阵、观测标识与定位标识投影距离、深度差等距离参数,得到三维解算所需各类距离信息。采用空间三点定标方法,完成位移阵空间数据解算。

Spatial Object Aggregation Based on Data Structure, Local Triangulation and Hierarchical Analyzing Method

This paper focuses on the methods and process of spatial aggregation based on semantic and geometric characteristics of spatial objects and relations among the objects with the help of spatial data structure (Formal Data Structure),the Local Constrained Delaunay Triangulations and semantic hierarchy.The adjacent relation among connected objects and unconnected objects has been studied through constrained triangle as elementary processing unit in aggregation operation.The hierarchical semantic analytical matrix is given for analyzing the similarity between objects types and between objects.Several different cases of aggregation have been presented in this paper.

Stckelberg Holographic Superconductor Models with Backreactions

We study the Stiickelberg holographic superconductors away from the probe limit. We find that the backreaction of the spacetime can bring richer physics in the phase transition. Moreover we observe that the ratio ω9 /Tc changes with the strength of the backreaction and is not a universal constant.