基于OpenCV的二维定位系统设计

Design of Two-dimension Location System Based on OpenCV

提出一种在照、摄像机内部参数未知的条件下,由单幅二维投影图像进行目标定位的方法和系统设计方案。即对目标平面上位置已知的参考特征点与他们在二维图像上的投影仅进行一次匹配训练,便可由单幅二维图像确定目标方位。文中以Intel公司开发的开源计算机视觉库OpenCV作为定位系统的开发工具,充分利用其提供的函数库功能,根据本系统的特点在组件层次上进行设计和优化,提高了定位的精度和效率,具有良好的跨平台移植性,可以满足多种计算机视觉系统的需要。

This paper presents a method and system design of determining the position of an object from a two-dimensional image in the absence of the interior parameters of the camera.This can be achieved by training the matching relationship between the characteristic points whose positions are known in the destination plane and their correspondences in the two-dimensional perspective image.We use the OpenCV-Intel corporation＇s open source computer vision library as the designed tool to make the most of the functions of the library,to design and optimize the system on the component levels according to its characteristics.This improves the accuracy and efficiency of the locating system,can satisfy the need of many computer vision systems with good cross-platform portability.