基于标定信息的高低分辨率图像配准方法

Registration method between high-low resolution images based on calibration information

针对激光三维成像系统分辨率较低,特征点不易提取,同时与可见光成像系统图像配准实时性不高的问题,提出了一种基于标定信息的低分辨率距离图像与高分辨率强度图像配准方法。首先,通过对激光三维成像系统与可见光成像系统进行标定,得到了二者的内参数、外参数以及畸变系数;其次,利用二者的标定信息,通过构造像素匹配模型,确定了低分辨率距离图像像素点所对应的高分辨率强度图像像素点。最后,通过遍历低分辨率距离图像每一个像素点,实现低分辨率距离图像与高分辨率强度图像的像素配准。实验结果表明:该方法在保持准配精度基本不变的情况下,配准时间从2.111 s减为0.856 s,降低了算法的时间消耗,具有一定的可行性。

Due to the low-resolution of three-dimension laser image,feature points are difficult to extract and the speed of image pixel registration between three-dimensional image and visible image is slow. In order to solve these problems,a registration method between low resolution distance image and high resolution intensity image is proposed based on the calibration information of optical imaging systems. Firstly,by means of calibrations of the three-dimensional image and visible image,their intrinsic external parameters and distortion coefficients are obtained. Subsequently,by establishing pixel registration model,the corresponding pixels between low-resolution distance image and high-resolution intensity image are determined on the basis of their calibration informations. Finally,by iterating each pixel of low-resolution image,the pixel registration is achieved. The experiment results show that the proposed method reduces the registration time from 2. 111 s to 0. 856 s,while remains registration accuracy.