基于位置分辨率的折反射全向图像邻域定义

Neighborhood Definition for Catadioptric Omnidirectional Image Based on Resolution of Position

由于折反射投影,两个具有相同欧氏距离的世界点,当它们成像在折反射全向图像边缘或图像中心时,它们之间的像素距离却并不相同.因此,传统的邻域选取方法并不适合折反射全向图像处理.本文根据全向图像不同位置分辨率的比例关系,提出了一套新的邻域定义方法并推导了一种新的折反射全向图像分辨率计算公式.通过在马尔可夫随机场全向图像运动目标检测应用中与传统邻域进行对比实验,显示改进后的邻域比传统邻域在整个图像中有更一致的检测效果.

Because of catadioptric imaging,two points in the world with same distance will have different distance in omnidirectional image when they are projected to the periphery or center on the image plane.Thus,traditional definition of the neighborhood cannot be appropriate for omnidirectional images.In this paper,make use of ratio of resolution between different position in image,we propose a new system of neighborhood adapted to the omnidirectional images and deduce a new formula for calculating resolution of a catadioptric sensor.We show that this definition of neighborhood for catadioptric omnidirectional image conduce a more coincident result than traditional one in application of moving target detection base on Markov random fields.