基于对数极坐标映射的目标搜索方法

文中提出了一种基于对数极坐标映射的目标搜索方法，均匀取样的传感器所获得的像包含有许多相对特定目标搜索而言冗余的信息，对这些信息的处理往往要消耗许多时间。对数极坐标映射可以近似模拟人眼视网膜到条状表皮的映射，利用映射的比例和旋转不变性，可以对大视场目标进行搜索识别。对数极坐标映射将对空间均匀取样得到的图像变换成非均匀取样的图像，减少冗余像素，压缩搜索空间，从而降低运算量，提高系统的目标快速捕获能力

Target searching method based on log-polar coordinate mapping

A target searching method based on log|polar coordinate mapping is presented in this paper. For specific object searching, the amount of redundant information, which is acquired by uniform sampling sensor, will cost much computer time. The mapping between the retina of human eye and the striate cortex can be approximated by a log|polar coordinate mapping. Its scaling and rotation invariance are useful for object searching and recognition in large viewfield. A uniform sampling image can be transformed to a space variant sampling image by log|polar coordinate mapping which reduces the searching space and redundant pixels. It greatly decreases the amount of computation and improves the target recapture ability in system.