基于灰关联分析的红外图像边缘检测算法

An Algorithm of Infrared Imaging Edge Detection Based on Grey Relational Analysis

提出了一种用于红外成像导弹的改进型边缘检测算法,该算法基于灰色系统理论中的灰关联分析方法。首先选取基于像素的参考序列和比较序列,由参考序列和比较序列的灰关联度来判断像素点的系统行为,即属于边缘点或非边缘点;然后通过改变维空间中距离测度的参考点来提高算法的实时性;最后通过仿真试验及实时性分析,证明该算法不仅能够很好的检测出边缘,具有良好的抗噪声能力,而且实时性有了进一步提高。论文提出的改进型边缘检测算法对红外成像制导系统有一定的参考意义。

A new and improved edge detection algorithm is developed based on grey theory and grey relational analysis （GILA） ,which applies to the target recognition of the infrared imaging missile. At first the selection of referential sequence and comparative sequence is introduced and analyzed based on pixels. Then the grey relational degree between two sequences is calculated to make an estimate of the system behavior and distinguish between the edge pixels and non - edge pixels. Finally,it is put forward that the real time attribute of the algorithm can be improved by changing the reference point of the distance measure in k - dimensions space, that is to say changing the value of the referential sequence. The calculation result and the analysis of real - time attribute show that the suggested algorithm can detect and obtain more precise edge pixels against noise. The results also show that the real - time attribute of the suggested is improved compared with other algorithms. The algorithm research provides a good reference for engineering applications of the edge detection used in the infrared imaging seeker.