基于最大中值滤波和K-means聚类红外弱小目标检测
Infrared Dim and Small Target Detection Based on Max-median Filter and K-means Clustering Algorithm
由于背景边缘及强噪声的存在,红外弱小目标容易被覆盖,弱小目标的检测一直是红外图像处理的难点。在分析红外图像模型的基础上,引入最大中值滤波,在不影响边缘锐度的条件下,较好地抑制孤立噪声点,有效提高信噪比,然后采用基于方差的K均值聚类算法最终检测出弱小目标。实验结果表明,与传统滤波算法及形态学算法相比,该算法计算简单,能有效检测出弱小目标。
The dim and small infrared targets are easily covered for the background edge and strong noise, andthe dim and small target detection is always the difficulties of infrared image processing. Based on analyzing the in-frared image model, max-median filter algorithm is introduced to inhibit isolated noise point and improve signal tonoise rate(SNR) under the condition of no influence on edge sharpness. And the dim and small target is detected atlast using variance K-means clustering algorithm. Experimental results show that comparing with traditional filter-ing and morphologic algorithms, the algorithm has simple calculation, which can effectively get the dim and smalltarget.
dim and small target; false alarm rate; max-median filter; signal to noise rate(SNR);
TP391.41
Read this article on cellphoneDownload and install mobile APPScan QR codes and read this article synchronously
Instantly read on your cellphone
The first stepScan QR Codes
"Mobile CNKI-CNKI Express" App
The second step打开“CNKI Express”
Click the scan icon in the upper left corner of the homepage
Scan QR Codes
Read this article on cellphone synchronously