红外技术, 2016, 38 (9): 779, 网络出版: 2016-10-19
沙漠背景下红外偏振图像目标检测方法
Target Detection for Infrared Polarization Image in the Background of Desert
红外偏振 核模糊 C均值聚类 稀疏融合 模式识别 infrared polarization kernel fuzzy C clustering sparse fusion pattern recognition
摘要
红外偏振成像探测同时探测目标的强度辐射与反射偏振态,可以获取传统光学无法获取的目标。偏振探测获取的偏振度、偏振角等信息反映不同的物理特性,与强度图像有较强的互补性。针对该特性,提出一种沙漠背景目标红外偏振图像检测方法。使用一种改进的核模糊聚类算法对红外图像和偏振图像进行聚类处理;利用稀疏融合方法将聚类后的红外图像和偏振度图像中的物体信息充分结合,以区分目标与背景,以达到目标检测的目的。实验表明,提出的检测方法相对小波融合和拉普拉斯金字塔融合结果噪声更低、细节更清晰。
Abstract
Infrared polarization imaging detection can be used to obtain not only the polarization state but also the radiation of target. With this method, the target that traditional photometry cannot detect can be settled. The degree and angle of polarization that used in polarization detection reflect different physical properties, and it is strongly complementary to intensity of images. A target detection method for polarization infrared image in the background of desert is proposed aiming at such features. A modified kernel fuzzy clustering algorithm is used to cluster infrared images and the polarization images. Then to distinguish targets from the background, the object information of clustered infrared and polarization image are combined according to sparse fusion method. Experimental results show that the proposed detection method is with lower noise and more clear details than wavelet fusion and Laplacian pyramid fusion.
李小明, 黄勤超. 沙漠背景下红外偏振图像目标检测方法[J]. 红外技术, 2016, 38(9): 779. LI Xiaoming, HUANG Qinchao. Target Detection for Infrared Polarization Image in the Background of Desert[J]. Infrared Technology, 2016, 38(9): 779.