基于纹理与特征选择的前视红外目标识别

针对前视红外(FLIR)目标自动目标识别(ATR)问题 ,提出了一种基于纹理特征的ATR方法。不同于传统基于学习、基于 模板以及基于稀疏表示的方法,从图像灰度入手,提出采用局部三值模式(LTP )描述图像纹理特征,同时结合FLIR图像的特点,对LTP进行了增强处 理；然后针对特征的高维问题,采用特征选择方法进行降维处理；最后 采用降维后的特征实现ATR。实验结果表明,本文方法取得了比传统方法 更好的效果；同时也证明,仅从纹理分析入手,也能较好地实现前视红外目标的ATR。

Forward-looking infrared target recognition based on texture and feature select ion

Unlike the traditional learning-based, template-based and sparse-ba sed approaches, this paper presents a novel feature extraction algorithm based on texture and feature selection for automatic target recognition (ATR) in infrared imagery.Firstly, combining with the characteristics of the forward-looking-infrared (FLIR) imag es,we introduce a new concav e-convex local ternary pattern (CCLTP) operator by incorporating global intensity information,which divides the local features LTP into two distinct groups,namely,convex LTP and concave LTP.After that,different feature selection methods are discussed and tested to reduce the dimensionality of the features.Finally,the reduced feature is used for forward-looking infrared target recognition.Experi mental results demonstrate that the proposed method can achieve competitive results (at lower computational complexity) compared with th e state-of-the-art methods.