基于方向极傅里叶频谱2DPCA 的尾迹检测

针对航空图像中的水面尾迹, 提出了一种基于方向极傅里叶频谱二维主成分分析(Two-dimensional principal component analysis, 2DPCA)的尾迹自动检测算法. 该方法根据子图像的纹理方向, 对傅里叶频谱进行极坐标变换, 使得到的方向极傅里叶频谱具有平移和旋转不变性. 相对于文献中对极频谱的直接划分作为纹理特征, 本文对它进行一次列二维主成分分析, 一次行二维主成分分析和两次二维主成分分析, 实验结果表明本文方法具有更高的分类识别率, 其中两次二维主成分分析的分类识别率最高. 对40幅图像的测试结果表明, 本文的方法能够有效地自动检测航空图像中的水面尾迹纹理.

Wake Detection Using 2DPCA of Directional Polar Fourier Spectrum

A wake detection method is proposed for the water wake of airphotoes based on two-dimensional principal component analysis(2DPCA)of directional polar Fourier spectrum.This method improves the traditional principal components analysis to obtain the image direction from their Fourier power spectrum,and transforms the Fourier spectrum into the polar coordinates based on the image direction.The directional polar Fourier spectrum are translation and rotation invariant.Compared to the previous method of partitioning the polar spectrum to achieve texture features,the row 2DPCA,the column 2DPCA,and the improved 2DPCA are used to analysis the directional polar Fourier spectrum. From experimental results of 40 images,it is proved that the proposed algorithm can fetch the wake texture precisely.