基于小波变换的运动目标特征提取

The Feature Detection of Moving Target Based on Wavelet Transform

本文研究的目的就是针对飞机、车辆等运动目标,如何提取角点特征。提出了一种基于小波变换的特征提取方法,充分利用了双正交小波的多尺度特性、对称性、正则性的优点,作者选取了角点这一重要的局部特征作为研究对象,并以曲率为出发点,结合基于灰度图像和边缘图像的角点检测方法提取角点,最后与其他方法提取的角点进行了比对。实验表明,这种方法的稳定性较强、算法简单,在同等运算量的情况下提高了角点的准确性。

The purpose of this article is used to detect corner feature for moving object such as airplane and automobile.A feature detection algorithm based on wavelet transform was proposed,it makes full use of multi-scale feature,symmetry and regularity of Biorthogonal Wavelet,The corner was regarded as the important local feature.At the beginning of the curvature,the author proposed the algorithm combined the grey image corner detection ways with the edge corner detection ways.At last,the author compared the exper...