基于伪Wigner-Ville分布和Rnyi熵的显著图目标检测

Target detection of saliency map based on pseudo Wigner-Ville distribution and Rényi entropy

在复杂背景中,往往难以实现目标的自动检测,依据Wigner-Ville分布能够对图像在空间域/空间频率域上联合表示的特性.研究了图像经伪Wigner-Ville分布后Rnyi熵的统计特性,分析了人造目标的出现会引起自然场景中Rnyi熵统计特性的变化,并在此基础上提出了一种新的基于伪Wigner-Ville分布和Rnyi熵的显著图生成方法.之后对显著图进行简便的阈值分割,完成目标检测.实验结果表明,所提出的方法能够有效地检测复杂地面背景中的军用车辆.

Automatic target detection is always difficult in complex background. The Wigner-Ville distribution has a good characteristic that the images can be represented in spatial/spatial-frequency domains. Through the pseudo Wigner-Ville distribution, the statistical property of Rényi entropy is studied. The change of Rényi entropy’s statistical property in natural images when the man-made objects appear is analysed. Then a novel method for generating saliency map based on pseudo Wigner-Ville distribution and Rényi entropy is proposed. Target detection is performed when the saliency map is segmented using a simple and convenient threshold method. Experimental results show the proposed method can detect the military vehicles from complex earth background effectively.