基于互信息量的图像目标定位研究

Image Target Localization Based on Mutual Information

为了实现图像目标定位的准确识别,提出一种基于互信息量的图像目标定位方法.首先对图像进行压缩,然后按照图像结构纹理的相关度进行像素信息融合,采用互信息量对图像进行区域标定和特征检测,实现图像目标的块匹配检测定位,最后在Matlab环境下进行仿真测试.结果表明,该方法对图像目标定位的速度快,定位误差小,有较强的抗干扰能力.

In order to identify image target location accurately,a new method based on mutual information is proposed. Firstly, the image is compressed, and then pixel information is fused according to correlation of image structure texture, image region labeling and feature detection are matched by using mutual information, and localization is realized for block image target, finally the simulation test is carried out in Matlab. The results show that the proposed method has advantages of high speed, small positioning error and strong antiinterference ability.