Wide-baseline stereo matching based on multiple views

To solve the problem of wide-baseline stereo image matching based on multiple cameras,the paper puts forward an image matching method of combining maximally stable extremal regions (MSER) with Scale Invariant Feature Transform (SIFT) . It uses MSER to detect feature regions instead of difference of Gaussian. After fitted into elliptical regions,those regions will be normalized into unity circles and represented with SIFT descriptors. The method estimates fundamental matrix and removes outliers by auto-maximum a posteriori sample consensus after initial matching feature points. The experimental results indicate that the method is robust to viewpoint changes,can reduce computational complexity effectively and improve matching accuracy.

一种基于MSER的遥感影像盲水印算法

实用的遥感影像水印算法对多项指标要求较高,在平衡多项要求的前提下,提出了一种实用的抗几何攻击遥感影像盲水印算法。首先,提取影像中分布均匀且互不重叠的最大稳定极值区域(maximally stable extremal regions,MS⁃ER),并将不规则的MSER拟合为最小矩形区域;以矩形区域的不变质心为圆心,构造不超过该矩形的圆形区域作为特征区域;然后,对特征区域进行基于矩的归一化处理,并对归一化特征区域实施离散小波变换(discrete wavelet trans⁃form,DWT),运用量化嵌入规则将水印嵌入小波变换后的低频系数;最后,依次进行逆小波变换、水印嵌入前后的差值图像反归一化,将反归一化差值图像加性嵌入圆形特征区域,完成水印的嵌入。实验结果表明,水印具有良好的不可感知性;在对含水印的遥感影像进行不同程度的旋转攻击后,提取的水印与原水印相关系数均高于0.85;在平移、缩放、裁剪、加噪、滤波等常规水印攻击实验与组合攻击实验中,提取的水印与原水印相关系数均高于0.9;水印提取过程无需原始影像参与,属于盲水印算法。