沙漠地区无人机影像连接点提取

摘要

提出了一种纹理自适应的影像连接点提取方法,有针对性地解决沙漠地区无人机影像对比度低、相似性强、纹理信息不均衡,经常会造成连接点过少甚至提取、匹配失败的突出问题.该方法利用影像金字塔进行粗匹配,建立影像之间近似单应变换关系;通过对原始影像分块计算灰度共生矩阵的熵来评估影像纹理指标,并据此实现特征点的自适应提取与匹配.实验表明,该方法能够得到数量较多、分布均匀、可靠性强的同名点.%Images captured in desert area are often with low contrast, repetitive patterns and uneven texture, which will result in scarce tie points or a number of mismatches. A texture adaptive method for tie point extraction is pro-posed for desert area. Firstly, the image pyramid is built to perform initial matching and establish the approximate homography transformation between the images. Then, the texture level is evaluated based on the grey level co-cocurrence matrix of the image blocks, and the adaptive extraction and matching of the feature points are undertak-en. Experiments show the method can obtain considerable, relatively robust and homogenous corresponding points.