一种结合SIFT和边缘信息的多源遥感影像匹配方法
A Node Localization Method in Wireless Sensor Network Based on K-means Cluster
-
摘要: 针对多源遥感影像间几何变形和灰度差异造成的匹配困难问题,提出一种结合SIFT和边缘信息的影像匹配方法。首先在高斯差分尺度空间进行特征点检测,并采用相位一致性提取可靠的边缘信息;然后结合改进的SIFT和形状上下文对特征点进行描述;最后将欧氏距离和χ2统计作为相似性测度获取同名点。相比于SIFT算法,本文方法可有效地提高匹配正确率,并获得更多的同名点。Abstract: Considering the influence of the environmental difference in the same localization circumstance, we proposes a node localization algorithm based on clustering in this paper. This algorithm can realize nodes clustering by using the RSSI-similarity degree in space environment, and succeed in localization estimation with different model parameters. Experimental results show that the proposed algorithm has a better localization accuracy than some RSSI algorithm.