摘要
针对Kmeans算法初始聚类中心选择及聚类结果需人工解读的问题,提出对MODIS数据(一般取波段26)使用Otsu法确定出云和非云集合,分别取两类集合中最接近均值的点作为Kmeans算法的初始聚类中心,并根据初始聚类中心的类别确定出聚类结果的类别。解决了传统Kmeans算法中初始聚类中心随机选取造成的误差和聚类结果需人工解读的问题,实现了自动云检测算法,实验结果验证了该方法的有效性。
In this paper, we proposed a method to choose the initial clustering center for the K-means algorithm and recognize the clustering results without artificial interpretation. We took the nearest pixels from each class’ s mean value as the initial clustering center of the K-means algorithm, and determined the category of the clustering results according to the category of the initial clustering center. Theoretically, the method can reduce the error caused by the random choice of the initial clustering center in traditional K-means algorithm, and realize automatic cloud detection without artificial interpretation. The experimental results verified the effectiveness of the proposed method.
出处
《地理空间信息》
2020年第4期31-33,I0006,共4页
Geospatial Information
