Research on emote Sensing Image Classification based on Multi-core Fuzzy C-means Clustering
[1]Zhang Chengcai,Li Fei,Wang Yanmei,et al.Research on emote Sensing Image Classification based on Multi-core Fuzzy C-means Clustering[J].Journal of Zhengzhou University (Engineering Science),2020,41(03):20-25.[doi:10.13705/j.issn.1671-6833.2019.05.024]
Copy
Journal of Zhengzhou University (Engineering Science)[ISSN
1671-6833/CN
41-1339/T] Volume:
41卷
Number of periods:
2020 03
Page number:
20-25
Column:
Public date:
2020-07-29
- Title:
- Research on emote Sensing Image Classification based on Multi-core Fuzzy C-means Clustering
- Keywords:
- remote sensing images; multi-core; fuzzy C-means; kernel function
- CLC:
- -
- DOI:
- 10.13705/j.issn.1671-6833.2019.05.024
- Abstract:
- Fuzzy C-means clustering (FCM) algorithm does not consider the correlation between pixels when classifying remote sensing images. In order to increase the correlation information between pixels, a multi-core fuzzy C-means clustering (MKFCM) algorithm is proposed, in which multiple kernel functions are introduced into FCM algorithm. And automatically filters out the optimal weight combination among kernel functions according to the distribution characteristics of pixels in feature space. The medium-high resolution Landsat8 images and high resolution Pleiades images as research data, and by analyzing the accuracy of classification results of MKFCM and FCM algorithm ,the results show that MKCM algorithm can better distinguish pixels with similar spectral information for different resolution remote sensing images, and whether the accuracy of the single category or the overall classification accuracy is higher than the FCM algorithm, which provides an effective way to accurately extract the regional land cover information
- References:
- -
- Similar References:
Memo
-
Last Update:
2020-07-28