GIG OpenIR  > 中科院广州地化所(-2008)
MODIS Cloud Detection and Analysis Based on Support Vector Machine
Pan C; Xia B; McGill M; Li JF; Chen HS; Gao HJ
Source Publication2nd International Conference on Modelling and Simulation
Conference Date2009-5-21
Conference PlaceManchester, ENGLAND
Indexed BySCI
AbstractCloud detection is a large obstacle to remote sensing image processing and a necessary step to preprocess image all the while. In order to discriminate the clouds, the article applies Support Vector Machine (SVM) algorithm to some channels of Moderate Resolution Imaging Spectroradiometer (MODIS) which are sensitive to characteristic of clouds. To prove the performance of the cloud detection algorithm, the article uses the MODIS images of typical areas under distinct underlying surfaces in different daytime and nighttime as training and testing samples. By comparison with Cloud Physics Lidar (CPL) data and MODIS Cloud Mask product, it is proved that the algorithm is good at detecting the territorial cloud and some pixels with small area. The SVM algorithm is a kind of practical machine learning method for cloud detection and good preparation for cloud elimination. What is more, the article indicates improved methods to cloud detection with SVM.
Document Type会议论文
Recommended Citation
GB/T 7714
Pan C,Xia B,McGill M,et al. MODIS Cloud Detection and Analysis Based on Support Vector Machine[C],2009.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Pan C]'s Articles
[Xia B]'s Articles
[McGill M]'s Articles
Baidu academic
Similar articles in Baidu academic
[Pan C]'s Articles
[Xia B]'s Articles
[McGill M]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Pan C]'s Articles
[Xia B]'s Articles
[McGill M]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.