( 中文版 )
Total-sky Cloud Imager (TCI) is an automatic ground-based cloud observation instrument, developed by the State Key Laboratory of Severe Weather at the Chinese Academy of Meteorological Sciences. The core unit of the TCI system consists of an industrial camera and a fisheye lens. It can provide the 24 bit RGB color images at resolution of 1392*1024 pixels at fixed intervals. Unlike other total-sky imagers, TCI adopts an auto exposure technology to capture the total sky images without occluding the sun. This achievement has won several Chinese national patents.
Field experiments in several different climatic regions
Interface of TCI software
We carried out field experiments in several different climatic regions and obtained a number of ground-based total-sky cloud imagers since 2009. Using these data, the researchers of Chinese Academy of Meteorological Sciences and Beijing Jiaotong University carried out algorithms development on cloud detection and cloud classification. To better share these data and promote research on related algorithms, we established this total-sky cloud image set (TCIS), which are opened to domestic and foreign research.
TCIS consists of 5000 total-sky cloud images. It is divided into five sky types: clear sky, cirriform, stratiform, cumuliform, and mixed cloudiness. Each type contains 1000 images, which are captured by TCI devices in China Tibetan Plateau from 2012 to 2014. All images are stored in color JPEG format, and the effective area of the TCI image is a circular region with a diameter of 800 pixels, after the removal of margin region and some ground objects. Some typical total-sky cloud images are as follows.
Some typical total-sky cloud images
Please download, fill and sign the User License Agreement (ULA) and return the whole document to firstname.lastname@example.org. The downloaded URL and password will be contained in the replied email.
Q. Li, Z. Zhang, W. Lu, J. Yang, Y. Ma, and W. Yao. From Pixels to Patches: a Cloud Classification Method Based on Bag of Micro-structures, Atmos. Meas. Tech. Discuss., 8, 10213–10247, doi:10.5194/amtd-8-10213-2015.
J. Yang, Q. Min, W. Lu, Y. Ma, W. Yao, T. Lu, J. Du, and G. Liu. A total sky cloud detection method using real clear sky background, Atmos. Meas. Tech. Discuss., 8, 13073–13098, doi:10.5194/amtd-8-13073-2015.
J. Yang, Q. Min, W. Lu, Y. Ma, W. Yao, T. Lu, J. Du, and G. Liu. An automated cloud detection method based on the green channel of total-sky visible images, Atmos. Meas. Tech., 8, 4671–4679, doi:10.5194/amt-8-4671-2015, 2015.
M. Xia, W. Lu, J. Yang, Y. Ma, W. Yao, and Z. Zhang. A hybrid method based on extreme learning machine and k-nearest neighbor for cloud classification of ground-based visible cloud image, neurocomputing, 160, 238-249, 2015.
J. Yang, W. Lu, Y. Ma, and W. Yao. An automated cirrus cloud detection method for a ground based cloud image, J. Atmos. Ocean. Tech., 29, 527–537, 2012.
Q. Li, W. Lu, J. Yang, and J. Wang. Thin Cloud Detection of All-Sky Images Using Markov Random Fields, IEEE Geoscience and Remote Sensing Letters, 9(3), 417-421, 2012.
Q. Li, W. Lu, and J. Yang. A hybrid thresholding algorithm for cloud detection on ground-based color images, J. Atmos. Ocean. Tech., 28, 1286–1296, 2011.