Abstract Affected by the atmospheric pollution,the moonlight and the zodiac light,the night-sky cloud images vary greatly. The conventional threshold methods which only utilize pixel gray value as well as the neighborhood information are difficult to segment the image accurately because of their uneven backgrounds. In this paper,two prior features of cloud images are observed from the statistical analysis,and a prior threshold surface based cloud segmentation algorithm is presented. After reliable background regions are extracted according to the prior features,an adaptive threshold surface can be obtained by polynomial fitting on the background regions,and the values of the threshold surface are between the clouds and backgrounds. Thus the cloud can be segmented from the background. The experimental results show that the proposed algorithm is more feasible and effective compared with other existing algorithms. Moreover,it produces fine results on the cloud images of light influence.
[1] Ma Fang,Zhang Qiang,Guo Ni. The Study of Cloud Detection with Multi-Channel Data of Satellite. Chinese Journal of Atmospheric Sciences,2007,31(1): 119-128(in Chinese) (马 芳,张 强,郭 铌.多通道卫星云图云检测方法的研究.大气科学,2007,31(1): 119- 128) [2] Hoyt D V. Percent of Possible Sunshine and the Total Cloud Cover. Monthly Weather Review,1977,105(5): 648-652 [3] Otsu N. A Threshold Selection Method from Gray Level Histogram. IEEE Trans on Systems,Man and Cybernetics,1979,9(1): 62-66 [4] Yang Jian,Xue Feng,Song Zhigang,et al. Recognition of Ground Nephogram Cloudage Based on Image Processing Technology. Meteorological,Hydrological and Marine Instrument,2008,(3): 67-71(in Chinese) (杨 健,薛 峰,宋志刚,等.基于图像处理技术的地基云图云状的识别.气象水文海洋仪器,2008,(3): 67-71) [5] Yang Jun,Lü Weitao,Ma Ying,et al. An Automatic Ground-Based Cloud Detection Method Based on the Local Threshold Interpolation. Acta Meteorologica Sinica,2010,68(6): 1007-1017(in Chinese) (杨 俊,吕伟涛,马 颖,等.基于局部阈值插值的地基云自动检测方法.气象学报,2010,68(6): 1007-1017) [6] Huang Qian,Wang Shaolong,Xu Daolei,et al. Adaptive Threshold Approach for Night-Sky Cloud Inspection. Journal of Image and Graphics,2012,17(8): 960-965(in Chinese) (黄 茜,王少龙,徐道磊,等.云的自适应阈值检测方法.中国图像图形学报,2012,17(8): 960-965) [7] Wu Chengmao,Tian Xiaoping,Tan Tieniu. Fast Iterative Algorithm for Two-Dimensional Otsu Thresholding Method. Pattern Recognition and Artificial Intelligence,2008,21(6): 746-757(in Chinese) (吴成茂,田小平,谭铁牛.二维Otsu阈值法的快速迭代算法.模式识别与人工智能,2008,21(6): 746-757) [8] Wu Chengmao. A New Information Entropy Definition and Its Application in Image Segmentation. Journal of Xi′an University of Posts and Telecommunications,2009,14(1): 72-79(in Chinese) (吴成茂.一种新信息熵定义及其在图像分割中的应用.西安邮电大学学报,2009,14(1): 72-79)
2013, Vol. 26 
