Journal of Computer Applications ›› 2018, Vol. 38 ›› Issue (11): 3175-3179.DOI: 10.11772/j.issn.1001-9081.2018041350

Previous Articles     Next Articles

Automatic cloud detection algorithm based on deep belief network-Otsu hybrid model

QIU Meng, YIN Haoyu, CHEN Qiang, LIU Yingjian   

  1. Department of Computer Science and Technology, Ocean University of China, Qingdao Shandong 266100, China
  • Received:2018-04-30 Revised:2018-06-12 Online:2018-11-10 Published:2018-11-10
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61572448, 61673357), the Natural Science Foundation of Shandong Province (ZR2014JL043), the Key R&D Program of Shandong Province (2018GSF120015).

基于深度置信网络Otsu混合模型的自动云检测算法

邱梦, 尹浩宇, 陈强, 刘颖健   

  1. 中国海洋大学 计算机科学与技术系, 山东 青岛 266100
  • 通讯作者: 刘颖健
  • 作者简介:邱梦(1992-),女,山东高密人,硕士研究生,主要研究方向:大数据、机器学习;尹浩宇(1994-),男,重庆人,硕士研究生,CCF会员,主要研究方向:机器学习、无线传感器网络、计算机视觉;陈强(1987-),男,山东泰安人,硕士研究生,主要研究方向:数据挖掘、机器学习;刘颖健(1974-),女,山东滨州人,副教授,博士,CCF会员,主要研究方向:海洋大数据、机器学习、卫星遥感、海洋传感器网络。
  • 基金资助:
    国家自然科学基金资助项目(61572448,61673357);山东省自然科学基金资助项目(ZR2014JL043);山东省重点研发计划项目(2018GSF120015)。

Abstract: More than half of the earth's surface is covered by cloud. Current cloud detection methods from satellite remote sensing imageries are mainly manual or semi-automatic, depending upon manual intervention with low efficiency. Such methods can hardly be utilized in real-time or quasi real-time applications. To improve the availability of satellite remote sensing data, an automatic cloud detection method based on Deep Belief Network (DBN) and Otsu's method was proposed, named DOHM (DBN-Otsu Hybrid Model). The main contribution of DOHM is to replace the empirical fixed thresholds with adaptive ones, therefore achieve full-automatic cloud detection and increase the accuracy to greater than 95%. In addition, a 9-dimensional feature vector is adopted in network training. Diversity of the input feature vector helps to capture the characteristics of cloud more effectively.

Key words: deep learning, cloud detection, Deep Belief Network (DBN), Otsu's method, Advanced Very High Resolution Radiometer (AVHRR)

摘要: 地球表面一半以上被云覆盖,卫星遥感图像中的云检测主要是人工检测识别或者半自动化方法,依赖人工干预,效率不高,难以满足实时或准实时应用的需要。为了提高卫星遥感数据的可用性,基于深度置信网络(DBN)和最大类间方差法,提出一种自动云检测算法——DOHM。该算法采用自适应阈值代替人工标定阈值,实现云检测的全自动化,将云检测的正确率提高到95%以上;DOHM算法选取了维度为9的特征向量作为检测网络的输入,输入特征向量的多样性,有利于网络更全面有效地捕捉到云的特点。

关键词: 深度学习, 云检测, 深度置信网络, 最大类间方差法, 高级甚高分辨率辐射计

CLC Number: