Cloud Detection of Gray Photographs by Cloud Region Detectionand Optimal Region Grow Threshold

DOI

10.2991/icicci-15.2015.20How to use a DOI?

Keywords

Keywords-Cloud detection; Gray photograph; Human visual perception; Conditional contrast; Region grow; Optimal threshold; Texture

Abstract

Abstract—The most cloud detection method depends on various bands such as thermal band. In this paper, we propose an automatic cloud detection algorithm for gray photographs. Based on the properties of cloud derived from gray photographs and the human visual perception, we present a novel scheme for detecting clouds in the gray photographs. We first cut an input graph into many pieces. Through the conditional contrast and area feature, we label these pieces into thick cloud, thin cloud and no cloud. We select the point of maximal gray as seed point and calculate the optimal threshold. Then, we consider the texture feature of the growing area and fix some errors of detection results. Finally, we get the detected result. The algorithm is evaluated in terms of aerial photograph scenes with manually generated cloud masks was created, and the evaluation results show that the method works well for the cloud detection of gray photographs.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Xingying Zhao
AU  - Hong Zheng
PY  - 2015/09
DA  - 2015/09
TI  - Cloud Detection of Gray Photographs by Cloud Region Detectionand Optimal Region Grow Threshold
BT  - Proceedings of the 2nd International Conference on Intelligent Computing and Cognitive Informatics
PB  - Atlantis Press
SP  - 91
EP  - 95
SN  - 1951-6851
UR  - https://doi.org/10.2991/icicci-15.2015.20
DO  - 10.2991/icicci-15.2015.20
ID  - Zhao2015/09
ER  -