IIAE CONFERENCE SYSTEM, The 1st IEEE/IIAE International Conference on Intelligent Systems and Image Processing 2013 (ICISIP2013)

Font Size: 
Enhancement of Sky and Cloud Type Classification
Khaled F. Hussain, Hanaa Aly Sayed

Last modified: 2013-10-01

Abstract


The sky is an essential component in outdoor images. Sky and cloud type classification has applications in many areas such as image enhancement and sky image retrieval. In this paper, we improve the sky and cloud type classification rate over existing methods. Our work is based on two classification stages: sky image classification stage and sky cloud type classification stage. In sky classification stage, the image is classified into blue sky, cloudy sky, and sunset sky. Due to the impact of descriptor selection in the sky classification, we investigate ten descriptors; we show that the classifiers based on color descriptors are more accurate than the classifiers based on shape descriptors in sky type classification. We improve the sky image classification ratio using K-HSV descriptors. The sky classification with K-HSV descriptors has 77.3% correct classification rate.

In cloud type's classification stage, the cloud is classified based on the sky type. For both the blue sky and the sunset sky, the cloud type is classified into six types: cloudless, thin-cirrus, cirrus, cirrocumulus, cumulus, and cumulonimbus. In cloudy sky, the cloud type is classified into three types: stratus, stratocumulus, and altostratus. The clouds are classified based on their shape and color using Gist minimum distance classification. The average correct classification rate of the clouds classifier is over 85% for cloudless, cumulus clouds, and stratus clouds and over 60% for thin-cirrus, cumulonimbus, stratocumulus, and altostratus clouds.


Keywords


image classification; sky detection; cloud types; color descriptors

References


(1)   London, Meteorological Office : "Cloud types for observers", London HMSO, 1982.

(2)   Dave Parker : "Clouds and cloud identification", http://www.invectis.co.uk/cloud/cloud.html

(3)   Wikimedia Commons, http://commons.wikimedia.org/wiki/Cloud

(4)   Sid-Ahmed Maher : "Image processing", McGraw-Hill, 1994.‏

(5)   Andrea Vedaldi and Brian Fulkerson :  "VLFeat: An Open and Portable Library of Computer Vision Algorithms", http://www.vlfeat.org/.

(6)   Martin Szummer and Rosalind Picard : "Indoor-outdoor image classification", IEEE International Workshop on Content-Based Access of Image and Video Databases, Bombay, India, pp 42–51, 1998.

(7)   Christina Pavlopoulou and Stella Yu : "Indoor-outdoor classification with human accuracies: Image or edge gist", In Computer Vision and Pattern Recognition Workshops (CVPRW), IEEE Computer Society Conference on. IEEE, San Francisco, USA, 2010.‏

(8)   Anna Bosch, Andrew Zisserman, Xavier Muñoz : "Scene classification via pLSA", Computer Vision–ECCV, Springer Berlin Heidelberg, pp 517-530, 2006.

(9)   Wang Gang, Derek Hoiem, and David Forsyth : "Learning image similarity from flickr groups using stochastic intersection kernel machines", In Computer Vision, IEEE International Conference on. IEEE, Kyoto, Japan, 2009.‏

(10)          Dan LU Qihao Weng : "A survey of image classification methods and techniques for improving classification performance", International Journal of Remote Sensing : Vol. 28, No. 5, pp 823–870, 2007.

(11)          Koen Van de Sande, Theo Gevers, and Cees GM Snoek, "Evaluating color descriptors for object and scene recognition", Pattern Analysis and Machine Intelligence, IEEE Transactions, Vol. 32, No. 9, pp 1582-1596, 2010.

(12)          Andrew Gallagher, Jiebo Luo, Wei Hao :  "Improved blue sky detection using polynomial model fit", IEEE International Conference on Image Processing, Singapore,   pp 2367-2370, 2004.

(13)           Jiebo Luo and Stephen Etz : "Method for detecting sky in images", U.S. Patent No. 6,504,951 2003.‏

(14)          Stephen Herman and Erwin Bellers : "Locally-adaptive processing of television images based on real-time image segmentation", IEEE International Conference on Consumer Electronics, Los Angeles, USA, pp 66-67, 2002.

(15)          Stephen Herman and Johan Janssen : "System and method for performing segmentation-based enhancements of a video image", U.S. Patent No. 6, 903,782, 2005.‏

(16)          Bahman Zafarifar and Peter de With : "Blue sky detection for content-based television picture quality enhancement", In the International Conference on Consumer Electronics, Las Vegas, USA, 2007.‏

(17)          Litian Tao, Lu Yuan, and Jian Sun : "SkyFinder: attribute-based sky image search", ACM Graphics (TOG) Transactions. Vol. 28. No. 3, pp 68-72, 2009.‏

(18)          Aude Oliva and Antonio Torralba : "Building the gist of a scene: The role of global image features in recognition" Progress in brain research, Vol. 155, pp 23-36, 2006.‏

(19)          Gjorgji Madzarov, Dejan Gjorgjevikj, and Ivan Chorbev : "A multi-class svm classifier utilizing binary decision tree", Informatica, Vol. 33, No. 2, pp 233-241, 2009.‏

(20)          Cintia Henken, Maurice Schmeits, Hartwig Deneke, and Rob Roebeling :  " Using MSG-SEVIRI Cloud Physical Properties and Weather Radar Observations for the Detection of Cb/TCu Clouds", Journal of Applied Meteorology and Climatology, Vol. 50, No. 7, pp. 1587-1600, 2011.

(21)          Jianxin Wu and Jim. Rehg :  "CENTRIST: A visual descriptor for scene categorization", Pattern Analysis and Machine Intelligence, IEEE Transactions, Vol. 33 No. 8, pp 1489-1501, 2011.‏


Full Text: PDF