Study of Cloud-Type Recognition Based on Multi-Class Features

详细信息    查看全文 | 下载全文 | 推荐本文 |

• 作者：Ling YANGZhong-ke WANGJun WANGWen-ting Cui
• 会议时间：2014-09-10
• 关键词：Feature Extraction ; Feature Combinations ; Cloud-Type Recognition ; Support Vector Machine (SVM)
• 作者单位：Ling YANG,Jun WANG,Wen-ting Cui(College of Electronic Engineering,Chengdu University of Information Technology,Chengdu 610225,China)Zhong-ke WANG(College of Network Engineering,Chengdu University of Information Technology,Chengdu 610225,China)
• 母体文献：第八届全国优秀青年气象科技工作者学术研讨会论文集
• 会议名称：第八届全国优秀青年气象科技工作者学术研讨会
• 会议地点：江苏宜兴
• 主办单位：中国气象学会
• 语种：chi

摘要

According to changeability of cloud, cloud-type recognition was primarily based on single-class feature in previous papers which was restricted to a certain degree.A set of features describing the color, texture as well as the shape features were extracted, then the shape and texture features combination methods were discussed.Here Gray-level co-occurrence matrix(GLCM) and Gabor wavelet transform based texture features and Zemikc moment based shape features were combined, then support vector machine (SVM) was employed to recognize cloud-type.Experimental results showed that the correct recognition rates of altocumulus, cirrus, clear, cumulus and stratus were improved significantly, with the average recognition rate of 88.6%, and clear sky and stratus's recognition rate of 100%.