CAJ | 학술논문

针对基于全天空极光图像的极光事件自动分类问题，提出一种基于方向能量二元编码重组表征的自动分类方法。首先，通过对多个方向上能量分解来描述极光事件中的局部纹理和各个方向上的运动信息，并且结合分块策略获得极光事件的全局形态信息；然后，借鉴一种二元编码重组的方式对多个方向能量进行融合，从而使得极光事件的表征具有同时表征局部纹理、全局形态和运动信息的能力。该表征方法完全不依赖于极光事件的长度，可用于表征不同持续时间的极光事件，并且不需要复杂的训练过程。利用最近邻和支撑向量机分类器分别对从中国北极黄河站拍摄到的极光图像中挑选的特定极光事件进行自动分类，结果表明，与其他两种典型的动态纹理描述方法相比，本文所提出的表征方法结合最近邻分类器，得到了最好的分类效果，能有效用于极光事件的分析，为海量数据中的极光事件自动分类提供了一种新方法。
침대기우전천공겁광도상적겁광사건자동분류문제，제출일충기우방향능량이원편마중조표정적자동분류방법。수선，통과대다개방향상능량분해래묘술겁광사건중적국부문리화각개방향상적운동신식，병차결합분괴책략획득겁광사건적전국형태신식；연후，차감일충이원편마중조적방식대다개방향능량진행융합，종이사득겁광사건적표정구유동시표정국부문리、전국형태화운동신식적능력。해표정방법완전불의뢰우겁광사건적장도，가용우표정불동지속시간적겁광사건，병차불수요복잡적훈련과정。이용최근린화지탱향량궤분류기분별대종중국북겁황하참박섭도적겁광도상중도선적특정겁광사건진행자동분류，결과표명，여기타량충전형적동태문리묘술방법상비，본문소제출적표정방법결합최근린분류기，득도료최호적분류효과，능유효용우겁광사건적분석，위해량수거중적겁광사건자동분류제공료일충신방법。
Auroral event is a physical phenomenon for which there is much information in terms of texture, morphology, and motion.Therefore, there is an urgent need for a representation that captures the information simultaneously.A three-dimensional dynamic texture representation method based on oriented energies with binary coding is proposed for auroral event representation and automatic classification.First, local texture and oriented motion are described by the decomposition of energy into different orientations.Second, global morphology information is obtained in combination with the block partition strategy.To obtain a statistical histogram, binary coding is applied for the fu-sion of energies with different orientations.Finally, the classifiers of nearest neighbor and support vector machines are used to classify auroral events from the Chinese Arctic Yellow River Station.The classification results demon-strate that the proposed method, using the nearest neighbor classifier, achieves superior classification performance compared with two other representative dynamic texture representation methods.The proposed method is specifically designed for auroral event representation, which is independent of the duration and captures the local texture, glob-al morphology, and motion simultaneously.It provides a feasible method for automatic classification of massive au-roral events.