摘要
针对传统基于单一分形维数进行底质分类存在近似底质分类可靠性不高的问题,提出了顾及分形维数、空隙特征和多重分形的多特征海底底质分类方法。结合均值、标准差、分位数等灰度统计信息,组成特征向量组,并获取其主成分特征向量组实施底质分类,相比传统方法,本方法显著提高了近似底质的分类精度,并在胶州湾实验中得到了验证。
Aimed at the poor seabed classification reliability of traditional single fractal dimension, this paper puts for- ward a seabed classification of considering fractal dimension, lacunarity and multi-fractal. Combining gray statistical infor- mation such as mean value, standard deviation and median, a full feature vector is constructed and principal component a- nalysis is carried out on later sediment classification work. The method of our proposed is applied to the Jiaozhou bay, and reliable experiment results have been obtained.
出处
《测绘地理信息》
2017年第4期77-80,共4页
Journal of Geomatics
基金
国家自然科学基金资助项目(41376109
41176068
41576107)
关键词
底质分类
分形
空隙
多重分形
主成分分析
seabed classification
fractal
lacunarity
multi- fractal
principal component analysis
