摘要
将基于多尺度显著性检测的视觉注意机制引入到高光谱影像的噪声去除和图像增强处理中,并基于分层聚类算法,提出一种结合聚类降维和视觉注意机制的高光谱影像分类方法。以Indian数据集和Pavia数据集为例,开展降维、显著性映射图获取和支持向量机监督分类实验。结果表明,本文方法能够较大地提升高光谱影像的分类精度和效率。
A multi-scale saliency detection-based visual attention mechanism is introduced to eliminate noise and enhance the quality of the hyperspectral images.Further,a hyperspectral image classification method is proposed by combining the clustering dimensionality reduction and visual attention mechanism in accordance with the hierarchical clustering algorithm.Subsequently,dimensionality reduction,acquisition of saliency mapping,and support-vectormachine-supervised classification experiments are conducted by considering the Indian and Pavia datasets as examples.The results denote that the proposed method can considerably improve the classification accuracy and efficiency of hyperspectral images.
作者
曾朝平
琚丽君
张建辰
Zeng Chaoping;Ju Lijun;Zhang Jianchen(Department of Space Information Engineering,Henan College of Surveying and Mapping,Zhengzhou,Henan 450015,China;College of Environment and Planning,Henan University,Kaifeng,Henan 475004,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2019年第21期238-244,共7页
Laser & Optoelectronics Progress
基金
河南省教育厅教改项目(ZJA15132)
关键词
遥感
图像分类
聚类降维
视觉注意机制
多尺度显著性检测
remote sensing
image classification
clustering dimensionality reduction
visual attention mechanism
multi-scale saliency detection
