Polsar Image Classification Based On An Improved Bow Model With Mid-Level Semantic Features

2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019)(2019)

引用 1|浏览6
暂无评分
摘要
In recent years, using mid-level features to interpret images has attracted more and more attention. Mid-level features can solve the semantic gap between the low-level features and the high-level features. This paper proposes a PolSAR image classification method using Support Vector Machines (SVM) classifier based on an improved bag-of-visual-words (BOW) model combined with contextual information to generate mid-level semantic features. In order to solve the synonym word or polysemic word problem caused by the uncertainty of the number of visual words in the traditional BOW model, the improved visual-vocabulary construction method is proposed by defining visual words using the prior knowledge to reduce the uncertainty and feature dimension effectively. Since the traditional BOW representation ignores the correlation between words, the scale context information between words will be integrated by down-sampling to construct a multi-scale visual-vocabulary. Moreover, comparative experiments are implemented to prove the feasibility of the proposed method.
更多
查看译文
关键词
mid-level features, semantic, improved BOW, PolSAR image, classification
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络