Semisupervised Hyperspectral Image Classification via Discriminant Analysis and Robust Regression
文献类型：期刊论文
| 作者 | Cheng, Guangliang ; Zhu, Feiyun; Xiang, Shiming; Wang, Ying; Pan, Chunhong
|
| 刊名 | IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
 |
| 出版日期 | 2016-02-01 |
| 卷号 | 9期号:2页码:595-608 |
| 关键词 | Discriminant Analysis Hyperspectral Image Classification (Hsic) Pairwise Constraints Robust Regression Semisupervised Learning (Ssl) |
| DOI | 10.1109/JSTARS.2015.2471176 |
| 文献子类 | Article |
| 英文摘要 | In recent years, hyperspectral image classification (HSIC) has received increasing attention in a wide range of hyperspectral applications. It is still very challenging due to the following factors: 1) there are not enough labeled samples; 2) the images are easy to be polluted by outlier channels; and 3) different objects may have similar spectra. Considering these three factors, we propose a novel semisupervised HSIC method, which is constructed on discriminant analysis and robust regression (DARR). Specifically, a regression-based semisupervised technique is employed by not only exploiting the rich information in labeled samples, but also taking advantage of abundant unlabeled ones. In this way, the true data distribution can be obtained accurately. Then, we introduce a robust adaptive loss function to measure the representation loss. As a result, it can greatly relieve the side effects of outlier channels. Finally, to increase discriminating power of our approach for different objects, we utilize the pairwise constraints to incorporate the discriminant information among labeled samples. Through these constraints, the same-category samples are projected to be close to each other, while the different-category samples are as far apart as possible. The above three components can be integrated into a graph-based objective function, whose optimization is systematically provided. Extensive experiments on four data sets demonstrate that our method achieves higher quantitative results, as well as more satisfactory visual performances by comparing with state-of-the-art methods and using different parameter settings. |
| WOS关键词 | SUPPORT VECTOR MACHINES ; REMOTE-SENSING IMAGES ; MORPHOLOGICAL ATTRIBUTE PROFILES ; HIGH-RESOLUTION IMAGES ; SPATIAL CLASSIFICATION ; SEGMENTATION ; FUSION |
| WOS研究方向 | Engineering ; Physical Geography ; Remote Sensing ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| WOS记录号 | WOS:000370877600005 |
| 资助机构 | National Natural Science Foundation of China(61305049 ; 91338202 ; 61375024 ; 91438105) |
| 源URL | [http://ir.ia.ac.cn/handle/173211/11354]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_遥感图像处理团队 |
| 作者单位 | Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Cheng, Guangliang,Zhu, Feiyun,Xiang, Shiming,et al. Semisupervised Hyperspectral Image Classification via Discriminant Analysis and Robust Regression[J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,2016,9(2):595-608. |
| APA | Cheng, Guangliang,Zhu, Feiyun,Xiang, Shiming,Wang, Ying,&Pan, Chunhong.(2016).Semisupervised Hyperspectral Image Classification via Discriminant Analysis and Robust Regression.IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,9(2),595-608. |
| MLA | Cheng, Guangliang,et al."Semisupervised Hyperspectral Image Classification via Discriminant Analysis and Robust Regression".IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 9.2(2016):595-608. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。