Knowledge Commons of Institute of Automation,CAS
Hyperspectral and lidar data land-use classification using parallel transformers | |
Hu Yuxuan1,2![]() ![]() ![]() | |
2022-07 | |
会议名称 | IEEE International Geoscience and Remote Sensing Symposium |
会议日期 | 2022-7-17 -> 2022-7-22 |
会议地点 | 线上会议 |
摘要 | It has been proved that the fusion of hyperspectral and LiDAR data can effectively improve the performance of land-use classification. Hyperspectral data contain more information than LiDAR data but most recent models pay more attention to the design of feature fusion mechanisms. They use CNN which is not powerful enough in extracting spatialspectral features of hyperspectral data. In this paper, a simple yet effective model with parallel transformers is proposed. Transformer is a powerful tool for both feature extraction and feature fusion. One transformer acts as an hyperspectral image feature extractor while the other transformer is responsible for capturing crossmodal interactions. Experiments on Houston dataset and MUUFL Gulfport dataset demonstrate that the proposed model has significantly better performance than other state-of-the-art models. |
关键词 | Hyperspectral LiDAR Data Fusion Transformer Crossmodal |
收录类别 | EI |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
国重实验室规划方向分类 | AI For Science |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48691 |
专题 | 多模态人工智能系统全国重点实验室_先进时空数据分析与学习 |
通讯作者 | Weng Lubin |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Hu Yuxuan,He Hao,Weng Lubin. Hyperspectral and lidar data land-use classification using parallel transformers[C],2022. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Hyperspectral and li(1565KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论