中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Integrating Backdating and Transfer Learning in an Object-Based Framework for High Resolution Image Classification and Change Analysis

文献类型:期刊论文

作者Qian, Yuguo; Zhou, Weiqi; Yu, Wenjuan; Han, Lijian; Li, Weifeng; Zhao, Wenhui
刊名REMOTE SENSING
出版日期2020-12
卷号12期号:24页码:1-11
关键词urban landscape multi-temporal change detection land cover land use remote sensing urban ecology
英文摘要Classification and change analysis based on high spatial resolution imagery are highly desirable for urban landscapes. However, methods with both high accuracy and efficiency are lacking. Here, we present a novel approach that integrates backdating and transfer learning under an object-based framework. Backdating is used to optimize the target area to be classified, and transfer learning is used to select training samples for classification. We further compare the new approach with that of using backdating or transfer learning alone. We found: (1) The integrated new approach had higher overall accuracy for both classifications (85.33%) and change analysis (88.67%), which were 2.0% and 4.0% higher than that of backdating, and 9.3% and 9.0% higher than that of transfer learning, respectively. (2) Compared to approaches using backdating alone, the use of transfer learning in the new approach allows automatic sample selection for supervised classification, and thereby greatly improves the efficiency of classification, and also reduces the subjectiveness of sample selection. (3) Compared to approaches using transfer learning alone, the use of backdating in the new approach allows the classification focusing on the changed areas, only 16.4% of the entire study area, and therefore greatly improves the efficiency and largely avoid the false change. In addition, the use of a reference map for classification can improve accuracy. This new approach would be particularly useful for large area classification and change analysis.
源URL[http://ir.rcees.ac.cn/handle/311016/44352]  
专题生态环境研究中心_城市与区域生态国家重点实验室
推荐引用方式
GB/T 7714
Qian, Yuguo,Zhou, Weiqi,Yu, Wenjuan,et al. Integrating Backdating and Transfer Learning in an Object-Based Framework for High Resolution Image Classification and Change Analysis[J]. REMOTE SENSING,2020,12(24):1-11.
APA Qian, Yuguo,Zhou, Weiqi,Yu, Wenjuan,Han, Lijian,Li, Weifeng,&Zhao, Wenhui.(2020).Integrating Backdating and Transfer Learning in an Object-Based Framework for High Resolution Image Classification and Change Analysis.REMOTE SENSING,12(24),1-11.
MLA Qian, Yuguo,et al."Integrating Backdating and Transfer Learning in an Object-Based Framework for High Resolution Image Classification and Change Analysis".REMOTE SENSING 12.24(2020):1-11.

入库方式: OAI收割

来源:生态环境研究中心

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。