Geocomplexity Statistical Indicator to Enhance Multiclass Semantic Segmentation of Remotely Sensed Data with Less Sampling Bias
文献类型：期刊论文
| 作者 | He, Wei1,2; Li, Lianfa1,2; Gao, Xilin1,2 |
| 刊名 | REMOTE SENSING
 |
| 出版日期 | 2024-06-01 |
| 卷号 | 16期号:11页码:1987 |
| 关键词 | sampling bias optimal sampling semantic segmentation deep learning |
| DOI | 10.3390/rs16111987 |
| 产权排序 | 1 |
| 文献子类 | Article |
| 英文摘要 | Challenges in enhancing the multiclass segmentation of remotely sensed data include expensive and scarce labeled samples, complex geo-surface scenes, and resulting biases. The intricate nature of geographical surfaces, comprising varying elements and features, introduces significant complexity to the task of segmentation. The limited label data used to train segmentation models may exhibit biases due to imbalances or the inadequate representation of certain surface types or features. For applications like land use/cover monitoring, the assumption of evenly distributed simple random sampling may be not satisfied due to spatial stratified heterogeneity, introducing biases that can adversely impact the model's ability to generalize effectively across diverse geographical areas. We introduced two statistical indicators to encode the complexity of geo-features under multiclass scenes and designed a corresponding optimal sampling scheme to select representative samples to reduce sampling bias during machine learning model training, especially that of deep learning models. The results of the complexity scores showed that the entropy-based and gray-based indicators effectively detected the complexity from geo-surface scenes: the entropy-based indicator was sensitive to the boundaries of different classes and the contours of geographical objects, while the Moran's I indicator had a better performance in identifying the spatial structure information of geographical objects in remote sensing images. According to the complexity scores, the optimal sampling methods appropriately adapted the distribution of the training samples to the geo-context and enhanced their representativeness relative to the population. The single-score optimal sampling method achieved the highest improvement in DeepLab-V3 (increasing pixel accuracy by 0.3% and MIoU by 5.5%), and the multi-score optimal sampling method achieved the highest improvement in SegFormer (increasing ACC by 0.2% and MIoU by 2.4%). These findings carry significant implications for quantifying the complexity of geo-surface scenes and hence can enhance the semantic segmentation of high-resolution remote sensing images with less sampling bias. |
| WOS关键词 | LAND-COVER ; ESTIMATING AREA ; CLASSIFICATION ; IMAGE ; COMPLEXITY ; ALLOCATION ; DESIGN ; FOREST ; MAP |
| WOS研究方向 | Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology |
| WOS记录号 | WOS:001245706500001 |
| 出版者 | MDPI |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/205326]  |
| 专题 | 资源与环境信息系统国家重点实验室_外文论文 |
| 通讯作者 | Li, Lianfa |
| 作者单位 | 1.Univ Chinese Acad Sci, Coll Resources & Environm, Beijing 100049, Peoples R China 2.Chinese Acad Sci, State Key Lab Resources & Environm Informat Syst, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China |
| 推荐引用方式 GB/T 7714 | He, Wei,Li, Lianfa,Gao, Xilin. Geocomplexity Statistical Indicator to Enhance Multiclass Semantic Segmentation of Remotely Sensed Data with Less Sampling Bias[J]. REMOTE SENSING,2024,16(11):1987. |
| APA | He, Wei,Li, Lianfa,&Gao, Xilin.(2024).Geocomplexity Statistical Indicator to Enhance Multiclass Semantic Segmentation of Remotely Sensed Data with Less Sampling Bias.REMOTE SENSING,16(11),1987. |
| MLA | He, Wei,et al."Geocomplexity Statistical Indicator to Enhance Multiclass Semantic Segmentation of Remotely Sensed Data with Less Sampling Bias".REMOTE SENSING 16.11(2024):1987. |
入库方式： OAI收割
来源：地理科学与资源研究所
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。