Change Cross-Detection Based on Label Improvements and Multi-Model Fusion for Multi-Temporal Remote Sensing Images
Change Cross-Detection Based on Label Improvements and Multi-Model Fusion for Multi-Temporal Remote Sensing Images
复制标题
基于标签改进和多模型融合的多时相遥感图像变化交叉检测
DOI：
10.1109/igarss47720.2021.9553120
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Liangpei Zhang
中科院分区：
文献类型：
--
作者：
Zhuo Li;Fangxiao Lu;Hongyan Zhang;Guangyi Yang;Liangpei Zhang
变化检测是一种社会公益的地理空间应用，其发展受到缓慢发展的标签技术和过时的遥感图像分类标签的限制。针对弱、噪声、低分辨率标签的多时相语义变化检测，提出了一种基于标签改进和多模型融合的变化交叉检测方法。对于不匹配的标签，提出了一种暹罗Skip_FCN网络来生成高分辨率的初始标签。在此基础上，提出了一种多模型融合方法，实现了准确、稳定的土地覆盖分类。此外，使用交叉检测结构来生成高精度的变化图，并通过后处理步骤进一步提高最终结果。在2021年数据融合大赛(DFC21-MSD)的赛道MSD中，该方法在第一阶段获得了70.25%的平均交集并集(MIUU)，在第二阶段达到了67.72%，在两个阶段都位居第一[1]。
Change detection is a geospatial application for social good whose development is restricted by a slow-growing labeling technology and outdated classification labels for remotely sensed images. In this paper, a change cross-detection method based on label improvements and multi-model fusion is proposed for Multi-temporal Semantic change Detection (MSD) with weak, noisy, and low-resolution labels. For unmatched labels, a Siamese Skip_FCN network is proposed to generate preliminary labels at high-resolution. Subsequently, a multi-model fusion method is introduced to perform accurate and stable land cover classification. In addition, a cross-detection structure is used to generate high precision change maps and a post-processing step further improves the final results. In the track MSD of the 2021 Data Fusion Contest (DFC21-MSD), the proposed method achieved a mean intersection over union (mIoU) of 70.25% in phase 1 and 67.72% in phase 2, ranking first in both phases [1].