4.7 Article

Unsupervised Change Detection by Cross-Resolution Difference Learning

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2021.3079907

关键词

Image resolution; Feature extraction; Image segmentation; Remote sensing; Mutual information; Learning systems; Data mining; Coupled deep neural network (CDNN); cross-resolution difference; mutual information distance; unsupervised change detection (CD)

资金

  1. National Science Fund for Distinguished Young Scholars [61925112]
  2. National Natural Science Foundation of China [61806193, 61772510]
  3. Innovation Capability Support Program of Shaanxi [2020KJXX-091, 2020TD-015]
  4. Key Research and Development Program of Shaanxi [2020ZDLGY04-03]
  5. Funds for International Cooperation and Exchange of the National Natural Science Foundation of China [62011530021]

向作者/读者索取更多资源

This article proposes a cross-resolution difference learning method to detect changes from multitemporal images in their original different resolutions without resizing operations. The method involves segmenting input images into homogeneous regions, generating pixelwise difference maps based on mutual information distance and deep feature distance, and then fusing and binarizing the cross-resolution difference maps to produce the final binary change map. Extensive experiments on four datasets demonstrate the effectiveness of the proposed method for detecting changes from different resolution images.
Change detection (CD) aims to identify the differences between multitemporal images acquired over the same geographical area at different times. With the advantages of requiring no cumbersome labeled change information, unsupervised CD has attracted extensive attention of researchers. Multitemporal images tend to have different resolutions as they are usually captured at different times with different sensor properties. It is difficult to directly obtain one pixelwise change map for two images with different resolutions, so current methods usually resize multitemporal images to a unified size. However, resizing operations change the original information of pixels, which limits the final CD performance. This article aims to detect changes from multitemporal images in the originally different resolutions without resizing operations. To achieve this, a cross-resolution difference learning method is proposed. Specifically, two cross-resolution pixelwise difference maps are generated for the two different resolution images and fused to produce the final change map. First, the two input images are segmented into individual homogeneous regions separately due to different resolutions. Second, each pixelwise difference map is produced according to two measure distances, the mutual information distance and the deep feature distance, between image regions in which the pixel lies. Third, the final binary change map is generated by fusing and binarizing the two cross-resolution difference maps. Extensive experiments on four datasets demonstrate the effectiveness of the proposed method for detecting changes from different resolution images.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据