Mask DeepLab: End-to-end image segmentation for change detection in high-resolution remote sensing images
Traditional change detection (CD) algorithms cannot meet the requirements of today’s high resolution remote sensing images (HR). Recently, deep learning-based CD has become a popular research topic. However, there are not many annotated samples for training deep learning (DL) models. Patch-based alg...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-12-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0303243421002890 |
| _version_ | 1811317571347021824 |
|---|---|
| author | Yanheng Wang Lianru Gao Danfeng Hong Jianjun Sha Lian Liu Bing Zhang Xianhui Rong Yonggang Zhang |
| author_facet | Yanheng Wang Lianru Gao Danfeng Hong Jianjun Sha Lian Liu Bing Zhang Xianhui Rong Yonggang Zhang |
| author_sort | Yanheng Wang |
| collection | DOAJ |
| description | Traditional change detection (CD) algorithms cannot meet the requirements of today’s high resolution remote sensing images (HR). Recently, deep learning-based CD has become a popular research topic. However, there are not many annotated samples for training deep learning (DL) models. Patch-based algorithm has become an important research direction in CD in response to the lack of training datasets, but the optimal patch size is relatively small and difficult to determine, which limits the use of spatial information and the extension of deep network. In this paper, we develop a feature-regularized mask DeepLab (FRM-DeepLab) for HRCD. First, a mask-based framework (MaskNet) that uses a few annotated samples to update model parameters is introduced. Based on MaskNet, we design a Mask-DeepLab to make full use of HR. Last, the deep features of unlabeled areas are extracted by an autoencoder as auxiliary information, and those features are concatenated in the middle-level features extracted by Mask-DeepLab to alleviate the influences of overfitting caused by small-scale samples. The algorithm is verified on three HRCD datasets. The visualization and quantitative analysis of the experiment results figure that this algorithm can implement significant performance improvement. |
| first_indexed | 2024-04-13T12:10:37Z |
| format | Article |
| id | doaj.art-60a846e7a497413fac247d5dec8fdf7d |
| institution | Directory Open Access Journal |
| issn | 1569-8432 |
| language | English |
| last_indexed | 2024-04-13T12:10:37Z |
| publishDate | 2021-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj.art-60a846e7a497413fac247d5dec8fdf7d2022-12-22T02:47:29ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322021-12-01104102582Mask DeepLab: End-to-end image segmentation for change detection in high-resolution remote sensing imagesYanheng Wang0Lianru Gao1Danfeng Hong2Jianjun Sha3Lian Liu4Bing Zhang5Xianhui Rong6Yonggang Zhang7College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin 150001, China; Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China; Corresponding author.Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaCollege of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin 150001, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China; College of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, ChinaCollege of Materials Science and Chemical Engineering, Harbin Engineering University, Harbin 150001, ChinaCollege of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin 150001, ChinaTraditional change detection (CD) algorithms cannot meet the requirements of today’s high resolution remote sensing images (HR). Recently, deep learning-based CD has become a popular research topic. However, there are not many annotated samples for training deep learning (DL) models. Patch-based algorithm has become an important research direction in CD in response to the lack of training datasets, but the optimal patch size is relatively small and difficult to determine, which limits the use of spatial information and the extension of deep network. In this paper, we develop a feature-regularized mask DeepLab (FRM-DeepLab) for HRCD. First, a mask-based framework (MaskNet) that uses a few annotated samples to update model parameters is introduced. Based on MaskNet, we design a Mask-DeepLab to make full use of HR. Last, the deep features of unlabeled areas are extracted by an autoencoder as auxiliary information, and those features are concatenated in the middle-level features extracted by Mask-DeepLab to alleviate the influences of overfitting caused by small-scale samples. The algorithm is verified on three HRCD datasets. The visualization and quantitative analysis of the experiment results figure that this algorithm can implement significant performance improvement.http://www.sciencedirect.com/science/article/pii/S0303243421002890AutoencoderChange detection (CD)DeepLabV3+High-resolution remote sensing images (HR)Mask |
| spellingShingle | Yanheng Wang Lianru Gao Danfeng Hong Jianjun Sha Lian Liu Bing Zhang Xianhui Rong Yonggang Zhang Mask DeepLab: End-to-end image segmentation for change detection in high-resolution remote sensing images International Journal of Applied Earth Observations and Geoinformation Autoencoder Change detection (CD) DeepLabV3+ High-resolution remote sensing images (HR) Mask |
| title | Mask DeepLab: End-to-end image segmentation for change detection in high-resolution remote sensing images |
| title_full | Mask DeepLab: End-to-end image segmentation for change detection in high-resolution remote sensing images |
| title_fullStr | Mask DeepLab: End-to-end image segmentation for change detection in high-resolution remote sensing images |
| title_full_unstemmed | Mask DeepLab: End-to-end image segmentation for change detection in high-resolution remote sensing images |
| title_short | Mask DeepLab: End-to-end image segmentation for change detection in high-resolution remote sensing images |
| title_sort | mask deeplab end to end image segmentation for change detection in high resolution remote sensing images |
| topic | Autoencoder Change detection (CD) DeepLabV3+ High-resolution remote sensing images (HR) Mask |
| url | http://www.sciencedirect.com/science/article/pii/S0303243421002890 |
| work_keys_str_mv | AT yanhengwang maskdeeplabendtoendimagesegmentationforchangedetectioninhighresolutionremotesensingimages AT lianrugao maskdeeplabendtoendimagesegmentationforchangedetectioninhighresolutionremotesensingimages AT danfenghong maskdeeplabendtoendimagesegmentationforchangedetectioninhighresolutionremotesensingimages AT jianjunsha maskdeeplabendtoendimagesegmentationforchangedetectioninhighresolutionremotesensingimages AT lianliu maskdeeplabendtoendimagesegmentationforchangedetectioninhighresolutionremotesensingimages AT bingzhang maskdeeplabendtoendimagesegmentationforchangedetectioninhighresolutionremotesensingimages AT xianhuirong maskdeeplabendtoendimagesegmentationforchangedetectioninhighresolutionremotesensingimages AT yonggangzhang maskdeeplabendtoendimagesegmentationforchangedetectioninhighresolutionremotesensingimages |