Local Similarity Siamese Network for Urban Land Change Detection on Remote Sensing Images
Change detection is an important task in the field of remote sensing. Various change detection methods based on convolutional neural networks (CNNs) have recently been proposed for remote sensing using satellite or aerial images. However, existing methods allow only the partial use of content inform...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9387529/ |
| _version_ | 1818438269560422400 |
|---|---|
| author | Haeyun Lee Kyungsu Lee Jun Hee Kim Younghwan Na Juhum Park Jihwan P. Choi Jae Youn Hwang |
| author_facet | Haeyun Lee Kyungsu Lee Jun Hee Kim Younghwan Na Juhum Park Jihwan P. Choi Jae Youn Hwang |
| author_sort | Haeyun Lee |
| collection | DOAJ |
| description | Change detection is an important task in the field of remote sensing. Various change detection methods based on convolutional neural networks (CNNs) have recently been proposed for remote sensing using satellite or aerial images. However, existing methods allow only the partial use of content information in images during change detection because they adopt simple feature similarity measurements or pixel-level loss functions to construct their network architectures. Therefore, when these methods are applied to complex urban areas, their performance in terms of change detection tends to be limited. In this article, a novel CNN-based change detection approach, referred to as a local similarity Siamese network (LSS-Net), with a cosine similarity measurement, was proposed for better urban land change detection in remote sensing images. To use content information on two sequential images, a new change attention map-based content loss function was developed in this study. In addition, to enhance the performance of the LSS-Net in terms of change detection, a suitable feature similarity measurement method, incorporated into a local similarity attention module, was determined through systemic experiments. To verify the change detection performance of the LSS-Net, it was compared with other state-of-the-art methods. The experimental results show that the proposed method outperforms the state-of-the-art methods in terms of the F1 score (0.9630, 0.9377, and 0.7751) and kappa (0.9581, 0.9351, and 0.7646) on the three test datasets, thus suggesting its potential for various remote sensing applications. |
| first_indexed | 2024-12-14T17:37:53Z |
| format | Article |
| id | doaj.art-61f400ece15d4b15ae407e6ae1b6e95f |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-14T17:37:53Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-61f400ece15d4b15ae407e6ae1b6e95f2022-12-21T22:52:55ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352021-01-01144139414910.1109/JSTARS.2021.30692429387529Local Similarity Siamese Network for Urban Land Change Detection on Remote Sensing ImagesHaeyun Lee0https://orcid.org/0000-0002-7572-1705Kyungsu Lee1https://orcid.org/0000-0003-2516-7598Jun Hee Kim2https://orcid.org/0000-0001-7141-9288Younghwan Na3Juhum Park4Jihwan P. Choi5https://orcid.org/0000-0001-7996-5507Jae Youn Hwang6https://orcid.org/0000-0003-4659-6009Information and Communication Engineering, Daegu Gyeongbuk Institute of Science and Technology, Daegu, South KoreaInformation and Communication Engineering, Daegu Gyeongbuk Institute of Science and Technology, Daegu, South KoreaAgency for Defense Development, Daejoen, South KoreaInformation and Communication Engineering, Daegu Gyeongbuk Institute of Science and Technology, Daegu, South KoreaDabeeo Inc., Seoul, South KoreaDepartment of Aerospace Engineering, Korea Advanced Institute of Science and Technology, Daejoen, South KoreaInformation and Communication Engineering, Daegu Gyeongbuk Institute of Science and Technology, Daegu, South KoreaChange detection is an important task in the field of remote sensing. Various change detection methods based on convolutional neural networks (CNNs) have recently been proposed for remote sensing using satellite or aerial images. However, existing methods allow only the partial use of content information in images during change detection because they adopt simple feature similarity measurements or pixel-level loss functions to construct their network architectures. Therefore, when these methods are applied to complex urban areas, their performance in terms of change detection tends to be limited. In this article, a novel CNN-based change detection approach, referred to as a local similarity Siamese network (LSS-Net), with a cosine similarity measurement, was proposed for better urban land change detection in remote sensing images. To use content information on two sequential images, a new change attention map-based content loss function was developed in this study. In addition, to enhance the performance of the LSS-Net in terms of change detection, a suitable feature similarity measurement method, incorporated into a local similarity attention module, was determined through systemic experiments. To verify the change detection performance of the LSS-Net, it was compared with other state-of-the-art methods. The experimental results show that the proposed method outperforms the state-of-the-art methods in terms of the F1 score (0.9630, 0.9377, and 0.7751) and kappa (0.9581, 0.9351, and 0.7646) on the three test datasets, thus suggesting its potential for various remote sensing applications.https://ieeexplore.ieee.org/document/9387529/Change detectionremote sensingSiamese networksimilarity attention |
| spellingShingle | Haeyun Lee Kyungsu Lee Jun Hee Kim Younghwan Na Juhum Park Jihwan P. Choi Jae Youn Hwang Local Similarity Siamese Network for Urban Land Change Detection on Remote Sensing Images IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Change detection remote sensing Siamese network similarity attention |
| title | Local Similarity Siamese Network for Urban Land Change Detection on Remote Sensing Images |
| title_full | Local Similarity Siamese Network for Urban Land Change Detection on Remote Sensing Images |
| title_fullStr | Local Similarity Siamese Network for Urban Land Change Detection on Remote Sensing Images |
| title_full_unstemmed | Local Similarity Siamese Network for Urban Land Change Detection on Remote Sensing Images |
| title_short | Local Similarity Siamese Network for Urban Land Change Detection on Remote Sensing Images |
| title_sort | local similarity siamese network for urban land change detection on remote sensing images |
| topic | Change detection remote sensing Siamese network similarity attention |
| url | https://ieeexplore.ieee.org/document/9387529/ |
| work_keys_str_mv | AT haeyunlee localsimilaritysiamesenetworkforurbanlandchangedetectiononremotesensingimages AT kyungsulee localsimilaritysiamesenetworkforurbanlandchangedetectiononremotesensingimages AT junheekim localsimilaritysiamesenetworkforurbanlandchangedetectiononremotesensingimages AT younghwanna localsimilaritysiamesenetworkforurbanlandchangedetectiononremotesensingimages AT juhumpark localsimilaritysiamesenetworkforurbanlandchangedetectiononremotesensingimages AT jihwanpchoi localsimilaritysiamesenetworkforurbanlandchangedetectiononremotesensingimages AT jaeyounhwang localsimilaritysiamesenetworkforurbanlandchangedetectiononremotesensingimages |