Deep learning for change detection in remote sensing: a review
ABSTRACTA large number of publications have incorporated deep learning in the process of remote sensing change detection. In these Deep Learning Change Detection (DLCD) publications, deep learning methods have demonstrated their superiority over conventional change detection methods. However, the th...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-07-01
|
| Series: | Geo-spatial Information Science |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/10095020.2022.2085633 |
| _version_ | 1797649184476626944 |
|---|---|
| author | Ting Bai Le Wang Dameng Yin Kaimin Sun Yepei Chen Wenzhuo Li Deren Li |
| author_facet | Ting Bai Le Wang Dameng Yin Kaimin Sun Yepei Chen Wenzhuo Li Deren Li |
| author_sort | Ting Bai |
| collection | DOAJ |
| description | ABSTRACTA large number of publications have incorporated deep learning in the process of remote sensing change detection. In these Deep Learning Change Detection (DLCD) publications, deep learning methods have demonstrated their superiority over conventional change detection methods. However, the theoretical underpinnings of why deep learning improves the performance of change detection remain unresolved. As of today, few in-depth reviews have investigated the mechanisms of DLCD. Without such a review, five critical questions remain unclear. Does DLCD provide improved information representation for change detection? If so, how? How to select an appropriate DLCD method and why? How much does each type of change benefits from DLCD in terms of its performance? What are the major limitations of existing DLCD methods and what are the prospects for DLCD? To address these five questions, we reviewed according to the following strategies. We grouped the DLCD information assemblages into the four unique dimensions of remote sensing: spectral, spatial, temporal, and multi-sensor. For the extraction of information in each dimension, the difference between DLCD and conventional change detection methods was compared. We proposed a taxonomy of existing DLCD methods by dividing them into two distinctive pools: separate and coupled models. Their advantages, limitations, applicability, and performance were thoroughly investigated and explicitly presented. We examined the variations in performance between DLCD and conventional change detection. We depicted two limitations of DLCD, i.e. training sample and hardware and software dilemmas. Based on these analyses, we identified directions for future developments. As a result of our review, we found that DLCD’s advantages over conventional change detection can be attributed to three factors: improved information representation; improved change detection methods; and performance enhancements. DLCD has to surpass the limitations with regard to training samples and computing infrastructure. We envision this review can boost developments of deep learning in change detection applications. |
| first_indexed | 2024-03-11T15:42:39Z |
| format | Article |
| id | doaj.art-e37581ab8ee94044b19718d11c0249be |
| institution | Directory Open Access Journal |
| issn | 1009-5020 1993-5153 |
| language | English |
| last_indexed | 2024-03-11T15:42:39Z |
| publishDate | 2023-07-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Geo-spatial Information Science |
| spelling | doaj.art-e37581ab8ee94044b19718d11c0249be2023-10-26T11:21:36ZengTaylor & Francis GroupGeo-spatial Information Science1009-50201993-51532023-07-0126326228810.1080/10095020.2022.2085633Deep learning for change detection in remote sensing: a reviewTing Bai0Le Wang1Dameng Yin2Kaimin Sun3Yepei Chen4Wenzhuo Li5Deren Li6Project Planning Department, Wuhan Land Arranging Storage Center, Wuhan, ChinaDepartment of Geography, University at Buffalo, The State University of New York, Buffalo, USAInstitute of Crop Sciences, Chinese Academy of Agricultural Sciences, Beijing, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, ChinaSchool of Computer Science, Hubei University of Technology, Wuhan, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, ChinaABSTRACTA large number of publications have incorporated deep learning in the process of remote sensing change detection. In these Deep Learning Change Detection (DLCD) publications, deep learning methods have demonstrated their superiority over conventional change detection methods. However, the theoretical underpinnings of why deep learning improves the performance of change detection remain unresolved. As of today, few in-depth reviews have investigated the mechanisms of DLCD. Without such a review, five critical questions remain unclear. Does DLCD provide improved information representation for change detection? If so, how? How to select an appropriate DLCD method and why? How much does each type of change benefits from DLCD in terms of its performance? What are the major limitations of existing DLCD methods and what are the prospects for DLCD? To address these five questions, we reviewed according to the following strategies. We grouped the DLCD information assemblages into the four unique dimensions of remote sensing: spectral, spatial, temporal, and multi-sensor. For the extraction of information in each dimension, the difference between DLCD and conventional change detection methods was compared. We proposed a taxonomy of existing DLCD methods by dividing them into two distinctive pools: separate and coupled models. Their advantages, limitations, applicability, and performance were thoroughly investigated and explicitly presented. We examined the variations in performance between DLCD and conventional change detection. We depicted two limitations of DLCD, i.e. training sample and hardware and software dilemmas. Based on these analyses, we identified directions for future developments. As a result of our review, we found that DLCD’s advantages over conventional change detection can be attributed to three factors: improved information representation; improved change detection methods; and performance enhancements. DLCD has to surpass the limitations with regard to training samples and computing infrastructure. We envision this review can boost developments of deep learning in change detection applications.https://www.tandfonline.com/doi/10.1080/10095020.2022.2085633Deep learningchange detectionremote sensingreviewinformation representation |
| spellingShingle | Ting Bai Le Wang Dameng Yin Kaimin Sun Yepei Chen Wenzhuo Li Deren Li Deep learning for change detection in remote sensing: a review Geo-spatial Information Science Deep learning change detection remote sensing review information representation |
| title | Deep learning for change detection in remote sensing: a review |
| title_full | Deep learning for change detection in remote sensing: a review |
| title_fullStr | Deep learning for change detection in remote sensing: a review |
| title_full_unstemmed | Deep learning for change detection in remote sensing: a review |
| title_short | Deep learning for change detection in remote sensing: a review |
| title_sort | deep learning for change detection in remote sensing a review |
| topic | Deep learning change detection remote sensing review information representation |
| url | https://www.tandfonline.com/doi/10.1080/10095020.2022.2085633 |
| work_keys_str_mv | AT tingbai deeplearningforchangedetectioninremotesensingareview AT lewang deeplearningforchangedetectioninremotesensingareview AT damengyin deeplearningforchangedetectioninremotesensingareview AT kaiminsun deeplearningforchangedetectioninremotesensingareview AT yepeichen deeplearningforchangedetectioninremotesensingareview AT wenzhuoli deeplearningforchangedetectioninremotesensingareview AT derenli deeplearningforchangedetectioninremotesensingareview |