TransC-GD-CD: Transformer-Based Conditional Generative Diffusion Change Detection Model
Change detection (CD) methodologies have garnered substantial attention owing to their capability to monitor alterations in geographic spaces across temporal intervals, especially with the acquisition of high-resolution remote sensing images. However, challenges persist due to dissimilar imaging con...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10460113/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850023102724964352 |
|---|---|
| author | Yihan Wen Zhuo Zhang Qi Cao Guanchong Niu |
| author_facet | Yihan Wen Zhuo Zhang Qi Cao Guanchong Niu |
| author_sort | Yihan Wen |
| collection | DOAJ |
| description | Change detection (CD) methodologies have garnered substantial attention owing to their capability to monitor alterations in geographic spaces across temporal intervals, especially with the acquisition of high-resolution remote sensing images. However, challenges persist due to dissimilar imaging conditions and temporal windows. Although deep-learning architectures have shown promise in addressing challenges in CD, many existing methods struggle to capture long-range dependencies and local spatial information effectively. The current CD methods rely heavily on pure CNNs and transformers, which employ only single-pass forward propagation. This approach leads to inadequate utilization of feature information, resulting in inaccurate CD maps, particularly when discerning edges. To overcome these limitations, we propose a transformer-based conditional generative diffusion method for CD, named TransC-GD-CD, tailored for RS data. This approach leverages the numerous sampling iterations of the DDPM, contributing to the generation of high-quality CD maps. In addition, the frequency cross transformer mechanism seamlessly amalgamates CD condition with the noise feature within the DDPM. The innovative mechanism effectively bridges diffusion noise and conditional semantic terrains. Moreover, a novel multitype difference extraction module, named appear–disappear–concat, is devised to partition the CD task to optimize both segmentation extraction and CD classification, overcoming the persistent challenge of information loss endemic to conventional CD algorithms, such as simple subtraction. We demonstrate the superiority of TransC-GD-CD by comparing the experiment results against various algorithms across three widely used CD datasets, namely CDD, WHU, and LEVIR. |
| format | Article |
| id | doaj-art-1640b4f55f294f80871ffc84a820cd06 |
| institution | DOAJ |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-1640b4f55f294f80871ffc84a820cd062025-08-20T03:01:28ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352024-01-01177144715810.1109/JSTARS.2024.337320110460113TransC-GD-CD: Transformer-Based Conditional Generative Diffusion Change Detection ModelYihan Wen0https://orcid.org/0009-0009-9106-8521Zhuo Zhang1https://orcid.org/0000-0002-3506-232XQi Cao2https://orcid.org/0000-0001-8649-9313Guanchong Niu3https://orcid.org/0000-0002-0571-2571Guangzhou Institute of Technology, Xidian University, Guangzhou, ChinaSchool of Computer Science, National University of Defense Technology, Changsha, ChinaGuangzhou Institute of Technology, Xidian University, Guangzhou, ChinaGuangzhou Institute of Technology, Xidian University, Guangzhou, ChinaChange detection (CD) methodologies have garnered substantial attention owing to their capability to monitor alterations in geographic spaces across temporal intervals, especially with the acquisition of high-resolution remote sensing images. However, challenges persist due to dissimilar imaging conditions and temporal windows. Although deep-learning architectures have shown promise in addressing challenges in CD, many existing methods struggle to capture long-range dependencies and local spatial information effectively. The current CD methods rely heavily on pure CNNs and transformers, which employ only single-pass forward propagation. This approach leads to inadequate utilization of feature information, resulting in inaccurate CD maps, particularly when discerning edges. To overcome these limitations, we propose a transformer-based conditional generative diffusion method for CD, named TransC-GD-CD, tailored for RS data. This approach leverages the numerous sampling iterations of the DDPM, contributing to the generation of high-quality CD maps. In addition, the frequency cross transformer mechanism seamlessly amalgamates CD condition with the noise feature within the DDPM. The innovative mechanism effectively bridges diffusion noise and conditional semantic terrains. Moreover, a novel multitype difference extraction module, named appear–disappear–concat, is devised to partition the CD task to optimize both segmentation extraction and CD classification, overcoming the persistent challenge of information loss endemic to conventional CD algorithms, such as simple subtraction. We demonstrate the superiority of TransC-GD-CD by comparing the experiment results against various algorithms across three widely used CD datasets, namely CDD, WHU, and LEVIR.https://ieeexplore.ieee.org/document/10460113/Change detection (CD)denoising diffusion probabilistic modelgenerative models |
| spellingShingle | Yihan Wen Zhuo Zhang Qi Cao Guanchong Niu TransC-GD-CD: Transformer-Based Conditional Generative Diffusion Change Detection Model IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Change detection (CD) denoising diffusion probabilistic model generative models |
| title | TransC-GD-CD: Transformer-Based Conditional Generative Diffusion Change Detection Model |
| title_full | TransC-GD-CD: Transformer-Based Conditional Generative Diffusion Change Detection Model |
| title_fullStr | TransC-GD-CD: Transformer-Based Conditional Generative Diffusion Change Detection Model |
| title_full_unstemmed | TransC-GD-CD: Transformer-Based Conditional Generative Diffusion Change Detection Model |
| title_short | TransC-GD-CD: Transformer-Based Conditional Generative Diffusion Change Detection Model |
| title_sort | transc gd cd transformer based conditional generative diffusion change detection model |
| topic | Change detection (CD) denoising diffusion probabilistic model generative models |
| url | https://ieeexplore.ieee.org/document/10460113/ |
| work_keys_str_mv | AT yihanwen transcgdcdtransformerbasedconditionalgenerativediffusionchangedetectionmodel AT zhuozhang transcgdcdtransformerbasedconditionalgenerativediffusionchangedetectionmodel AT qicao transcgdcdtransformerbasedconditionalgenerativediffusionchangedetectionmodel AT guanchongniu transcgdcdtransformerbasedconditionalgenerativediffusionchangedetectionmodel |