Sliding-Window Dissimilarity Cross-Attention for Near-Real-Time Building Change Detection
A near-real-time change detection network can consistently identify unauthorized construction activities over a wide area, empowering authorities to enforce regulations efficiently. Furthermore, it can promptly assess building damage, enabling expedited rescue efforts. The extensive adoption of deep...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/1/135 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841548979161006080 |
|---|---|
| author | Wen Lu Minh Nguyen |
| author_facet | Wen Lu Minh Nguyen |
| author_sort | Wen Lu |
| collection | DOAJ |
| description | A near-real-time change detection network can consistently identify unauthorized construction activities over a wide area, empowering authorities to enforce regulations efficiently. Furthermore, it can promptly assess building damage, enabling expedited rescue efforts. The extensive adoption of deep learning in change detection has prompted a predominant emphasis on enhancing detection performance, primarily through the expansion of the depth and width of networks, overlooking considerations regarding inference time and computational cost. To accurately represent the spatio-temporal semantic correlations between pre-change and post-change images, we create an innovative transformer attention mechanism named Sliding-Window Dissimilarity Cross-Attention (SWDCA), which detects spatio-temporal semantic discrepancies by explicitly modeling the dissimilarity of bi-temporal tokens, departing from the mono-temporal similarity attention typically used in conventional transformers. In order to fulfill the near-real-time requirement, SWDCA employs a sliding-window scheme to limit the range of the cross-attention mechanism within a predetermined window/dilated window size. This approach not only excludes distant and irrelevant information but also reduces computational cost. Furthermore, we develop a lightweight Siamese backbone for extracting building and environmental features. Subsequently, we integrate an SWDCA module into this backbone, forming an efficient change detection network. Quantitative evaluations and visual analyses of thorough experiments verify that our method achieves top-tier accuracy on two building change detection datasets of remote sensing imagery, while also achieving a real-time inference speed of 33.2 FPS on a mobile GPU. |
| format | Article |
| id | doaj-art-2d44364bdf124a1083165f70d228fbce |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-2d44364bdf124a1083165f70d228fbce2025-01-10T13:20:21ZengMDPI AGRemote Sensing2072-42922025-01-0117113510.3390/rs17010135Sliding-Window Dissimilarity Cross-Attention for Near-Real-Time Building Change DetectionWen Lu0Minh Nguyen1School of Engineering, Computer & Mathematical Sciences, Auckland University of Technology, Auckland 1010, New ZealandSchool of Engineering, Computer & Mathematical Sciences, Auckland University of Technology, Auckland 1010, New ZealandA near-real-time change detection network can consistently identify unauthorized construction activities over a wide area, empowering authorities to enforce regulations efficiently. Furthermore, it can promptly assess building damage, enabling expedited rescue efforts. The extensive adoption of deep learning in change detection has prompted a predominant emphasis on enhancing detection performance, primarily through the expansion of the depth and width of networks, overlooking considerations regarding inference time and computational cost. To accurately represent the spatio-temporal semantic correlations between pre-change and post-change images, we create an innovative transformer attention mechanism named Sliding-Window Dissimilarity Cross-Attention (SWDCA), which detects spatio-temporal semantic discrepancies by explicitly modeling the dissimilarity of bi-temporal tokens, departing from the mono-temporal similarity attention typically used in conventional transformers. In order to fulfill the near-real-time requirement, SWDCA employs a sliding-window scheme to limit the range of the cross-attention mechanism within a predetermined window/dilated window size. This approach not only excludes distant and irrelevant information but also reduces computational cost. Furthermore, we develop a lightweight Siamese backbone for extracting building and environmental features. Subsequently, we integrate an SWDCA module into this backbone, forming an efficient change detection network. Quantitative evaluations and visual analyses of thorough experiments verify that our method achieves top-tier accuracy on two building change detection datasets of remote sensing imagery, while also achieving a real-time inference speed of 33.2 FPS on a mobile GPU.https://www.mdpi.com/2072-4292/17/1/135remote sensingbuilding change detectiontransformercross-attention |
| spellingShingle | Wen Lu Minh Nguyen Sliding-Window Dissimilarity Cross-Attention for Near-Real-Time Building Change Detection Remote Sensing remote sensing building change detection transformer cross-attention |
| title | Sliding-Window Dissimilarity Cross-Attention for Near-Real-Time Building Change Detection |
| title_full | Sliding-Window Dissimilarity Cross-Attention for Near-Real-Time Building Change Detection |
| title_fullStr | Sliding-Window Dissimilarity Cross-Attention for Near-Real-Time Building Change Detection |
| title_full_unstemmed | Sliding-Window Dissimilarity Cross-Attention for Near-Real-Time Building Change Detection |
| title_short | Sliding-Window Dissimilarity Cross-Attention for Near-Real-Time Building Change Detection |
| title_sort | sliding window dissimilarity cross attention for near real time building change detection |
| topic | remote sensing building change detection transformer cross-attention |
| url | https://www.mdpi.com/2072-4292/17/1/135 |
| work_keys_str_mv | AT wenlu slidingwindowdissimilaritycrossattentionfornearrealtimebuildingchangedetection AT minhnguyen slidingwindowdissimilaritycrossattentionfornearrealtimebuildingchangedetection |