Bi-temporal Attention Transformer for Building Change Detection and Building Damage Assessment

Simple item page
aut.relation.endpage20
aut.relation.issue99
aut.relation.journalIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
aut.relation.startpage1
aut.relation.volumePP
dc.contributor.authorLu, W
dc.contributor.authorWei, L
dc.contributor.authorNguyen, M
dc.date.accessioned2024-01-31T01:11:47Z
dc.date.available2024-01-31T01:11:47Z
dc.date.issued2024-01-16
dc.description.abstractBuilding Change Detection (BCD) holds significant value in the context of monitoring land use, while Building Damage Assessment (BDA) plays a crucial role in expediting humanitarian rescue efforts post-disasters. To address these needs, we propose the Bi-Temporal Attention Module (BAM) as an innovative cross-attention mechanism aimed at effectively capturing spatio-temporal semantic relations between a pair of bi-temporal remote sensing images. Within BAM, a shifted windowing scheme has been implemented to confine the scope of the cross-attention mechanism to a specific range, not only excluding remote and irrelevant information but also contributing to computational efficiency. Moreover, existing methods for BDA often overlook the inherent order of ordinal labels, treating the BDA task simplistically as a multi-class semantic segmentation problem. Recognizing the vital significance of ordinal relationships, we approach the BDA task as an ordinal regression problem. To address this, we introduce a rank-consistent ordinal regression loss function to train our proposed change detection network, Bi-temporal Attention Transformer (BAT). Our method achieves state-of-the-art accuracy on two BCD datasets (LEVIR-CD+ and S2Looking), as well as the largest BDA dataset (xBD).
dc.identifier.citationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, ISSN: 1939-1404 (Print); 2151-1535 (Online), Institute of Electrical and Electronics Engineers (IEEE), PP(99), 1-20. doi: 10.1109/JSTARS.2024.3354310
dc.identifier.doi10.1109/JSTARS.2024.3354310
dc.identifier.issn1939-1404
dc.identifier.issn2151-1535
dc.identifier.urihttp://hdl.handle.net/10292/17170
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.relation.urihttps://ieeexplore.ieee.org/document/10400761
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. For more information, see https://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.accessrightsOpenAccess
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subject4605 Data Management and Data Science
dc.subject46 Information and Computing Sciences
dc.subject4603 Computer Vision and Multimedia Computation
dc.subject15 Life on Land
dc.subject0406 Physical Geography and Environmental Geoscience
dc.subject0801 Artificial Intelligence and Image Processing
dc.subject0909 Geomatic Engineering
dc.subject3709 Physical geography and environmental geoscience
dc.subject4013 Geomatic engineering
dc.subject4601 Applied computing
dc.titleBi-temporal Attention Transformer for Building Change Detection and Building Damage Assessment
dc.typeJournal Article
pubs.elements-id536093
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Bi-temporal_Attention_Transformer_for_Building_Change_Detection_and_Building_Damage_Assessment.pdf
Size:
20.24 MB
Format:
Adobe Portable Document Format
Description:
Journal article
Download
Collections
School of Engineering, Computer and Mathematical Sciences - Te Kura Mātai Pūhanga, Rorohiko, Pāngarau