درحال بارگذاري...
| ایمیل دوست | |
| نام شما | |
| ایمیل شما | |
| کد مقابل را وارد نمایید | |
این صفحه برای دوست شما با موفقیت ارسال شد.
0 مرتبه مشاهده شده
MaskChanger: A Transformer-Based Model Tailoring Change Detection with Mask Classification
Ebrahimzadeh, M.
- DOI:10.1109/MVIP62238.2024.10491166
- Main Entry: Ebrahimzadeh, M.
- Title:MaskChanger: A Transformer-Based Model Tailoring Change Detection with Mask Classification.
- Publisher:2024.
- Abstract:Change detection in multi-temporal remote sensing data enables crucial urban analysis and environmental monitoring applications. However, complex factors like illumination variance and occlusion make robust automated change interpretation challenging. We propose MaskChanger - a novel deep learning paradigm tailored for satellite image change detection. Our method adapts the segmentation-specialized Mask2Former architecture by incorporating Siamese networks to extract features separately from bi-temporal images, while retaining the original mask transformer decoder. To our knowledge, this is the first study in which change detection is converted from the existing per-pixel classification approach into a mask classification approach. Evaluated on the LEVIR-CD benchmark of over 600 very high-resolution image pairs exhibiting real-world rural and urban changes, MaskChanger achieves Fl-Score of 91.96%, outperforming prior transformer-based change detection approaches. © 2024 IEEE
- Notes:Sharif Repository
- Subject:Transformer.
- Subject:Deep learning.
- Subject:Image classification.
- Subject:Image segmentation.
- Subject:Remote sensing.
- Subject:Classification approach.
- Subject:Complex factors.
- Subject:Environmental Monitoring.
- Subject:Monitoring applications.
- Subject:Multi-temporal remote sensing.
- Subject:Remote sensing data.
- Subject:Remote sensing images.
- Subject:Urban analysis.
- Subject:Change detection.
- Added Entry:Manzuri, M. T.
- Added Entry:Sharif University of Technology.
- Source: Iranian Conference on Machine Vision and Image Processing, MVIP ; 2024 ; 21666776 (ISSN); 979-835035049-4 (ISBN)
- Web Site:https://ieeexplore.ieee.org/document/10491166
