Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2401.05157 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929497554550784 |
|---|---|
| author | Zhao, Yitao Li, Heng-Chao Liu, Nanqing Wang, Rui |
| author_facet | Zhao, Yitao Li, Heng-Chao Liu, Nanqing Wang, Rui |
| contents | In the conventional change detection (CD) pipeline, two manually registered and labeled remote sensing datasets serve as the input of the model for training and prediction. However, in realistic scenarios, data from different periods or sensors could fail to be aligned as a result of various coordinate systems. Geometric distortion caused by coordinate shifting remains a thorny issue for CD algorithms. In this paper, we propose a reusable self-supervised framework for bitemporal geometric distortion in CD tasks. The whole framework is composed of Pretext Representation Pre-training, Bitemporal Image Alignment, and Down-stream Decoder Fine-Tuning. With only single-stage pre-training, the key components of the framework can be reused for assistance in the bitemporal image alignment, while simultaneously enhancing the performance of the CD decoder. Experimental results in 2 large-scale realistic scenarios demonstrate that our proposed method can alleviate the bitemporal geometric distortion in CD tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_05157 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Toward distortion-aware change detection in realistic scenarios Zhao, Yitao Li, Heng-Chao Liu, Nanqing Wang, Rui Computer Vision and Pattern Recognition In the conventional change detection (CD) pipeline, two manually registered and labeled remote sensing datasets serve as the input of the model for training and prediction. However, in realistic scenarios, data from different periods or sensors could fail to be aligned as a result of various coordinate systems. Geometric distortion caused by coordinate shifting remains a thorny issue for CD algorithms. In this paper, we propose a reusable self-supervised framework for bitemporal geometric distortion in CD tasks. The whole framework is composed of Pretext Representation Pre-training, Bitemporal Image Alignment, and Down-stream Decoder Fine-Tuning. With only single-stage pre-training, the key components of the framework can be reused for assistance in the bitemporal image alignment, while simultaneously enhancing the performance of the CD decoder. Experimental results in 2 large-scale realistic scenarios demonstrate that our proposed method can alleviate the bitemporal geometric distortion in CD tasks. |
| title | Toward distortion-aware change detection in realistic scenarios |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.05157 |