Temporal Attention for Cross-View Sequential Image Localization
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913483567661056 |
|---|---|
| author | Yuan, Dong Maire, Frederic Dayoub, Feras |
| author_facet | Yuan, Dong Maire, Frederic Dayoub, Feras |
| contents | This paper introduces a novel approach to enhancing cross-view localization, focusing on the fine-grained, sequential localization of street-view images within a single known satellite image patch, a significant departure from traditional one-to-one image retrieval methods. By expanding to sequential image fine-grained localization, our model, equipped with a novel Temporal Attention Module (TAM), leverages contextual information to significantly improve sequential image localization accuracy. Our method shows substantial reductions in both mean and median localization errors on the Cross-View Image Sequence (CVIS) dataset, outperforming current state-of-the-art single-image localization techniques. Additionally, by adapting the KITTI-CVL dataset into sequential image sets, we not only offer a more realistic dataset for future research but also demonstrate our model's robust generalization capabilities across varying times and areas, evidenced by a 75.3% reduction in mean distance error in cross-view sequential image localization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_15569 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Temporal Attention for Cross-View Sequential Image Localization Yuan, Dong Maire, Frederic Dayoub, Feras Computer Vision and Pattern Recognition This paper introduces a novel approach to enhancing cross-view localization, focusing on the fine-grained, sequential localization of street-view images within a single known satellite image patch, a significant departure from traditional one-to-one image retrieval methods. By expanding to sequential image fine-grained localization, our model, equipped with a novel Temporal Attention Module (TAM), leverages contextual information to significantly improve sequential image localization accuracy. Our method shows substantial reductions in both mean and median localization errors on the Cross-View Image Sequence (CVIS) dataset, outperforming current state-of-the-art single-image localization techniques. Additionally, by adapting the KITTI-CVL dataset into sequential image sets, we not only offer a more realistic dataset for future research but also demonstrate our model's robust generalization capabilities across varying times and areas, evidenced by a 75.3% reduction in mean distance error in cross-view sequential image localization. |
| title | Temporal Attention for Cross-View Sequential Image Localization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.15569 |