Temporal Attention for Cross-View Sequential Image Localization

TL;DR

This paper presents a Temporal Attention Module (TAM) that significantly improves cross-view sequential image localization accuracy by leveraging contextual information, outperforming existing methods on multiple datasets.

Contribution

The paper introduces a novel Temporal Attention Module (TAM) for sequential image localization, enhancing accuracy and robustness over traditional single-image methods.

Findings

Substantial reduction in localization errors on CVIS dataset.

75.3% decrease in mean distance error on adapted KITTI-CVL dataset.

Outperforms state-of-the-art single-image localization techniques.

Abstract

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.