MOGeo: Beyond One-to-One Cross-View Object Geo-localization

TL;DR

This paper introduces a new multi-object cross-view geo-localization task, constructs a benchmark dataset, and proposes a novel method, MOGeo, demonstrating its effectiveness in realistic multi-object scenarios.

Contribution

The paper defines the CVMOGL task, creates the CMLocation benchmark, and develops the MOGeo method to address multi-object geo-localization across views.

Findings

MOGeo outperforms existing methods on the CMLocation benchmark.

Cross-view multi-object geo-localization remains a challenging problem.

The proposed benchmark facilitates future research in realistic scenarios.

Abstract

Cross-View Object Geo-Localization (CVOGL) aims to locate an object of interest in a query image within a corresponding satellite image. Existing methods typically assume that the query image contains only a single object, which does not align with the complex, multi-object geo-localization requirements in real-world applications, making them unsuitable for practical scenarios. To bridge the gap between the realistic setting and existing task, we propose a new task, called Cross-View Multi-Object Geo-Localization (CVMOGL). To advance the CVMOGL task, we first construct a benchmark, CMLocation, which includes two datasets: CMLocation-V1 and CMLocation-V2. Furthermore, we propose a novel cross-view multi-object geo-localization method, MOGeo, and benchmark it against existing state-of-the-art methods. Extensive experiments are conducted under various application scenarios to validate the effectiveness of our method. The results demonstrate that cross-view object geo-localization in the more realistic setting remains a challenging problem, encouraging further research in this area.