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

2026-03-14

AI Summary

This work addresses the limitation of existing cross-view geolocalization methods, which are confined to single-target scenarios and struggle to meet the multi-object requirements of real-world applications. We introduce, for the first time, the Cross-View Multi-Object Geolocalization (CVMOGL) task, establish a benchmark dataset comprising CMLocation-V1 and CMLocation-V2, and propose the MOGeo algorithm to enable accurate cross-view matching and localization of multiple targets simultaneously. Experimental results demonstrate that MOGeo performs effectively across diverse scenarios, substantially advancing beyond the conventional one-to-one matching paradigm and facilitating practical deployment. Furthermore, our study highlights persistent challenges in current approaches, thereby laying a foundational framework for future research in this emerging direction.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Localization, Mapping, and Navigation

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

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.

Problem

• Cross-View Object Geo-Localization
• Multi-Object Geo-Localization
• CVMOGL
• Realistic Geo-Localization

Innovation

• Cross-View Multi-Object Geo-Localization
• MOGeo
• CMLocation
• Satellite-to-Ground Matching
• Multi-Object Localization