Game4Loc: A UAV Geo-Localization Benchmark from Game Data

TL;DR

This paper introduces GTA-UAV, a large-scale UAV geo-localization dataset created from computer game environments, and proposes a practical cross-view image retrieval method that improves UAV localization accuracy in diverse scenarios.

Contribution

The work provides a new large-scale, diverse UAV dataset from game data and develops a contrastive learning approach for cross-view geo-localization that addresses practical challenges.

Findings

The dataset covers multiple altitudes, attitudes, and scenes.

The proposed method effectively learns cross-view matching without extra post-processing.

Experiments show improved localization accuracy and generalization to real-world scenarios.

Abstract

The vision-based geo-localization technology for UAV, serving as a secondary source of GPS information in addition to the global navigation satellite systems (GNSS), can still operate independently in the GPS-denied environment. Recent deep learning based methods attribute this as the task of image matching and retrieval. By retrieving drone-view images in geo-tagged satellite image database, approximate localization information can be obtained. However, due to high costs and privacy concerns, it is usually difficult to obtain large quantities of drone-view images from a continuous area. Existing drone-view datasets are mostly composed of small-scale aerial photography with a strong assumption that there exists a perfect one-to-one aligned reference image for any query, leaving a significant gap from the practical localization scenario. In this work, we construct a large-range contiguous area UAV geo-localization dataset named GTA-UAV, featuring multiple flight altitudes, attitudes, scenes, and targets using modern computer games. Based on this dataset, we introduce a more practical UAV geo-localization task including partial matches of cross-view paired data, and expand the image-level retrieval to the actual localization in terms of distance (meters). For the construction of drone-view and satellite-view pairs, we adopt a weight-based contrastive learning approach, which allows for effective learning while avoiding additional post-processing matching steps. Experiments demonstrate the effectiveness of our data and training method for UAV geo-localization, as well as the generalization capabilities to real-world scenarios.