Game4Loc：從遊戲數據中獲取的 UAV 地理定位基準測試

Game4Loc: A UAV Geo-Localization Benchmark from Game Data

September 25, 2024

作者: Yuxiang Ji, Boyong He, Zhuoyue Tan, Liaoni Wu

cs.AI

摘要

基於視覺的 UAV 地理定位技術，作為全球導航衛星系統（GNSS）之外的 GPS 信息的輔助來源，可以在 GPS 無法使用的環境中獨立運作。最近基於深度學習的方法將這視為圖像匹配和檢索的任務。通過在地理標記的衛星圖像數據庫中檢索無人機視圖圖像，可以獲得大致的定位信息。然而，由於高昂的成本和隱私問題，通常很難從連續區域獲得大量的無人機視圖圖像。現有的無人機視圖數據集主要由小規模航空攝影組成，並強烈假定對於任何查詢，存在一個完美的一對一對齊參考圖像，這與實際的定位場景存在顯著差距。在這項工作中，我們構建了一個名為 GTA-UAV 的大範圍連續區域 UAV 地理定位數據集，使用現代電腦遊戲展示多個飛行高度、態度、場景和目標。基於這個數據集，我們引入了一個更實際的 UAV 地理定位任務，包括跨視圖配對數據的部分匹配，並將圖像級檢索擴展為實際距離（米）的定位。為了構建無人機視圖和衛星視圖對，我們採用基於權重的對比學習方法，這使得在避免額外後處理匹配步驟的同時實現有效學習。實驗證明了我們的數據和訓練方法對於 UAV 地理定位的有效性，以及對於真實場景的泛化能力。

English

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.