The estimation of Unmanned Aerial Vehicle (UAV) poses using visual information is essential in Global Navigation Satellite System (GNSS)-denied environments. In this paper, we propose a UAV visual navigation algorithm based on visual-geography Bundle Adjustment (BA) to address the challenge of missing geolocation information in monocular visual navigation. This algorithm presents an effective approach to UAV navigation and positioning. Initially, Visual Odometry (VO) was employed for tracking the UAV’s motion and extracting keyframes. Subsequently, a geolocation method based on heterogeneous image matching was utilized to calculate the geographic pose of the UAV. Additionally, we introduce a tightly coupled information fusion method based on visual-geography optimization, which provides a geographic initializer and enables real-time estimation of the UAV’s geographical pose. Finally, the algorithm dynamically adjusts the weight of geographic information to improve optimization accuracy. The proposed method is extensively evaluated in both simulated and real-world environments, and the results demonstrate that our proposed approach can accurately and in real-time estimate the geographic pose of the UAV in a GNSS-denied environment. Specifically, our proposed approach achieves a root-mean-square error (RMSE) and mean positioning accuracy of less than 13 m.

Maintaining real-time and stable geolocation for unmanned aerial vehicles (UAVs) using pre-existing geolocation information remains a pivotal and pressing challenge in the realm of autonomous navigation and localization. To tackle this, we introduce a framework that integrates visual Simultaneous Localization and Mapping (vSLAM) with a deep-learning-based UAV-to-satellite (U2S) image matching technique, specifically tailored for downward-tilted camera setups. This framework incorporates a similarity-based heterogeneous image matching approach, enabling 6 degrees of freedom (DOF) U2S prediction for UAVs. Utilizing this prediction, we devise a single-shot global initialization method for rapid and robust global initialization. Furthermore, to bolster localization accuracy, we propose an iterative map fusion method that integrates U2S predictions with visual data from vSLAM in real-time. Evaluations conducted using aerial datasets demonstrate the proposed method’s capability to facilitate rapid and effective global initialization, as well as real-time and accurate estimation of the UAV’s geographical pose.

Visual geolocalization for aerial vehicles based on an analysis of Earth observation imagery is an effective method in GNSS-denied environments. However, existing methods for geographic location estimation have limitations: one relies on high-precision geodetic elevation data, which is costly, and the other assumes a flat ground surface, ignoring elevation differences. This paper presents a novel aerial vehicle geolocalization method. It integrates 2D information and relative depth information, which are both from Earth observation images. Firstly, the aerial and reference remote sensing satellite images are fed into a feature-matching network to extract pixel-level feature-matching pairs. Then, a depth estimation network is used to estimate the relative depth of the satellite remote sensing image, thereby obtaining the relative depth information of the ground area within the field of view of the aerial image. Finally, high-confidence matching pairs with similar depth and uniform distribution are selected to estimate the geographic location of the aerial vehicle. Experimental results demonstrate that the proposed method outperforms existing ones in terms of geolocalization accuracy and stability. It eliminates reliance on elevation data or planar assumptions, thus providing a more adaptable and robust solution for aerial vehicle geolocalization in GNSS-denied environments.