Using images captured by drone cameras and comparing them with known Google satellite maps to obtain the current location of the drone is an important way of UAV navigation in GPS-denied environments. But, due to inherent modality differences and significant geometric deformations, cross-modal image registration is challenging. This paper proposes a CNN-Transformer hybrid network model for feature detection and feature matching. ResNet50 is used as the backbone network for feature extraction. An improved feature fusion module is used to fuse feature maps from different levels, and then a Transformer encoder–decoder structure is used for feature matching to obtain preliminary correspondences. Finally, a geometric outlier removal method (GSM) is used to eliminate mismatched points based on the geometric similarity of inliers, resulting in more robust correspondences. Qualitative and quantitative experiments were conducted on multimodal image datasets captured by UAVs; the correct matching rate was improved by 52%, 21%, and 15%, respectively, and the error was reduced by 36% compared to the 3MRS algorithm. A total of 56 experiments were conducted in actual scenarios, with a localization success rate of 91.1%, and the RMSE of UAV positioning was 4.6 m.
In general, path planning for unmanned aerial vehicles (UAVs) is modeled as a challenging optimization problem that is critical to ensuring efficient UAV mission execution. The challenge lies in the complexity and uncertainty of flight scenarios, particularly in three-dimensional scenarios. In this study, one introduces a framework for UAV path planning in a 3D environment. To tackle this challenge, we develop an innovative hybrid gray wolf optimizer (GWO) algorithm, named SDPGWO. The proposed algorithm simplifies the position update mechanism of GWO and incorporates a differential perturbation strategy into the search process, enhancing the optimization ability and avoiding local minima. Simulations conducted in various scenarios reveal that the SDPGWO algorithm excels in rapidly generating superior-quality paths for UAVs. In addition, it demonstrates enhanced robustness in handling complex 3D environments and outperforms other related algorithms in both performance and reliability.
In this work, we propose a geolocation framework for distant ground targets integrating laser rangefinder sensors with multimodal visual servo control. By simulating binocular visual servo measurements through monocular visual servo tracking at fixed time intervals, our approach requires only single-session sensor attitude correction calibration to accurately geolocalize multiple targets during a single flight, which significantly enhances operational efficiency in multi-target geolocation scenarios. We design a step-convergent target geolocation optimization algorithm. By adjusting the step size and the scale factor of the cost function, we achieve fast accuracy convergence for different UAV reconnaissance modes, while maintaining the geolocation accuracy without divergence even when the laser ranging sensor is turned off for a short period. The experimental results show that through the UAV’s continuous reconnaissance measurements, the geolocalization error of remote ground targets based on our algorithm is less than 7 m for 3000 m, and less than 3.5 m for 1500 m. We have realized the fast and high-precision geolocalization of remote targets on the ground under the high-altitude reconnaissance of UAVs.