Yineng Li

The unmanned aerial vehicle (UAV) localization method based on global features is a fast and efficient approach for satellite-denied environments. Such methods typically extract global features from aerial images and retrieve matches from a constructed feature database to locate UAVs. However, constructing the feature database requires traversing the entire map, leading to storage redundancy. Moreover, the reference images in the database often have fixed fields of view and orientations, making it difficult to adapt to the changes in aerial images caused by the altitude and attitude changes of the UAV. To address these challenges, this paper explores the uniqueness of semantic instances within the mission region and proposes a UAV localization method based on unique semantic instances. The proposed method first extracts the labels of unique semantic instances from aerial images. These labels are then used to retrieve and match the corresponding feature vectors stored in the database. The location is determined based on the centroid positions of the matched unique semantic instances stored in the feature vectors. Experimental results on both simulation and flight datasets show that the proposed method achieves a localization success rate exceeding 95% in the mission region and remains robust to changes in the attitude and field of view of aerial images. The proposed method requires storing only the categories and locations of the instances, significantly reducing data storage requirements.

The low-altitude economy heavily relies on new carriers represented by unmanned aerial vehicles (UAVs). The localization accuracy of UAVs highly relies on the Global Navigation Satellite System (GNSS), which can be easily affected in low-altitude urban environments, making it difficult to maintain effective localization accuracy. To solve this problem, this paper proposes a UAV autonomous localization method with keypoints on the edges of semantic objects (KESO). Firstly, semantic objects within the working area are selected, and then the latitude, longitude, and altitude of these semantic objects’ keypoints are measured to construct a database. By identifying the semantic objects from aerial images and detecting the edge of the semantic objects, the keypoints of the semantic objects are obtained. Finally, by matching the detected keypoints in the aerial images with the keypoints in the database, the UAV’s position can achieve a high-precision position when satellite signals are blocked in low-altitude urban environments. As verified by real flight data, the results show that the localization error is less than 5 m, and the edges of objects can obtain more accurate keypoints to help UAVs locate more accurately. This paper can provide a reference for UAV localization in the urban environments of the low-altitude economy.