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.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    UAV Localization Method with Keypoints on the Edges of Semantic Objects for Low-Altitude Economy


    Beteiligte:
    Yineng Li (Autor:in) / Qinghua Zeng (Autor:in) / Chen Shao (Autor:in) / Peng Zhuo (Autor:in) / Bowen Li (Autor:in) / Kecheng Sun (Autor:in)


    Erscheinungsdatum :

    2024




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Unbekannt




    LOCALIZATION BASED ON SEMANTIC OBJECTS

    KAISER NATHANIEL JON / KROEGER TILL / STUMM ELENA STEPHANIE | Europäisches Patentamt | 2024

    Freier Zugriff

    LOCALIZATION BASED ON SEMANTIC OBJECTS

    KAISER NATHANIEL JON / KROEGER TILL / STUMM ELENA STEPHANIE | Europäisches Patentamt | 2022

    Freier Zugriff

    END-TO-END SIGNALIZED INTERSECTION TRANSITION STATE ESTIMATOR WITH SCENE GRAPHS OVER SEMANTIC KEYPOINTS

    CHEN KUN-HSIN / GONG PEIYAN / PILLAI SUDEEP et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    End-to-end signalized intersection transition state estimator with scene graphs over semantic keypoints

    CHEN KUN-HSIN / GONG PEIYAN / PILLAI SUDEEP et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    PEDESTRIAN BEHAVIOR PREDICTION WITH 3D HUMAN KEYPOINTS

    SHI XINWEI / LAN TIAN / STROUD JONATHAN CHANDLER et al. | Europäisches Patentamt | 2023

    Freier Zugriff