High-precision positioning method and system based on multi-source information fusion

By combining visual inertial navigation and satellite image matching with a multi-source information fusion method of real GPS sensors, the problem of insufficient accuracy of UAV positioning in complex environments was solved, and stable and high-precision positioning effects were achieved.

CN120685072APending Publication Date: 2025-09-23天津(滨海)人工智能创新中心
View PDF 0 Cites 5 Cited by

Patent Information

Application Number
CN202510966037.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-07-14
Publication Date
2025-09-23

AI Technical Summary

Technical Problem

Existing drone positioning technology has insufficient positioning accuracy in complex environments, especially when the GNSS signal fails intermittently, the positioning accuracy drops sharply. In addition, the traditional multi-sensor fusion system has poor robustness and cannot fully utilize the advantages of each positioning technology.

Method used

The odom positioning information of the UAV's posture is obtained by using a visual inertial navigation unit. The target image is matched from the satellite image library using a global feature extraction and similarity algorithm. The pixel coordinates are converted to geographic coordinates using a local feature matching algorithm. After the initial fusion, the real GPS sensor data is combined for a secondary fusion to achieve high-precision positioning of multi-source information.

Benefits of technology

It ensures stable positioning capabilities in complex environments, suppresses error accumulation of visual inertial data and satellite image prediction data in dynamic environments, significantly improves positioning accuracy, and provides stable navigation and precise operation capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120685072A_ABST
    Figure CN120685072A_ABST
Patent Text Reader

Abstract

The invention provides a high-precision positioning method and system based on multi-source information fusion. The high-precision positioning method comprises the following steps: acquiring the omm positioning information of the pose of an unmanned aerial vehicle in real time based on a visual inertial navigation unit; a global feature extraction algorithm is combined with a similarity algorithm, and a target satellite image matched with the airborne image of the unmanned aerial vehicle is selected from a satellite image library; using a local feature matching algorithm to combine with the geographic coordinates of the target satellite image to obtain GPS predicted positioning coordinates; fusing the odom positioning information and the GPS predicted positioning coordinates by using a global fusion technology to obtain preliminarily fused odom positioning information; according to the method, secondary fusion is carried out on the basis of GPS positioning data obtained by a real GPS sensor in combination with the preliminarily fused odom positioning information to obtain final odom positioning information, and through a double fusion strategy, the advantages of a multi-source positioning technology are fully integrated, and the positioning accuracy is improved.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Cited By

  • Unmanned aerial vehicle positioning method and system, unmanned aerial vehicle and medium

    CN120869106A

  • Urban canyon positioning method and system integrating GNSS, vision and low-orbit satellites

    CN121254316A

  • Vision and satellite navigation fused unmanned aerial vehicle inspection accurate positioning method and device

    CN121594854A

  • Unmanned aerial vehicle inspection precision positioning method and device fusing vision and satellite navigation

    CN121594854B

  • Unmanned aerial vehicle GPS-free navigation and positioning method based on image AI matching

    CN122130074A