An unmanned aerial vehicle target positioning method based on visual fusion and Kalman filtering

By employing visual fusion and Kalman filtering in UAV target localization, a northeast-sky coordinate system was established and combined with the field of view information of a monocular camera. This solved the problems of unclear position acquisition and complex calculation in UAV target localization, and achieved high-precision and high-stability target localization.

CN120778118BActive Publication Date: 2026-05-01NORTHEASTERN UNIV CHINA +1
View PDF 4 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
NORTHEASTERN UNIV CHINA
Filing Date
2025-08-11
Publication Date
2026-05-01

AI Technical Summary

Technical Problem

Existing UAV target positioning technologies suffer from problems such as unclear location acquisition, complex calculation process, unintuitive camera focal length information, and lack of filtering optimization, resulting in insufficient positioning accuracy and reliability.

Method used

A method based on visual fusion and Kalman filtering is adopted. By establishing a northeast-north-sky coordinate system and combining the field of view of the monocular camera and the target image position, the position of the target relative to the UAV is calculated, and the Kalman filter is used to filter and optimize the target position.

Benefits of technology

It improves the accuracy and stability of UAV target positioning, simplifies the calculation process, reduces data fluctuations, and enhances the reliability and adaptability of positioning.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120778118B_ABST
    Figure CN120778118B_ABST
Patent Text Reader

Abstract

The application belongs to the technical field of unmanned aerial vehicles, and relates to an unmanned aerial vehicle target positioning method based on visual fusion and Kalman filtering, which comprises the following steps: establishing a northeast celestial coordinate system with the takeoff point of the unmanned aerial vehicle as the origin, the positive east as the x-axis, the positive north as the y-axis and the zenith as the z-axis; converting the position of the unmanned aerial vehicle from a WGS-84 coordinate system to the northeast celestial coordinate system; determining the field angle data of the monocular camera of the unmanned aerial vehicle and the position of the target center point in the image; combining the position of the target center point in the image, the height of the unmanned aerial vehicle from the ground and the field angle information of the monocular camera to calculate the target position of the target center point relative to the unmanned aerial vehicle; converting the target position into three-dimensional coordinates in the northeast celestial coordinate system; and completing the unmanned aerial vehicle target positioning after filtering the target position based on Kalman filtering. The method has the beneficial effect of realizing high-precision, high-stability and high-adaptability unmanned aerial vehicle target positioning.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Image and navigation information based unmanned aerial vehicle (UAV) ground target positioning method

    CN108845335A

  • Ground target positioning method and system based on monocular vision of unmanned aerial vehicle

    CN112116651A

  • Target indication method based on MEMS attitude sensor and operation device

    CN119103931A

  • Indoor positioning method and system based on dynamic mode switching and data fusion

    CN119984268A