An assisted positioning method and system

By using a visual reference point-based assisted localization method, and leveraging topological localization relationships and weights, the problem of unstable aircraft localization caused by visual feature impairment or occlusion was solved, achieving stable localization results in complex scenarios.

CN122306059APending Publication Date: 2026-06-30BEIJING AUTOMATION CONTROL EQUIP INST
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
BEIJING AUTOMATION CONTROL EQUIP INST
Filing Date
2024-12-27
Publication Date
2026-06-30

AI Technical Summary

Technical Problem

Existing visual positioning methods are difficult to work reliably in scenarios where the visual features of the target itself are damaged or occluded, resulting in unstable aircraft positioning.

Method used

A visual reference point-based assisted localization method is adopted. By acquiring multiple candidate reference points from the baseline image, a topological localization relationship and weights are established. By comparing the reference points with the actual image, the final localization point is determined, eliminating the dependence on the visual features of the target itself.

Benefits of technology

Achieving stable and reliable target positioning in complex scenarios improves the positioning accuracy and robustness of the aircraft, especially enabling it to work effectively under conditions such as smoke and fog.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122306059A_ABST
    Figure CN122306059A_ABST
Patent Text Reader

Abstract

This invention proposes an assisted positioning method and system. The assisted positioning is achieved through steps such as preprocessing a reference map to select multiple reference point pairs, determining the weights of the topological positioning relationships, real-time processing of the captured image to establish a correspondence between the captured image and the reference points on the reference map, and determining the final positioning point of the target in the captured image. This invention utilizes the visual features of the reference points to locate the target point, thereby eliminating dependence on the target's own visual features and achieving stable and reliable target positioning under complex scene constraints.
Need to check novelty before this filing date? Find Prior Art