Event camera based space target ranging method and system

By capturing asynchronous event streams of space debris using an event camera, combining gravitational acceleration characteristics, extracting apparent acceleration, and embedding it into the gravitational field equations, the scale ambiguity and motion blur problems of monocular vision in space target monitoring are solved, achieving high-precision absolute ranging.

CN122362399APending Publication Date: 2026-07-10WUHAN UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
WUHAN UNIV
Filing Date
2026-03-17
Publication Date
2026-07-10

AI Technical Summary

Technical Problem

Existing monocular vision ranging technology suffers from scale ambiguity and motion blur in space target monitoring, making it difficult to achieve high-precision ranging, especially in high-speed dynamic scenes and complex noise backgrounds.

Method used

An event-based camera-based ranging method is employed, leveraging its microsecond-level temporal resolution and high dynamic range, combined with the gravitational acceleration characteristics of space debris. By extracting the apparent acceleration features of the image plane and embedding them into the gravitational field equations, the absolute distance is decoupled.

Benefits of technology

It achieves high-precision and robust monocular ranging without relying on prior target size, overcomes the scale recovery problem, and enhances the stability and consistency of the system in complex environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122362399A_ABST
    Figure CN122362399A_ABST
Patent Text Reader

Abstract

This invention discloses a spatial target ranging method and system based on an event camera, aiming to solve the problems of scale loss and motion blur in the monitoring of unknown spatial targets using existing monocular vision. The method utilizes a monocular event camera to capture high-frequency asynchronous event streams of space debris. First, it extracts the apparent acceleration features reflecting trajectory curvature through a spatiotemporal fusion attention module. Then, it constructs a physical constraint layer embedded with dynamic equations, using known gravitational acceleration as the absolute scale anchor point to establish a geometric mapping between it and the apparent acceleration. Finally, a neural network jointly calculates the absolute distance and three-dimensional velocity vector that conform to physical laws. This invention does not require prior knowledge of the target size and achieves high-precision, robust monocular absolute ranging in complex environments.
Need to check novelty before this filing date? Find Prior Art