A Space Target Detection and Tracking Method

CN122265337APending Publication Date: 2026-06-23XIAN EURASIA UNIVERSITY

Patent Information

Authority / Receiving Office: CN · China
Patent Type: Applications(China)
Current Assignee / Owner: XIAN EURASIA UNIVERSITY
Filing Date: 2026-05-26
Publication Date: 2026-06-23

AI Technical Summary

Technical Problem

Existing technologies for space target detection and tracking suffer from problems such as noise interference, poor tracking window adaptability, easy coordinate transformation errors, and difficulty in recovering lost targets, resulting in insufficient detection accuracy and tracking robustness.

Method used

A phased detection and tracking method is adopted, including a global detection phase and a local tracking phase. The target is distinguished from background noise by multi-frame statistics and angle deviation filtering. A dynamic search box is designed to adapt to changes in target size, and the coordinate transformation logic is optimized. A closed-loop re-detection mechanism is introduced.

Benefits of technology

It improves the noise resistance, tracking accuracy and robustness of space target detection, can adapt to changes in target size, quickly recover tracking, and achieve high-precision and high-robustness detection and tracking.

✦ Generated by Eureka AI based on patent content.

Smart Images

Figure CN122265337A_ABST

Patent Text Reader

Abstract

This invention discloses a spatial target detection and tracking method, involving computer vision target detection and tracking technology. It solves the technical problems of existing methods, such as noise interference, poor tracking window adaptability, easy coordinate transformation errors, and slow target loss recovery. This invention divides the detection process of spatial point and area targets into a global detection stage and a local tracking stage. In the global detection stage, candidate targets are extracted through multi-frame statistics and angle deviation filtering. In the local tracking stage, real-time tracking of the target neighborhood is achieved based on a dynamic search box, and tracking stability is improved through morphological processing, size filtering, and unified coordinate transformation. Simultaneously, a closed-loop mechanism is designed to trigger global detection upon tracking failure, ensuring the accuracy and continuity of point and area target detection and tracking throughout the entire process. This invention can be widely applied to scenarios such as star detection and small target tracking.

Need to check novelty before this filing date? Find Prior Art