Infrared moving platform small target tracking method based on complementary correlation filter

By using complementary correlation filters, image matching, inter-frame differential method and Kalman filtering in the infrared dynamic platform small target tracking, the problem of weak target features, frequent occlusion and rapid background motion is solved, and the infrared small target tracking with high robustness and stability is achieved.

CN119722737AActive Publication Date: 2025-03-28BEIJING INST OF TECH
7 Cites 0 Cited by

Patent Information

Application Number
CN202411770100.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-04
Publication Date
2025-03-28
Estimated Expiration
2044-12-04

AI Technical Summary

Technical Problem

In infrared dynamic platform small target tracking, there are problems of weak target characteristics, frequent occlusion and rapid background movement, which makes it difficult for the tracking algorithm to work stably.

Method used

A method based on complementary correlation filter is adopted, combined with images matching, inter-frame differential method and Kalman filtering and other technologies to achieve stable infrared dynamic platform small target tracking. The specific steps include calculating the target position response map using complementary correlation filters, judging the occlusion situation, correcting background motion using a multi-strategy joint image matching method, detecting the moving target through the inter-frame differential method, and using a Kalman filter to predict the target motion state.

Benefits of technology

It improves the anti-occlusion ability and background interference suppression ability, achieves accurate prediction and tracking of target positions, and enhances the robustness and stability of infrared small target tracking.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses an infrared moving platform small target tracking method based on a complementary correlation filter, and belongs to the field of remote sensing video target intelligent processing, and the method comprises the steps: S1, calculating a position response diagram of a target based on the complementary correlation filter, judging whether the target is shielded or not, and if the target is not shielded, executing the step S2; if yes, using the position with the maximum response value as the position of the target; otherwise, performing subsequent steps; s2, adopting a multi-strategy combined image matching method to carry out registration on a front frame image and a rear frame image; s3, performing moving target detection by adopting an inter-frame difference method to obtain a moving target set; s4, predicting the motion state of the target by adopting a Kalman filter, and taking the target closest to the Kalman filter prediction position in the motion target set as a final target; the complementary correlation filter provided by the invention has strong small target tracking and anti-shielding capabilities under a motion platform, and can effectively improve the precision of infrared small target tracking.
Need to check novelty before this filing date? Find Prior Art