Moving target detection method and device, equipment and medium
By combining sub-aperture segmentation and back projection imaging with deep learning semantic segmentation technology, the defocusing and information disconnection problems of moving target detection under long synthetic aperture conditions are solved, achieving high-precision pixel-level detection and echo domain signal inversion, which is suitable for moving target detection in single-channel systems.
Patent Information
- Application Number
- CN202511776790.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-28
- Publication Date
- 2026-02-17
AI Technical Summary
Under long synthetic aperture time observation conditions, moving target detection faces serious defocusing and positional shift problems. Existing methods are unable to achieve high-precision detection, and there is a lack of effective correlation mechanism between echo domain and image domain detection, resulting in insufficient detection accuracy and information disconnect.
A processing framework combining sub-aperture segmentation and back projection imaging is adopted, and deep learning semantic segmentation technology is introduced. By performing sub-aperture segmentation and image sequence processing on full aperture data, pixel-level accurate detection and cross-domain information inversion are achieved. Target segmentation and echo signal inversion are performed in conjunction with a deep learning model.
It significantly improves the accuracy and signal-to-noise ratio of moving target detection, achieves pixel-level precise segmentation and accurate positioning of echo domain signals, reduces system complexity, is suitable for single-channel systems, and is adaptable to moving target detection in various scenarios.