基于多级滤波与深度学习的气辉重力波检测方法和系统
By combining multi-level filtering with deep learning, the problem of noise interference in gasglow imager images was solved, enabling automatic identification of gravity wave features and accurate calculation of parameters, thus meeting the needs of batch processing of large-scale observation data.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-06-22
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies are insufficient to effectively remove star point interference and background noise from images acquired by gasglow imagers, and they also struggle to automatically identify and analyze the fluctuation regions of gravity waves, thus failing to meet the requirements for batch processing of large-scale observation data.
A multi-level filtering and deep learning approach is adopted, including median filtering, Gabor filtering, convolutional neural networks and cross-correlation analysis, to remove noise and extract gravity wave features. The wavelength, propagation direction and group velocity of gravity waves are calculated by Fourier transform and cross-correlation matching.
It achieves fully automated, high-precision detection of the gravity wave region, provides complete physical parameters of gravity waves, and meets the needs of batch scientific analysis of historical gasglow data.
Smart Images
Figure CN122416282A_ABST