公开(公告)号：US12175633B1

公开(公告)日：2024-12-24

申请号：US18763894

申请日：2024-07-03

Applicant: Chengdu University of Technology

Inventor： Guangle Yao ,  Honghui Wang ,  Wenlong Zhou ,  Wei Zeng ,  Chen Wang ,  Ruijia Li ,  Xiaoyu Xu ,  Jun Li ,  Siyuan Sun

IPC: G06T5/60 ,  G01S13/88 ,  G06T5/50 ,  G06T11/00

Abstract: A method of enhancing an abnormal area of a ground-penetrating radar image based on hybrid-supervised learning includes the steps of: building a database including a real image set, a simulation image set and a simulation image label set; adopting a generative adversarial network; processing semi-supervised training and unsupervised training alternately to obtain a trained model, then inputting a real radar image with abnormal area that needs to be enhanced into the model and processing through the generative network to output an abnormal-area-enhanced image. The method overcomes the problems of differences in characteristics between simulated images and real images, and low utilization efficiency of real image information by unsupervised methods, and improves the utilization efficiency of the enhanced network for real image information, the saliency of abnormal areas on real images, and the generalization ability of the enhanced network, therefore effectively enhances the significance of abnormal areas in ground-penetrating radar images.

公开(公告)号：US11768982B1

公开(公告)日：2023-09-26

申请号：US18116877

申请日：2023-03-03

Applicant: Chengdu University of Technology

Inventor： Jun Li ,  Zhengwei Xu ,  Xuben Wang ,  Rui Wang ,  Shengxian Liang

IPC: G06F30/27 ,  G06F111/04

CPC classification number: G06F30/27 ,  G06F2111/04

Abstract: Disclosed are a hybrid density abrupt interface inversion method based on machine learning constraints. The inversion method includes constructing an initial basin interface and randomly generating a disturbed basin interface data set; obtaining a basin interface data set through Hadamard product operation on the initial basin interface and the disturbed basin interface data set; obtaining a high-resolution density interface model data set through filling the basin interface data set with advanced functions; performing forward calculation to obtain a simulated gravity data set; carrying out mathematical transformation on the simulated gravity data set and weighting to obtain a low-resolution migration density interface model data set; optimizing a migration model-based deep learning network and mapping to obtain a high-resolution constrained density interface prior model; and constructing a stable nonlinear loss function and performing regularization inversion to obtain a high-resolution density interface model.