Target 3D Reconstruction Technique Based on ISAR Image Sequence
It is crucial for technologies such as target recognition and interpretation,as well as space target monitoring to obtain three-dimensional information of targets from inverse synthetic aperture radar(ISAR)image sequences.This paper researches the feature extraction,matching and 3D reconstruction technique for the scattering points,achieves the 3D reconstruction for targets based on the ISAR image sequences.Firstly,the feature matching algorithm for local feature based transformer(LoFTR)is used to extract the associated position information of the target strong scattering points.The horizontal and vertical coordinate information of the target is obtained through the coarse matching and fine matching,which generates an observation matrix,Then,the three-dimen-sional coordinate information of the target's strong scattering points is obtained through the orthogonal decomposition,and the shape and structure of the target are reconstructed,achieving a good reconstruction result through the fusion of reconstruction results.Fi-nally,the three-dimensional position and shape reconstruction results of the target's strong scattering points are obtained by processing the continuous ALOS satellite images.The reconstruction results show that this method can effectively reconstruct the three-dimen-sional position and shape information of the target from two-dimensional multi-angle ISAR images.
NETL
NSTL
万方数据
