Ground 3D Object Reconstruction Based on Multi-View 3D Occupancy Network using Satellite Remote Sensing Image

It is challenging to achieve high accuracy and rich details three-dimensional (3D) reconstruction of ground object using satellite remote sensing image (RSI). A 3D reconstruction method is proposed to address this problem based on multi-view 3D occupancy network. The domain adaptive multi-view image obtained by pretreatment is input into the depth residual network to extract perceptual features at first. The occupancy probability of objects at different coordinates in 3D space is obtained by combining spatial probability network with definition balance strategy. Then, the isosurface is extracted to obtain the 3D mesh of the object, and the reconstruction result is given scale by combining the attitude estimation and the original RSI parameter information. Experiments are carried out on a testing dataset composed of hundreds of object image pairs. The experimental results show that the proposed method for satellite RSI has better accuracy than the typical single-view and multi-view reconstruction methods.

1. Introduction

With the gradual maturity of satellite stereo imaging capability, three-dimensional (3D) reconstruction based on satellite remote sensing image (RSI) has a wide range of needs in the field of people's livelihood and national defense. 3D reconstruction method of traditional satellite RSI need to be achieved by using satellite parameters. Only 2.5D elevation maps, that lack a detailed description of the overall object structure, can be obtained when stringent stereo conditions are met [1]. Meanwhile, the resolution of satellite RSI is low, which is mostly used for terrain reconstruction. For the common ground targets such as planes, ships and buildings, it is difficult to achieve high accuracy and rich details 3D reconstruction.