MVSNet在空间目标三维重建中的应用  

Application of MVSNet in 3D Reconstruction of Space Objects

作　　者：王思启 张家强 李丽圆 李潇雁 陈凡胜[1,2] Wang Siqi;Zhang Jiaqiang;Li Liyuan;Li Xiaoyan;Chen Fansheng(Key Laboratory of Intelligent Infrared Perception,Shanghai Institute of Technical Physics,Chinese Academy of Sciences,Shanghai 200083,China;Hangzhou Institute for Advanced Study,University of Chinese Academy of Sciences,Hangzhou 310024,Zhejiang,China;University of Chinese Academy of Sciences,Beijing 100049,China)

机构地区：[1]中国科学院上海技术物理研究所中国科学院智能红外感知重点实验室,上海200083 [2]国科大杭州高等研究院,浙江杭州310024 [3]中国科学院大学,北京100049

出　　处：《中国激光》2022年第23期170-179,共10页Chinese Journal of Lasers

基　　金：国家自然科学基金(61975222);中国科学院地球微卫星热红外光谱仪项目(XDA19010102)。

摘　　要：对空间目标进行三维重建能够为在轨服务卫星提供服务对象的结构信息,是提高系统自主性的关键技术。受空间目标的结构对称性以及成像非朗伯特性的影响,传统的重建方法存在特征点匹配错误或特征点匹配不足的问题,重建精度低。针对该问题,提出了一种基于MVSNet深度学习网络实现空间目标三维重建的方法,利用深度学习提取图像高层语义,提高了立体匹配的鲁棒性。首先,基于空间目标的成像特点,分析了模型的几何结构和材质对重建结果的影响,设计了搭建在Blender平台上的空间目标多视图采集系统。然后,基于MVSNet深度学习网络,采用多尺度卷积充分提取了图像的深度特征,并通过编码解码结构融合和规整上下文信息进行了立体匹配,有效解决了传统方法重建卫星的弱纹理、反射、重复纹理等区域时对特征点的高度依赖问题。最后通过残差网络解决了多次卷积造成的边界过平滑问题,进一步提升了重建效果。实验结果表明,所设计的重建模型的平均准确度误差为0.449 mm,平均完整度误差为0.379 mm,误差综合评价为0.414 mm,精度较经典开源软件COLMAP提升了20%。该方法为空间操作自动化提供了技术参考,进一步推动了三维重建在相关领域中的应用。Objective 3D reconstruction of space targets can provide prior structural information for space services,which is a key technology for improving system autonomy.Conventional 3D reconstruction methods rely on handcrafted features to recover the 3D structure of objects by dense matching.Therefore,affected by the symmetrical structure and non-Lambert imaging of spatial targets,conventional 3D reconstruction methods often suffer from mismatching and insufficient matches of feature points,resulting in a low reconstruction accuracy.In recent years,with continuous developments in deep learning technology,convolution neural networks(CNNs)have been widely used in computer vision.Compared with the handcrafted features used by conventional 3D reconstruction methods,the deep features extracted by CNNs can introduce high-level semantics of images for more robust matching.Inspired by this,a 3D reconstruction method based on MVSNet for space targets is proposed.This algorithm organically applies CNNs with different structures to improve the accuracy and completeness of 3D reconstruction.We hope that our basic strategy and findings will be beneficial to the 3D reconstruction of space targets.Methods The space-target 3D-reconstruction algorithm model(Fig.1)is described as follows.First,in view of the imaging characteristics of a space target,the influence of the geometric structure and material of the model on reconstruction results is analyzed,and a multi-view acquisition system for space targets based on the Blender platform is designed.Subsequently,deep visual image features are fully extracted via multi-scale convolution based on MVSNet.The coder and decoder are then used to gather and regularize the spatial context information for stereo matching,which effectively avoids the heavy dependence of conventional methods on the feature points in the reconstructions of low-textured,reflective,and repetitive texture regions.Finally,the residual network is used to solve the boundary smoothing problem caused by the multiple convolutio

关 键 词：遥感 深度学习 多视图 空间目标三维重建 卷积神经网络 编码解码结构 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]