基于VSLAM的室内场景重建与虚实遮挡的边缘优化方法
The Method of Edge Optimization for Indoor Scene Reconstruction and Virtual-Real Occlusion Based on VSLAM
-
摘要: 在增强现实环境中, 虚拟物体和真实物体的融合效果经常受到虚实遮挡的影响. 为了提升虚实遮挡效果, 本文提出一种室内场景下基于VSLAM的三维物体稠密重建与分割的方法. 该方法首先利用YOLOv5s和ORB-SLAM2检测和去除环境中的动态特征点, 以便只利用静态特征点构建准确的点云地图. 接着, 使用OPTICS聚类算法约束体素边缘, 并进行网格分割. 本文提出的方法通过结合有符号距离函数形状先验算法对分割后的点云进行预测重建, 从而使分割的物体边缘更加准确. 最后, 在多个数据集上对提出的方法进行检验, 并进行了动态特征点去除和虚实遮挡等实验. 结果表明, 本文的方法可以准确地分割虚拟物体和真实物体的遮挡边缘, 同时保持形状化的重建结果, 使得虚实遮挡效果更加真实和自然.Abstract: In an augmented reality environment, the fusion effect of virtual and real objects is often affected by virtual-real occlusion. To improve the virtual-real occlusion effect, this article proposes a method for dense reconstruction and segmentation of three-dimensional objects in indoor scenes based on VSLAM. This method first uses YOLOv5s and ORB-SLAM2 to detect and remove dynamic feature points in the environment, to build an accurate point cloud map using only static feature points. Then, the OPTICS clustering algorithm is used to constrain the voxel edges and perform mesh segmentation. The method proposed in this article predicts the reconstruction of the segmented point cloud by combining the signed distance function shape prior algorithm, thereby making the edges of the segmented objects more accurate. Finally, the proposed method is tested on multiple datasets and experiments such as dynamic feature point removal and virtual-real occlusion are conducted. The results show that the method of this article can accurately segment the occlusion edges of virtual and real objects, while maintaining the shape of the reconstruction results, making the virtual-real occlusion effect more realistic and natural.