基于RGB-D单目视觉的室内场景三维重建

3D reconstruction of indoor scenes using RGB-D monocular vision

针对室内环境单目视觉的室内场景三维重建速度慢的问题,采用华硕Xtion单目视觉传感器获取的室内场景彩色图像和深度图像进行快速三维重建。在图像特征提取上使用ORB特征检测算法,并对比了几种经典特征检测算法在图像匹配中的效率,在图像匹配融合中采用Ransac算法和ICP算法进行点云融合。实现了一种室内简单、小规模的静态环境快速三维重建方法,通过实验验证了该方法有较好的精确性、鲁棒性、实时性和灵活性。

Aiming at the problem of low speed of 3D reconstruction of indoor scenes with monocular vision, the color images and depth images of indoor scenes obtained by ASUS Xtion monocular vision sensor are used for fast 3D reconstruction. The ORB feature detection algorithm is used in image feature extraction, and the efficiency of several kinds of classic feature detection algorithm in image matching is compared. Ransac al- gorithm and ICP algorithm are used for point cloud fusion. Finally, a fast 3D reconstruction method for indoor, simple and small-scale static environment is realized. It has good accuracy, robustness, real-time and flexibility.