基于KinectFusion的室内场景平面结构重建

系统仿真学报 ›› 2015, Vol. 27 ›› Issue (10): 2239-2245.

• 建模与仿真理论及方法 • 上一篇下一篇

基于KinectFusion的室内场景平面结构重建

蔡晨贾农^1,2, 施逸飞^1,2, 徐凯^1,2, 党岗¹

1.国防科学技术大学,长沙 410073;
2.中科院深圳先进技术研究院可视计算研究中心,深圳 518055

收稿日期:2015-06-14 修回日期:2015-07-23 出版日期:2015-10-08 发布日期:2020-08-07
作者简介:蔡晨贾农(1991-),男,内蒙古呼和浩特,蒙古族,硕士生,研究方向为计算机图形学、三维重建;施逸飞(1991-),男,江西萍乡,博士生,研究方向为计算机图形学、室内场景分析。
基金资助:
国家自然科学基金(61202333, 61272334)

Planar Structure Reconstruction for Indoor Scenes with KinectFusion

Cai Chenjianong^1,2, Shi Yifei^1,2, Xu Kai^1,2, Dang Gang¹

1. National University of Defence Technology, Changsha 410073, China;
2. Visual Computing Center, Shenzhen Institutes of Advanced Technology, Shenzhen 518055, China

Received:2015-06-14 Revised:2015-07-23 Online:2015-10-08 Published:2020-08-07

摘要/Abstract

摘要： 基于KinectFusion的在线扫描与重建技术极大改进了基于消费级深度摄像机的实时室内场景重建。由于目前多数深度摄像机的深度分辨率的限制,使用KinectFusion扫描获得的三维模型数据的重建质量不能满足要求。特别是对室内场景模型中常见的平面结构。这些平面结构往往可以确定室内环境的主要结构。以基于KinectFusion扫描获得室内场景点云数据为基础,提出了一种新的点云分割方法。该方法可准确识别和提取点云数据中的平面结构,并对其进行三维重建。

关键词: KinectFusion, 平面检测, 三维表面重建, 点云分割

Abstract: Online scanning and reconstruction with KinectFusion has greatly improved real-time reconstruction of indoor scenes with consumer depth camera. However, due to the limitation of depth resolution of current depth cameras, the quality of reconstructed scenes is in general unsatisfactory. This is especially true for planar structures which are commonly seen in indoor scenes and important in defining the major structure of an indoor room. A novel method was proposed for extracting and reconstructing planar structures from point clouds of indoor scenes scanned acquired by KinectFusion.

Key words: KinectFusion, plane detection, 3D surface reconstruction, point cloud segmentation

中图分类号:

TP391.9

蔡晨贾农, 施逸飞, 徐凯, 党岗. 基于KinectFusion的室内场景平面结构重建[J]. 系统仿真学报, 2015, 27(10): 2239-2245.

Cai Chenjianong, Shi Yifei, Xu Kai, Dang Gang. Planar Structure Reconstruction for Indoor Scenes with KinectFusion[J]. Journal of System Simulation, 2015, 27(10): 2239-2245.

参考文献

[1] Newcombe R A, Izadi S, Hilliges O, et al. KinectFusion: Real-time dense surface mapping and tracking[C]//Mixed and augmented reality (ISMAR), 2011 10th IEEE international symposium on. USA: IEEE, 2011: 127-136.
[2] Besl P J, McKay N D. Method for registration of 3-D shapes[C]// Robotics-DL tentative. USA: International Society for Optics and Photonics, 1992: 586-606.
[3] Curless B, Levoy M.A volumetric method for building complex models from range images[C]// Proceedings of the 23rd annual conference on Computer graphics and interactive techniques. USA: ACM, 1996: 303-312.
[4] Nießner M, Zollhöfer M, Izadi S, et al. Real-time 3d reconstruction at scale using voxel hashing[J]. ACM Transactions on Graphics (TOG), 2013, 32(6): 169.
[5] Schnabel R, Wahl R, Klein R.Efficient RANSAC for point‐cloud shape detection [C]// Computer graphics forum. USA: Blackwell Publishing Ltd, 2007, 26(2): 214-226.
[6] Mattausch O, Panozzo D, Mura C, et al. Object detection and classification from large‐scale cluttered indoor scans[J]. Computer Graphics Forum, 2014, 33(2): 11-21.
[7] Rabbani T, van den Heuvel F, Vosselmann G. Segmentation of point clouds using smoothness constraint[J]. International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 2006, 36(5): 248-253.
[8] Golovinskiy A, Funkhouser T.Min-cut based segmentation of point clouds[C]// Computer Vision Workshops (ICCV Workshops), 2009 IEEE 12th International Conference on. USA: IEEE, 2009: 39-46.
[9] Johnson-Roberson M, Bohg J, Björkman M, et al. Attention-based active 3D point cloud segmentation[C]// Intelligent Robots and Systems (IROS), 2010 IEEE/RSJ International Conference on. USA: IEEE, 2010: 1165-1170.
[10] Monszpart A, Mellado N, Brostow G, et al. RAPter: Rebuilding man-made scenes with regular arrangements of planes[J]. ACM Transactions on Graphics(TOG)- Proceedings of ACM SIGGRAPH (S0730-0301), 2015, 34(4): 87-99.
[11] Papon J, Abramov A, Schoeler M, et al. Voxel cloud connectivity segmentation-supervoxels for point clouds[C]// Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on. USA: IEEE, 2013: 2027-2034.
[12] Boykov Y Y, Jolly M P.Interactive graph cuts for optimal boundary & region segmentation of objects in ND images[C]// Computer Vision, 2001. ICCV 2001, Proceedings. Eighth IEEE International Conference on. USA: IEEE, 2001, 1: 105-112.
[13] Azernikov S, Fischer A.Surface reconstruction of freeform objects based on hierarchical space decomposition[J]. International Journal of Shape Modeling, 2003, 9(2): 177-190.
[14] Wu S, Sun W, Long P, et al. Quality-driven poisson-guided autoscanning[J]. ACM Transactions on Graphics (SIGGRAPH Asia)(S0730-0301), 2014, 33(6): 1-12.

基于KinectFusion的室内场景平面结构重建

Planar Structure Reconstruction for Indoor Scenes with KinectFusion

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价