A Triangular Texture Mapping for 3D Modeling with Kinect

3D modeling is a hot topic in the field of computer vision. With the appearance of the RGB-D camera, the 3D modeling becomes more convenient. However, during the modeling procedure, it will suffer from the error of pair-wise views registration, especially with the off-shelf sensor. In this paper we attempt to model the object in 3D space by using the Kinect sensor to scan the object on a rotating platform. To ensure the feasibility and modeling accuracy, we remove the non-overlapping points between adjacent frame cloud points during the pair-wise views registration, and propose a triangular UV mapping method to map the texture on the surface of object to the 3D model. Experimental results show that our solution could reconstruct the 3D model with high accuracy.

[1]  Andrew W. Fitzgibbon,et al.  KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera , 2011, UIST.

[2]  Lijun Zhao,et al.  Indoor objects 3D modeling based on RGB-D camera for robot vision , 2015, 2015 International Conference on Fluid Power and Mechatronics (FPM).

[3]  John J. Leonard,et al.  Kintinuous: Spatially Extended KinectFusion , 2012, AAAI 2012.

[4]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Daniel Cohen-Or,et al.  ℓ1-Sparse reconstruction of sharp point set surfaces , 2010, TOGS.

[6]  Zoltan-Csaba Marton,et al.  On fast surface reconstruction methods for large and noisy point clouds , 2009, 2009 IEEE International Conference on Robotics and Automation.

[7]  Andrew W. Fitzgibbon,et al.  KinectFusion: Real-time dense surface mapping and tracking , 2011, 2011 10th IEEE International Symposium on Mixed and Augmented Reality.

[8]  Xiaoming Wang,et al.  Fast 3D-Object Modeling with Kinect and Rotation Platform , 2015, 2015 Third International Conference on Robot, Vision and Signal Processing (RVSP).

[9]  Michael M. Kazhdan,et al.  Poisson surface reconstruction , 2006, SGP '06.

[10]  Ming-Ting Sun,et al.  3D object modeling with a Kinect camera , 2014, Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific.

[11]  Kok-Lim Low.  Linear Least-Squares Optimization for Point-to-Plane ICP Surface Registration , 2004 .

[12]  Yi Lin,et al.  An improved ICP algorithm for kinect point cloud registration , 2016, 2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD).

[13]  Marc Levoy,et al.  Efficient variants of the ICP algorithm , 2001, Proceedings Third International Conference on 3-D Digital Imaging and Modeling.

[14]  Registration of point clouds from kinect with congruent spheres , 2015, 2015 8th International Congress on Image and Signal Processing (CISP).

[15]  Marsette Vona,et al.  Moving Volume KinectFusion , 2012, BMVC.

[16]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[17]  Andrea Censi,et al.  An ICP variant using a point-to-line metric , 2008, 2008 IEEE International Conference on Robotics and Automation.

[18]  Nico Blodow,et al.  Towards 3D object maps for autonomous household robots , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.