3D Reconstruction Using Interval Methods on the Kinect Device Coupled with an IMU

The principle behind VSLAM applications like 3D object reconstruction or indoor mapping is to estimate the spatial transformation between two large clouds of points, which represent two poses of the same scene. They can further be processed to obtain detailed surfaces. Since its introduction in 1992, the standard algorithm for finding the alignment between two point clouds is ICP (Iterative Closest Point) and its variants, combined with RANSAC (RANdom SAmple Consensus). This paper presents a new approach using interval analysis. The idea is to define large intervals for the transformation parameters between the poses then to successively contract those intervals using the equations of the transformation of corresponding points between the poses. To contract those intervals faster, we added an IMU (Inertial Measurement Unit) to our system so the initial intervals of the parameters are already small before applying the contractions. We implemented our algorithm using the middleware ROS (Robot Operating System) and stated our performances.

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

[2]  Gérard G. Medioni,et al.  Object modelling by registration of multiple range images , 1992, Image Vis. Comput..

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

[4]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

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

[6]  Luc Jaulin,et al.  Applied Interval Analysis , 2001, Springer London.

[7]  Wolfram Burgard,et al.  Robust Monte Carlo localization for mobile robots , 2001, Artif. Intell..

[8]  Wolfram Burgard,et al.  Improving Simultaneous Mapping and Localization in 3D Using Global Constraints , 2005, AAAI.

[9]  Simon Lacroix,et al.  Vision-Based SLAM: Stereo and Monocular Approaches , 2007, International Journal of Computer Vision.

[10]  Nathan P. Koenig,et al.  Toward real-time human detection and tracking in diverse environments , 2007, 2007 IEEE 6th International Conference on Development and Learning.

[11]  Kurt Konolige,et al.  FrameSLAM: From Bundle Adjustment to Real-Time Visual Mapping , 2008, IEEE Transactions on Robotics.

[12]  Jean-Michel Morel,et al.  ASIFT: A New Framework for Fully Affine Invariant Image Comparison , 2009, SIAM J. Imaging Sci..

[13]  Luc Jaulin,et al.  Image Shape Extraction using Interval Methods , 2009 .

[14]  Christopher Hunt,et al.  Notes on the OpenSURF Library , 2009 .

[15]  Dieter Fox,et al.  RGB-D Mapping: Using Depth Cameras for Dense 3D Modeling of Indoor Environments , 2010, ISER.

[16]  Cyrill Stachniss,et al.  Hierarchical optimization on manifolds for online 2D and 3D mapping , 2010, 2010 IEEE International Conference on Robotics and Automation.

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