Extracting Plücker Line and Their Relations for 3D Reconstruction of Indoor Scene

The structure line is an important clue for understanding indoor space. Unfortunately, in the context of indoor scene, very little structural data is available due to occlusion. To address this issue, this paper proposes to extract structural lines and analyze their relations to obtain the structure lines, which are continuous, anti-occlusion, able to reconstruct indoor space. In this paper, Plucker line is used to express the lines in 3D indoor scene. And then it studies the properties and the benefits of using Plucker line. For the first time, a new strategy is suggested to maintain the integrity of indoor space, which uses the extracted high confidence lines to infer the properties of other lines. Experimental results show that our methods have many advantages in obtaining a complete 3D interior structure line, which resists most occlusion in near ground.

[1]  Václav Skala.  Plücker Coordinates and Extended Cross Product for Robust and Fast Intersection Computation , 2016, CGI.

[2]  Alexandre Hostettler,et al.  ORBSLAM-Based Endoscope Tracking and 3D Reconstruction , 2016, CARE@MICCAI.

[3]  Horst Bischof,et al.  Efficient 3D scene abstraction using line segments , 2017, Comput. Vis. Image Underst..

[4]  Danping Zou,et al.  StructSLAM: Visual SLAM With Building Structure Lines , 2015, IEEE Transactions on Vehicular Technology.

[5]  Franz Leberl,et al.  Detection ellipses by finding lines of symmetry in the images via an hough transform applied to straight lines , 2001, Image Vis. Comput..

[6]  B. Espiau,et al.  Revisiting Plücker Coordinates in Vision-Based Control , 2002 .

[7]  Andrew Zisserman,et al.  Feature Based Methods for Structure and Motion Estimation , 1999, Workshop on Vision Algorithms.

[8]  Chenglu Wen,et al.  Preproessing and modeling for visual-based 3D indoor scene reconstruction , 2013, 2013 8th International Conference on Computer Science & Education.

[9]  Stephen Mann,et al.  Geometric algebra for computer science - an object-oriented approach to geometry , 2007, The Morgan Kaufmann series in computer graphics.

[10]  Kaigui Bian,et al.  Multi-Story Indoor Floor Plan Reconstruction via Mobile Crowdsensing , 2016, IEEE Transactions on Mobile Computing.

[11]  Jitendra Malik,et al.  Indoor Scene Understanding with RGB-D Images: Bottom-up Segmentation, Object Detection and Semantic Segmentation , 2015, International Journal of Computer Vision.

[12]  Avideh Zakhor,et al.  Automatic Indoor 3D Surface Reconstruction with Segmented Building and Object Elements , 2015, 2015 International Conference on 3D Vision.

[13]  Adrien Bartoli,et al.  The 3D Line Motion Matrix and Alignment of Line Reconstructions , 2004, International Journal of Computer Vision.

[14]  Masatoshi Ishikawa,et al.  Stereo 3D reconstruction using prior knowledge of indoor scenes , 2011, 2011 IEEE International Conference on Robotics and Automation.

[15]  Joachim Hertzberg,et al.  Towards semantic maps for mobile robots , 2008, Robotics Auton. Syst..

[16]  Mehdi Ammi,et al.  3D reconstruction of indoor building environments with new generation of tablets , 2016, VRST.

[17]  Antonio Adán,et al.  3D Reconstruction of Interior Wall Surfaces under Occlusion and Clutter , 2011, 2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission.

[18]  Julia Armesto,et al.  Indoor Multi-Sensor Acquisition System for Projects on Energy Renovation of Buildings , 2016, Sensors.