Registration of Partial 3D Point Clouds Acquired from a Multi-view Camera for Indoor Scene Reconstruction

  title={Registration of Partial 3D Point Clouds Acquired from a Multi-view Camera for Indoor Scene Reconstruction},
  author={Sehwan Kim and Woontack Woo},
  journal={IEICE Trans. Inf. Syst.},
In this paper, a novel projection-based method is presented to register partial 3D point clouds, acquired from a multi-view camera, for 3D reconstruction of an indoor scene. In general, conventional registration methods for partial 3D point clouds require a high computational complexity and much time for registration. Moreover, these methods are not robust for 3D point cloud which has a low precision. To overcome these drawbacks, a projection-based registration method is proposed. Firstly… 
1 Citations

KinectScenes: Robust Real-Time RGB-D Fusion for Animal Behavioural Monitoring

  • Logan JeyaJ. Zelek
  • Computer Science
    2016 13th Conference on Computer and Robot Vision (CRV)
  • 2016
A near real-time method called KinectScenes that fuses N RGB-D point clouds acquired from statically positioned commodity hardware to reconstruct large & complete dynamic 3D scenes to enable rapid progress for behavioral tracking research.



Projection-based registration using a multi-view camera for indoor scene reconstruction

  • Sehwan KimWoontack Woo
  • Environmental Science
    Fifth International Conference on 3-D Digital Imaging and Modeling (3DIM'05)
  • 2005
A projection-based registration for 3D reconstruction of an indoor environment using a multi-view camera reduces computational complexity by searching for correspondences within an image plane and can be adopted for interaction with as well as navigation in a virtual environment.

Projection-Based Registration Using Color and Texture Information for Virtual Environment Generation

A projection-based registration method for 3D data which uses color and texture data acquired from a multi-view camera for virtual environment generation and an effective color selection can be done by setting up adaptive search ranges based on depth.

3-D Scene Data Recovery Using Omnidirectional Multibaseline Stereo

This paper provides a means of directly extracting 3-D data covering a very wide field of view, thus by-passing the need for numerous depth map merging, and shows the results of the approach applied to both synthetic and real scenes.

Registration and integration of textured 3-D data

  • A. JohnsonS. B. Kang
  • Computer Science
    Proceedings. International Conference on Recent Advances in 3-D Digital Imaging and Modeling (Cat. No.97TB100134)
  • 1997
This work addresses the problem of merging multiple textured 3-D data sets, each of which corresponds to a different view of a scene or object, by using a modified version of the Iterative Closest Point algorithm and showing that the use of color decreases registration error by an order of magnitude.

Registration and integration of textured 3D data

Outdoor scene reconstruction from multiple image sequences captured by a hand-held video camera

  • T. SatoM. KanbaraN. Yokoya
  • Computer Science
    Proceedings of IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI2003.
  • 2003
First, the method estimates extrinsic camera parameters of each image sequence, then reconstructs a dense 3D model of a scene using an extended multi-baseline stereo and voxel voting technique.

Registering Multiview Range Data to Create 3D Computer Objects

The effectiveness with which registration of range images can be accomplished makes this method attractive for many practical applications where surface models of 3D objects must be constructed.

Robust simultaneous registration of multiple range images comprising a large number of points

For more efficient and more accurate search for matching points, the KD-tree data structure is utilized, and additional attributes such as the laser reflection brightness and the brightness of the three-dimensional point itself are introduced into the error measure.

A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses

  • R. Tsai
  • Physics
    IEEE J. Robotics Autom.
  • 1987
A new technique for three-dimensional camera calibration for machine vision metrology using off-the-shelf TV cameras and lenses using two-stage technique has advantage in terms of accuracy, speed, and versatility over existing state of the art.

A Method for Registration of 3-D Shapes

A general-purpose, representation-independent method for the accurate and computationally efficient registration of 3-D shapes including free-form curves and surfaces based on the iterative closest point (ICP) algorithm.