Conference Paper

3D environment reconstruction using modified color ICP algorithm by fusion of a camera and a 3D laser range finder

Robot Res. Dept., Electron. & Telecommun. Res. Inst., Daejeon, South Korea
DOI: 10.1109/IROS.2009.5354500 Conference: Intelligent Robots and Systems, 2009. IROS 2009. IEEE/RSJ International Conference on
Source: IEEE Xplore

ABSTRACT In this paper, we propose a system which reconstructs the environment with both color and 3D information. We perform extrinsic calibration of a camera and a LRF (laser range finder) to fuse 3D information and color information of objects. We also formularize an equation to measure the result of the calibration. Moreover, we acquire 3D data by rotating 2D LRF with camera, and use ICP (iterative closest point) algorithm to combine data acquired in other places. We use the SIFT (scale invariant feature transform) matching for the initial estimation of ICP algorithm. It offers accurate and stable initial estimation robust to motion change compare to odometry. We also modify the ICP algorithm using color information. Computation time of ICP algorithm can be reduced by using color information.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents methodologies to accelerate the registration of 3D point cloud segments by using hue data from the associated imagery. The proposed variant of the Iterative Closest Point (ICP) algorithm combines both normalized point range data and weighted hue value calculated from RGB data of an image registered 3D point cloud. A k-d tree based nearest neighbor search is used to associated common points in {x, y, z, hue} 4D space. The unknown rigid translation and rotation matrix required for registration is iteratively solved using Singular Value Decomposition (SVD) method. A mobile robot mounted scanner was used to generate color point cloud segments over a large area. The 4D ICP registration has been compared with typical 3D ICP and numerical results on the generated map segments shows that the 4D method resolves ambiguity in registration and converges faster than the 3D ICP.
    Robotics and Automation (ICRA), 2011 IEEE International Conference on; 06/2011
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The modeling of three-dimensional scene geometry from temporal point cloud streams is of particular interest for a variety of computer vision applications. With the advent of RGB-D imaging devices that deliver dense, metric and textured 6-D data in real-time, on-the-fly reconstruction of static environments has come into reach. In this paper, we propose a system for real-time point cloud mapping based on an efficient implementation of the iterative closest point (ICP) algorithm on the graphics processing unit (GPU). In order to achieve robust mappings at real-time performance, our nearest neighbor search evaluates both geometric and photometric information in a direct manner. For acceleration of the search space traversal, we exploit the inherent computing parallelism of GPUs. In this work, we have investigated the fitness of the random ball cover (RBC) data structure and search algorithm, originally proposed for high-dimensional problems, for 6-D data. In particular, we introduce a scheme that enables both fast RBC construction and queries. The proposed system is validated on an indoor scene modeling scenario. For dense data from the Microsoft Kinect sensor (640×480 px), our implementation achieved ICP runtimes of < 20 ms on an off-the-shelf consumer GPU.
    IEEE International Conference on Computer Vision Workshops, ICCV 2011 Workshops, Barcelona, Spain, November 6-13, 2011; 01/2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: 3D image registration is an emerging research field in the study of computer vision. In this paper, two effective global optimization methods are considered for the 3D registration of point clouds. Experiments were conducted by applying each algorithm and their performance was evaluated with respect to rigidity, similarity and affine transformations. Comparison of algorithms and its effectiveness was tested for the average performance to find the global solution for minimizing the error in the terms of distance between the model cloud and the data cloud. The parameters for the transformation matrix were considered as the design variables. Further comparisons of the considered methods were done for the computational effort, computational time and the convergence of the algorithm. The results reveal that the use of TLBO was outstanding for image processing application involving 3D registration.
    3D Research. 09/2013; 4(3).