Abstract
The iterative closest point (ICP) algorithm is efficient and accurate for rigid registration but it needs the good initial parameters. It is easily failed when the rotation angle between two point sets is large. To deal with this problem, a new objective function is proposed by introducing a rotation invariant feature based on the Euclidean distance between each point and a global reference point, where the global reference point is a rotation invariant. After that, this optimization problem is solved by a variant of ICP algorithm, which is an iterative method. Firstly, the accurate correspondence is established by using the weighted rotation invariant feature distance and position distance together. Secondly, the rigid transformation is solved by the singular value decomposition method. Thirdly, the weight is adjusted to control the relative contribution of the positions and features. Finally this new algorithm accomplishes the registration by a coarse-to-fine way whatever the initial rotation angle is, which is demonstrated to converge monotonically. The experimental results validate that the proposed algorithm is more accurate and robust compared with the original ICP algorithm.
Highlights
Point set registration has become an important topic of computer vision and pattern recognition due to its wide applications such as 3D reconstruction [1,2], medical image analysis [3,4], and image retrieval and classification [5,6]
The goal of the registration is to establish the correspondence between these two sets via the rigid transformation, which can be expressed as the following least squares (LS) problem: min R;!t ;cðiÞ2f1;2;⋯;N m g
Accuracy and convergence of our algorithm, we conduct the experiments on simulation and standard data of MPEG-7 CE-Shape-1 dataset [21], where our algorithm is compared with the original iterative closest point (ICP)
Summary
Point set registration has become an important topic of computer vision and pattern recognition due to its wide applications such as 3D reconstruction [1,2], medical image analysis [3,4], and image retrieval and classification [5,6]. When the rotation angle between the two point sets is large and the initial guess is not accurate, the algorithm cannot register point sets correctly To cope with this problem, we introduce a global reference point. The standard ICP algorithm solves this problem by iteratively registering the shape point set to the model point set with rotation matrix R and translation vector t!. It has been proved that this method is locally convergent, which means that the algorithm is failed when the rotation angle between two point sets is large For this reason, a good initial transformation is so important that it guarantees that the algorithm converges to the global minimum . A new ICP algorithm is proposed to deal with this problem, which is demonstrated to be convergent
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
