Robust iterative closest point algorithm based on global reference point for rotation invariant registration

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.

A novel rotation invariant and Manhattan metric–based pose refinement: Augmented reality–based oral and maxillofacial surgery

“…To get very effective and accurate rigid registration of image, ICP needs good initial parameter values. To solve this problem, we adapted a rotation invariant feature, the so‐called global reference point, which is introduced to obtain good initial values . With this global reference point, more precise correspondence is provided between the two point sets in the matching stage of the ICP .…”

“…To solve this problem, we adapted a rotation invariant feature, the so‐called global reference point, which is introduced to obtain good initial values . With this global reference point, more precise correspondence is provided between the two point sets in the matching stage of the ICP . This feature also decreases the number of iterations needed for ICP; therefore, it accelerates the performance of the image registration process.…”

“…The best matched 2D pose is processed to the ICP algorithm. With an initial alignment obtained using the Ulrich method, rotation invariant registration is calculated using a global reference point to ensure that the initial parameter values are valid for ICP algorithm. This global reference point is vital for all the images, and it should be accurate as it is the reference to match all other pixels.…”

“…c ( k ) is the correspondence between the two point sets. To obtain the initial parameters of the ICP algorithm and avoid the wrong initializations, a global referencing point concept was introduced to point out the nearest closet point from the target pixel. It is calculated by using the weight difference between those pixels and presented as Equation that provides correct initial values for the algorithm .…”

“…To obtain the initial parameters of the ICP algorithm and avoid the wrong initializations, a global referencing point concept was introduced to point out the nearest closet point from the target pixel. It is calculated by using the weight difference between those pixels and presented as Equation that provides correct initial values for the algorithm . The rotation invariant measurements for the model set P and Q are calculated by using the ) and (), respectively. where w = weight.…”