3D non-rigid registration using color: Color Coherent Point Drift

Abstract

Research into object deformations using computer vision techniques has been under intense study in recent years. A widely used technique is 3D non-rigid registration to estimate the transformation between two instances of a deforming structure. Despite many previous developments on this topic, it remains a challenging problem. In this paper we propose a novel approach to non-rigid registration combining two data spaces in order to robustly calculate the correspondences and transformation between two data sets. In particular, we use point color as well as 3D location as these are the common outputs of RGB-D cameras. We have propose the Color Coherent Point Drift (CCPD) algorithm (an extension of the CPD method [1]). Evaluation is performed using synthetic and real data. The synthetic data includes easy shapes that allow evaluation of the effect of noise, outliers and missing data. Moreover, an evaluation of realistic figures obtained using Blensor is carried out. Real data acquired using a general purpose Primesense Carmine sensor is used to validate the CCPD for real shapes. For all tests, the proposed method is compared to the original CPD showing better results in registration accuracy in most cases.

A Review of Point Set Registration: From Pairwise Registration to Groupwise Registration

“…Therefore, the objective function of point set registration was composed of the global distance item, non-rigid transformation constraint item and two local structure constraints items.Extraction the feature of point sets: The spatial location of point sets is a traditional feature for registration. In [86], the color information of point sets was used to extend the CPD algorithm. In [87], the correlation of color information and spatial location information was formulated.…”

“…Then, an expectation-maximization (EM) algorithm is applied to perform this ML optimization. Many algorithms were proposed to extend the CPD method [ 1 , 72 , 73 , 74 , 75 , 76 , 77 , 78 , 79 , 80 , 81 , 82 , 83 , 84 , 85 , 86 , 87 , 88 , 89 , 90 , 91 , 92 ]. These algorithms can be summarized as follows: Selecting a suitable non-rigid transformation function: In the CPD method, only one non-rigid transformation function is considered.…”

“…Extraction the feature of point sets: The spatial location of point sets is a traditional feature for registration. In [ 86 ], the color information of point sets was used to extend the CPD algorithm. In [ 87 ], the correlation of color information and spatial location information was formulated.…”

Acceleration of Non-Rigid Point Set Registration With Downsampling and Gaussian Process Regression

“…The main advantage of ICP-based methods is their scalability to large point sets, and variants of the ICP algorithm have been developed in the field of mesh registration [5], [6], [7], [8], [9]. The latter group comprises the registration methods in which point-to-point correspondences are assumed to be one-to-many, and this characteristic often contributes to their robustness [10], [11], [12], [13], [14], [15], [16], [17], [18].…”

Probabilistic Learning Coherent Point Drift for 3D Ultrasound Fetal Head Registration

“…Other authors have reported CPD variants seeking to optimally assign the GMM membership probability using rotation invariant shape descriptors [23], correspondence priors and correspondence preserving subsampling approaches [24], and the shape context of one point with respect to the distribution of other points [25]. On the other hand, Saval-Calvo et al [26] proposed color-CPD algorithm to register 3D points by using color and shape spaces to jointly estimate the best match.…”