The traditional iterativeclosestpoint (ICP) algorithm is accurate and fast for rigid point set registration but it is unable to handle affine case. This paper instead introduces a novel generalized ICP algorithm bas...
详细信息
The traditional iterativeclosestpoint (ICP) algorithm is accurate and fast for rigid point set registration but it is unable to handle affine case. This paper instead introduces a novel generalized ICP algorithm based on lie group for affine registration of m-D point sets. First, with singular value decomposition technique applied, this paper decomposes affine transformation into three special matrices which are then constrained. Then, these matrices are expressed by exponential mappings of lie group and their Taylor approximations at each iterative step of affine ICP algorithm. In this way, affine registration problem is ultimately simplified to a quadratic programming problem. By solving this quadratic problem, the new algorithm converges monotonically to a local minimum from any given initial parameters. Hence, to reach desired minimum, good initial parameters and constraints are required which are successfully estimated by independent component analysis. This new algorithm is independent of shape representation and feature extraction, and thereby it is a general framework for affine registration of m-D point sets. Experimental results demonstrate its robustness and efficiency compared with the traditional ICP algorithm and the state-of-the-art methods. (c) 2010 Elsevier B.V. All rights reserved.
This article presents a robust translation, rotation, and scaling invariant pattern recognition algorithm using partially distorted two-dimensional (2D) contours. Both global and local matching accuracies are guarante...
详细信息
This article presents a robust translation, rotation, and scaling invariant pattern recognition algorithm using partially distorted two-dimensional (2D) contours. Both global and local matching accuracies are guaranteed: the former is achieved by using global control point (GCP) and curvature matching and the latter by using the iterativeclosestpoint (ICP) algorithm. In the proposed algorithm, an input contour is considered two possible types: first the contour contains GCP and the second contains no GCP For the contours with no detected GCPs, the algorithm considers the contour as the second type of contour and the curvature matching algorithm is directly applied. For the contour with GCPs, a global alignment is performed using the GCPs and then, the curvature matching algorithm is applied. The validity of the algorithm is illustrated by the presentation of experimental results. The experiments show that the algorithm works well for partial object recognition with and without GCPs. (C) 2011 Society for Imaging Science and Technology. [DOI: 10.2352/***.2011.55.6.060501]
We present a practical and systematic method to reconstruct accurate physical models of the guinea pig ear (n = 1). The method uses a semi-automatic technique to create three-dimensional (3-D) models of the guinea pig...
详细信息
We present a practical and systematic method to reconstruct accurate physical models of the guinea pig ear (n = 1). The method uses a semi-automatic technique to create three-dimensional (3-D) models of the guinea pig cochlea by registration of micro-computed tomography (CT) and histological images. An iterative closest point algorithm was employed to minimize the sum of square errors with respect to the closest histological model and corresponding micro-CT model. This allowed creation of an accurate geometric ear model including external ear canal, tympanic membrane, middle ear cavity, auditory ossicles, and the cochlea. The characteristic cross-sectional areas of scala tympani, scala vestibuli, and scala media were measured. The length, thickness, and apex width of the guinea pig's basilar membrane were compared to the data found in literature. Some shape parameters were also compared among different species. The results confirmed that the geometric model created by this method was accurate. This method provides an effective way to visualize the 3-D structure and the detailed information about ear geometry required for finite element and multibody dynamic analysis.
OBJECTIVE: In thoracolumbar spinal instrumentation surgery, pedicle screw fixation is widely used, whereas screw loosening occurs only occasionally over time. It is common to evaluate screw loosening by the radiograph...
详细信息
OBJECTIVE: In thoracolumbar spinal instrumentation surgery, pedicle screw fixation is widely used, whereas screw loosening occurs only occasionally over time. It is common to evaluate screw loosening by the radiographic lucent zone around screws, which can neither evaluate loosening quantitatively nor detect slight screw loosening. In the present technical note, we describe a novel assessment technique of screw loosening by generating 3-dimensional screw images from computed tomography data and superposing them in time series. METHODS: Computed tomography data were exported in digital imaging and communications in medicine dataset and imported to the 3-dimensional computer-aided designing software, by which screws and rods were segmented and outputted in stereolithography (STL) format. The STL files were imported to the software, and registration based on iterative closest point algorithm was performed to assess screw position changes. RESULTS: Positional changes on STL in time series were classified into 3 types: 1) no position changes existed in the entire system of screws and rods;2) position changes existed in the entire system of screws and rods, but no position changes were shown when the left-sided and right-sided screws and rod were separately evaluated;and 3) position changes existed in the left and/or right-sided screws and rods even when evaluated separately. CONCLUSIONS: This technique enables the quantitative evaluation of screw loosening and loosening between screws and rods. In conjunction with conventional methods of assessing radiographic lucent zone, we are able to obtain more accurate information regarding screw loosening after spinal instrumentation surgery.
Challenge in the registration of battlefield images in visible and far-infrared bands is the feature inconsistency. We propose a contour-based approach for the registration and apply two free-form curve-matching algor...
详细信息
ISBN:
(纸本)0819436771
Challenge in the registration of battlefield images in visible and far-infrared bands is the feature inconsistency. We propose a contour-based approach for the registration and apply two free-form curve-matching algorithms: adaptive hill climbing and the iterative closest point algorithm. Both algorithms do not requires explicit curve feature correspondence, are designed to be robust against outliers. We formulate the search as an adaptive hill climbing optimization for minimizing the partial Hausdorff distances. In the iterative closest point algorithm we choose the mean partial distance as the objective function, so that outliers can be easily handled by using rank order statistics.
point set registration is important for calibration of multiple cameras, 3D reconstruction and recognition, etc. The traditional scale iterativeclosestpoint (ICP) algorithm is fast and accurate for scale registratio...
详细信息
ISBN:
(纸本)9781922107909
point set registration is important for calibration of multiple cameras, 3D reconstruction and recognition, etc. The traditional scale iterativeclosestpoint (ICP) algorithm is fast and accurate for scale registration of point sets, but it performs worse when the point sets with large outliers or noise. This paper introduces a novel algorithm based on correntropy for scale registration of noisy point sets. Firstly, the definition of correntropy is introduced and its property of eliminating outliers is demonstrated by comparing with the mean square error (MSE). Secondly, a novel objective function of scale registration problem is proposed by applying the maximum correntropy criterion (MCC). After that, a new scale ICP algorithm is proposed to solve this energy function. This method uses a simple iterativealgorithm and computes the scale transformation by methods including half-quadratic technique and derivation quickly at each iterative step. Similar to the ICP algorithm, this new algorithm converges monotonically to a local maximum for any given initial parameters. Experimental results demonstrate that our algorithm has the high speed and accuracy for scale registration with outliers compared with the traditional scale ICP algorithm and the state-of-the-art algorithms.
We present a method for three-dimensional surface registration which utilizes a Genetic algorithm (GA) to perform a coarse alignment of two scattered point clouds followed by a slight variation of the iterative Closes...
详细信息
ISBN:
(纸本)9789898425836
We present a method for three-dimensional surface registration which utilizes a Genetic algorithm (GA) to perform a coarse alignment of two scattered point clouds followed by a slight variation of the iterativeclosestpoint (ICP) algorithm for a final fine-tuning. In this work, in order to improve the time of convergence, a sampling method consisting of three steps is used: 1) sample over the geometry of the clouds based on a gradient function to remove easily interpolating singularities;2) a random sampling of the clouds and 3) a final sampling based on the overlapping areas between the clouds. The presented method requires no more than 25% of overlapping surface between the two scattered point clouds and no rotational or translational information is needed. The proposed algorithm has shown a good convergence ratio with few generations and usability through automated applications such as object digitalization and reverse engineering.
This paper describes a parallel implementation developed to improve the time performance of the iterative closest point algorithm. Within each iteration, the correspondence calculations are distributed among the proce...
详细信息
ISBN:
(纸本)0769509851
This paper describes a parallel implementation developed to improve the time performance of the iterative closest point algorithm. Within each iteration, the correspondence calculations are distributed among the processor resources. Ar the end of each iteration, the results of the correspondence determination are communicated back to a central processor and the current transformation is calculated A number of additional techniques were developed that sen,ed to improve upon this basic scheme. Calculating the partial sums within each distributed resource made it unnecessary to transmit the correspondence values back to the central processor, which reduced the communication overhead, and improved time performance. Randomly distributing the points among the processor resources resulted in a better load balancing, which further improved time performance. We also found that thinning the image by randomly removing a certain percentage of the points did not improve the performance, when viewed as the progression of mse with time. The method was implemented and tested on a 22 node Beowulf class cluster. For a large image, linear performance improvements were obtained for up to 16 processors, while they held for rtp to 8 processors with a smaller image.
In order to realize the autonomous location and attitude estimation for speedy UAV, this paper designs an improved iterativeclosestpoints (ICP) algorithm for fixed-wing UAV with a laser range finder mounted onboard....
详细信息
ISBN:
(纸本)9781479946990
In order to realize the autonomous location and attitude estimation for speedy UAV, this paper designs an improved iterativeclosestpoints (ICP) algorithm for fixed-wing UAV with a laser range finder mounted onboard. This improved ICP adopts a K-d tree and AK-d tree mixed closestpoint searching strategy to enhance its rapidity, and an automatic trim approach to drop out outlier points to improve its reliability. In order to check the feasibility of the proposed algorithm, flight experiment is conducted. Experiment result demonstrates the good performance of the algorithm.
Image registration is a valuable technique for medical diagnosis and treatment. It allows physicians to combine information from multiple images by aligning them into the same coordinate space. Surface-based methods r...
详细信息
ISBN:
(纸本)0819420859
Image registration is a valuable technique for medical diagnosis and treatment. It allows physicians to combine information from multiple images by aligning them into the same coordinate space. Surface-based methods register images by aligning corresponding surfaces of one or more anatomical structures such as the surface of the brain or skull. In this paper we examine a novel implementation of this approach. We use the iterative closest point algorithm to iteratively search for the transformation that minimizes the distance between surface points in one image and a surface model in the other image. In each iteration we use the closestpoint transform to find corresponding points that are closest with respect to the transformation estimated in the previous iteration. Results from several experiments are presented to demonstrate the efficacy of this approach.
暂无评论