Conventional Iterative Closest Point Research Articles

Robust H-K Curvature Map Matching for Patient-to-CT Registration in Neurosurgical Navigation Systems

Image-to-patient registration is a coordinate system matching process between real patients and medical images to actively utilize medical images such as computed tomography (CT) during surgery. This paper mainly deals with a markerless method utilizing scan data of patients and 3D data from CT images. The 3D surface data of the patient are registered to CT data using computer-based optimization methods such as iterative closest point (ICP) algorithms. However, if a proper initial location is not set up, the conventional ICP algorithm has the disadvantages that it takes a long converging time and also suffers from the local minimum problem during the process. We propose an automatic and robust 3D data registration method that can accurately find a proper initial location for the ICP algorithm using curvature matching. The proposed method finds and extracts the matching area for 3D registration by converting 3D CT data and 3D scan data to 2D curvature images and by performing curvature matching between them. Curvature features have characteristics that are robust to translation, rotation, and even some deformation. The proposed image-to-patient registration is implemented with the precise 3D registration of the extracted partial 3D CT data and the patient’s scan data using the ICP algorithm.

RGB-D camera calibration and trajectory estimation for indoor mapping

In this paper, we present a system for estimating the trajectory of a moving RGB-D camera with applications to building maps of large indoor environments. Unlike the current most researches, we propose a ‘feature model’ based RGB-D visual odometry system for a computationally-constrained mobile platform, where the ‘feature model’ is persistent and dynamically updated from new observations using a Kalman filter. In this paper, we firstly propose a mixture of Gaussians model for the depth random noise estimation, which is used to describe the spatial uncertainty of the feature point cloud. Besides, we also introduce a general depth calibration method to remove systematic errors in the depth readings of the RGB-D camera. We provide comprehensive theoretical and experimental analysis to demonstrate that our model based iterative-closest-point (ICP) algorithm can achieve much higher localization accuracy compared to the conventional ICP. The visual odometry runs at frequencies of 30 Hz or higher, on VGA images, in a single thread on a desktop CPU with no GPU acceleration required. Finally, we examine the problem of place recognition from RGB-D images, in order to form a pose-graph SLAM approach to refining the trajectory and closing loops. We evaluate the effectiveness of the system on using publicly available datasets with ground-truth data. The entire system is available for free and open-source online.

Sparse Scaling Iterative Closest Point for Rail Profile Inspection

AbstractThe accuracy of rail profile inspections is critical for guaranteeing transport security and rail maintenance, and hence, the laser-based rail profile inspection has frequently been used. However, there are two major challenges in practical applications: the distortion of the measured rail profile and the influences of noise and outliers. In this paper, the sparse scaling iterative closest point method is proposed for rail profile inspection. First, the existing challenges for processing the measured rail profile via a line laser sensor are generally described. After this, a robust registration energy function that evolves both the scale factor and the lp norm is proposed for rail profile registration. Finally, the Hausdorff distance is adopted to visualize the matching results. The experiments indicate that the proposed method can both precisely rectify the distorted rail profile and avoid the influences of noise and outliers when compared with the conventional iterative closest point, sparse iterative closest point, and reweighted-scaling closest point methods.

Dynamic inspection of a rail profile under affine distortion based on the reweighted-scaling iterative closest point method

The precision and efficiency of rail inspection are of vital importance to the operation and safety of railway systems. However, because of vibrations that occur in the rail inspection vehicle and installation error of the line laser sensor, the collected rail profile is distorted. As a result, the accuracy and robustness of conventional registration and inspection methods cannot be guaranteed. In this paper, an accurate and robust calibration method for measuring rail profile distortion is proposed. In this study, the impact of vibration on the rail profile, which was obtained with a laser sensor, was analyzed. Then, the collected rail profile was divided into two segments according to the actual condition where only the upper part of the rail was subjected to wear. An accurate and robust reweighted-scaling iterative closest point algorithm was proposed to calibrate the distorted rail profile, and the upper and lower boundaries of the scale ratio were used as constraints to solve the registration problem effectively and efficiently. Finally, the Hausdorff distance method was introduced to clearly visualize the rectified rail profile and wear. The experimental results demonstrated that the proposed method can realize the affine transformation of the distorted rail profile with a high precision and robustness. Additionally, it can achieve an online dynamic calibration and inspection of the rail by comparing the data with the conventional iterative closest point, scaling iterative closest point, and Calipri.

Intensity-Assisted ICP for Fast Registration of 2D-LIDAR.

Iterative closest point (ICP) is a method commonly used to perform scan-matching and registration. To be a simple and robust algorithm, it is still computationally expensive, and it has been regarded as having a crucial challenge especially in a real-time application as used for the simultaneous localization and mapping (SLAM) problem. For these reasons, this paper presents a new method for the acceleration of ICP with an assisted intensity. Unlike the conventional ICP, this method is proposed to reduce the computational cost and avoid divergences. An initial transformation guess is computed with an assisted intensity for their relative rigid-body transformation. Moreover, a target function is proposed to determine the best initial transformation guess based on the statistic of their spatial distances and intensity residuals. Additionally, this method is also proposed to reduce the iteration number. The Anderson acceleration is utilized for increasing the iteration speed which has better ability than the Picard iteration procedure. The proposed algorithm is operated in real time with a single core central processing unit (CPU) thread. Hence, it is suitable for the robot which has limited computation resources. To validate the novelty, this proposed method is evaluated on the SEMANTIC3D.NET benchmark dataset. According to comparative results, the proposed method is declared as having better accuracy and robustness than the conventional ICP methods.

Three-Dimensional Point Cloud Registration Based on Normal Vector Angle

The widespread use of three-dimensional laser scanning makes point cloud registration essential for model reconstruction. Although iterative closest point (ICP) is a widely used algorithm for automatic and accurate point cloud registration, the ICP algorithm is time-intensive and typically falls in local optima. We employ the normal vector angle of the 3D model and integrate a heuristic search into the ICP algorithm to improve its efficiency, especially while registering complex surfaces. We compare this improved ICP algorithm with the original ICP algorithm and variants of the algorithm in terms of convergence, robustness, and response from a poor initial cloud point position to verify that the proposed improvements outperform the conventional ICP algorithm in the three evaluated aspects when processing point clouds with complex surfaces.

A FAST AND FLEXIBLE METHOD FOR META-MAP BUILDING FOR ICP BASED SLAM

Recent developments in LiDAR sensors make mobile mapping fast and cost effective. These sensors generate a large amount of data which in turn improves the coverage and details of the map. Due to the limited range of the sensor, one has to collect a series of scans to build the entire map of the environment. If we have good GNSS coverage, building a map is a well addressed problem. But in an indoor environment, we have limited GNSS reception and an inertial solution, if available, can quickly diverge. In such situations, simultaneous localization and mapping (SLAM) is used to generate a navigation solution and map concurrently. SLAM using point clouds possesses a number of computational challenges even with modern hardware due to the shear amount of data. In this paper, we propose two strategies for minimizing the cost of computation and storage when a 3D point cloud is used for navigation and real-time map building. We have used the 3D point cloud generated by Leica Geosystems's Pegasus Backpack which is equipped with Velodyne VLP-16 LiDARs scanners. To improve the speed of the conventional iterative closest point (ICP) algorithm, we propose a point cloud sub-sampling strategy which does not throw away any key features and yet significantly reduces the number of points that needs to be processed and stored. In order to speed up the correspondence finding step, a dual kd-tree and circular buffer architecture is proposed. We have shown that the proposed method can run in real time and has excellent navigation accuracy characteristics.

특징 점 기반의 ICP 알고리즘을 이용한 2차원 격자지도 보정

This paper suggests a feature point-based Iterative Closest Point (ICP) algorithm to compensate for the disparity error in building a two-dimensional map. The ICP algorithm is a typical algorithm for matching a common object in two different images. In the process of building a two-dimensional map using the laser scanner data, warping and distortions exist in the map because of the disparity between the two sensor values. The ICP algorithm has been utilized to reduce the disparity error in matching the scanned line data. For this matching process in the conventional ICP algorithm, pre-known reference data are required. Since the proposed algorithm extracts characteristic points from laser-scanned data, reference data are not required for the matching. The laser scanner starts from the right side of the mobile robot and ends at the left side, which causes disparity in the scanned line data. By finding the matching points between two consecutive frame images, the motion vector of the mobile robot can be obtained. Therefore, the disparity error can be minimized by compensating for the motion vector caused by the mobile robot motion. The validity of the proposed algorithm has been verified by comparing the proposed algorithm in terms of map-building accuracy to conventional ICP algorithm real experiments.

Medical augment reality using a markerless registration framework

This study proposes a cranial augmented-reality (AR) system which characterizes on performing image-to-patient registration using only natural facial features. Its hardware includes only three calibrated CCD cameras but any commercial spatial digitizing devices or artificial skin markers. Two of the cameras are mounted together to form a stereo-vision system, while the third camera moves freely and captures real-time images for AR-fusion display. The facial surface of a patient is first reconstructed by stereo vision. Meanwhile, another facial surface is reconstructed from preoperative computed tomography (CT) images of the patient. A iterative closest point (ICP)-based algorithm is then used to register the two facial data sets, which transfers the anatomical information from the CT images to the physical space. Since the natural of stereo-vision reconstruction usually accompanies with noisy data, the conventional ICP also suffers from its inherent local-minimum problem. Therefore, we propose an improved ICP which embeds a weighting and perturbing strategy to increase robustness and the ability of noise resistance. As a result, with a seamless integration among the preoperative CT images, the patient, the stereo-vision cameras, and the movable camera, an immersive medical AR environment based on a markerless image-to-patient registration is thus accomplished.