3D Curve Reconstruction Research Articles

3D Highway Curve Reconstruction From Mobile Laser Scanning Point Clouds

The point clouds acquired by a vehicle-borne mobile laser scanning (MLS) system have shown great potential for many applications such as intelligent transportation systems, road infrastructure inventories, and high-definition (HD) maps to support the advanced driver-assistance systems (ADAS) and autonomous vehicles (AVs). This paper presents a novel two-step approach to automated detection and reconstruction of three-dimensional (3D) highway curves from MLS point clouds. However, when dealing with noisy, unstructured, dense point clouds, we often face some challenges, most notably in handling of the outliers introduced during road marking detection and in recognition of curve types during 3D curve reconstruction. Our approach is formed by two main algorithms: a detector based on intensity variance and a robust model fitting estimator. The experimental results obtained using both a virtual scan dataset and a real MLS dataset demonstrated that our approach is very promising in handling of the outliers and reconstruction of 3D road curves. Specifically, a relative accuracy of 0.6% has been achieved in estimation of circle radii based on the virtual scan dataset. A comparative study also showed that our road marking detection approach is more effective and more stable than state-of-the-art approaches.

Reconstruction of 3D curves and surfaces using new variants of gravitational search algorithm

The problem of reconstruction of 3D curves and surfaces is modelled as a nonlinear optimization problem in which the objective function to be minimized is the error function between given data points and data points on the generated curve/surface.Although any optimization algorithm can be used to solve this problem, but due to the inherent complexities in the optimization model, heuristic algorithms are best suited. In this paper, a recently proposed nature motivated optimization technique, namely Gravitational Search Algorithm and its three variants are used to solve reconstruction problem. The approach is illustrated with the help of two examples- a helix and a dumbbell. The results are demonstrated and it is concluded that the approach is very promising in the area.

Shape from sensors: Curve networks on surfaces from 3D orientations

We present a novel framework for acquisition and reconstruction of 3D curves using orientations provided by inertial sensors. While the idea of sensor shape reconstruction is not new, we present the first method for creating well-connected networks with cell complex topology using only orientation and distance measurements and a set of user-defined constraints. By working directly with orientations, our method robustly resolves problems arising from data inconsistency and sensor noise. Although originally designed for reconstruction of physical shapes, the framework can be used for “sketching” new shapes directly in 3D space. We test the performance of the method using two types of acquisition devices: a standard smartphone, and a custom-made device.

StereoMorph: an R package for the collection of 3D landmarks and curves using a stereo camera set‐up

SummaryQuantitative, three‐dimensional measurements of anatomy in biology and paleontology are key to understanding the evolutionary processes underlying morphological, functional and ecological diversification. However, the collection of 3D morphometric data from a large number of samples or in the field is currently limited by methods that are either too costly, too time‐consuming or lack portability.We present a new R package, StereoMorph, for the rapid and accurate collection of 3D landmarks and curves using two standard digital cameras. StereoMorph provides a complete set of tools for every step in the collection of 3D landmarks and curves using a stereo camera set‐up. This includes image processing and optimization functions for automated camera calibration using a checkerboard pattern, an easy‐to‐use application for digitizing landmarks and curves from photographs, and tools for reconstructing points and curves in 3D. The image processing tools and digitizing application are readily applicable to 2D morphometrics as well, enabling 2D landmarks and curves to be digitized and scaled automatically using a checkerboard pattern.We include five examples that demonstrate key functionalities of StereoMorph: automated detection of checkerboard corners, camera calibration, testing calibration accuracy, digitizing photographs and 3D curve reconstruction. With a set‐up costing less than $1500, we show that it is possible to achieve a mean reconstruction error of less than 30 microns. Once the cameras are assembled, specimens can be photographed as quickly as with 2D morphometrics while digitizing takes two to three times as long as digitizing a single photograph.We conclude by presenting an accompanying tutorial which details all of the steps required to collect 3D landmarks and curves using StereoMorph. Additionally, we present a web blog that will provide a platform for updates and user questions and suggestions.

Robust three-dimensional vehicle reconstruction using cross-ratio invariance

A new method for structure-from-motion (SfM) is developed for moving vehicles on the street using a video camera Outdoor vehicle is one of the most difficult objects for tracking or three-dimensional (3D) reconstruction because most vehicle surfaces are specular and reflect background scenes. Therefore conventional point feature tracking method is not appropriate since spurious features are often tracked and the numbers of the correct features are too small. To overcome such difficulties, epipolar constraint, cross-ratio histogram and 3D curve reconstruction are employed in this method. The proposed method is also computationally efficient since it does not require expensive feature tracking process, which is used in most conventional SfM methods. Finally, to evaluate the error, experiments over 200 vehicles are performed under various viewing conditions and they show significant correlation among the number of frames, distance from the camera and accuracy of reconstruction.

Two-view curve reconstruction based on the snake model

Reconstruction of 3D curves from their stereo images is an important issue in computer vision. Based on deformation of the snake model and NURBS representation, we evolve the curve in the view of inverse optimization to finish reconstruction. This manner can reduce the need of matching multi-view space curve projections, meanwhile improve the reconstruction precision. Considering that the 2D data reconstruction exists error inevitably, based on two cameras, a discussion on its influence to stereo reconstruction is given next. Finally, the proposed approach is experimented with artificial and real data, and gains a satisfying reconstruction effect.

Hypergraph-oriented 3D reconstruction, interpretation and analysis of air flows

The paper introduces a new air flow analysis approach based on particle tracking velocimetry (PTV). One of the special features of the proposed method is that after the tracer particles are detected, matching and tracking are jointly conducted. To this end, we introduce an interpretation module based on a directed hypergraph for 3D curve reconstruction. At first, the 2D inter-frame locations are localised and used for the extraction and calculation of 3D keypoints. Through 3D keypoints, which are evaluated by the hypergraph together with the time information in several steps, reverse curve matching for path selection can be reconstructed and the resulting trajectories visualised. In contrast to the preceding works, our approach tries to describe the measuring data by 3D trajectories directly instead of estimating 2D trajectories first and then matching afterwards. A higher precision can be achieved also with complicated trajectories. A certain independence of the reflections and lighting conditions is reached by the interpretation. Moreover, the path of particles can also be reconstructed with the minimum number of 3D keypoints under consideration of the path energy minimisation.

Accurate Dimensional Measurement of 3D Round Holes Based on Stereo Vision

This paper present an effective method to accurately reconstruct and measure the 3D curve edges of small industrial parts based on stereo vision. To effectively fit the curve of the measured parts using a series of line segments in the images, a strategy from coarse to fine is employed based on multi-scale curve fitting. After reconstructing the 3D curve of a hole through a curved surface, its axis is adjusted so that it is parallel to the Z axis with least squares error and the dimensions of the hole can be calculated on the XY plane easily. Experimental results show that the presented method can accurately measure the dimensions of round holes through a curved surface. Keywords—Stereo Vision, 3D Round Hole Measurement, Curve Fitting, 3D Curve Reconstruction, Least Squares Error.

Silhouette Smoothing for Real-Time Rendering of Mesh Surfaces

Coarse piecewise linear approximation of surfaces causes undesirable polygonal appearance of silhouettes. We present an efficient method for smoothing the silhouettes of coarse triangle meshes using efficient 3D curve reconstruction and simple local re-meshing. It does not assume the availability of a fine mesh and generates only moderate amount of additional data at run time. Furthermore, polygonal feature edges are also smoothed in a unified framework. Our method is based on a novel interpolation scheme over silhouette triangles and this ensures that smooth silhouettes are faithfully reconstructed and always change continuously with respect to continuous movement of the view point or objects. We speed up computation with GPU assistance to achieve real-time rendering of coarse meshes with the smoothed silhouettes. Experiments show that this method outperforms previous methods for silhouette smoothing.

Optimized stereo reconstruction of free-form space curves based on a nonuniform rational B-spline model

Analytical reconstruction of 3D curves from their stereo images is an important issue in computer vision. We present an optimization framework for such a problem based on a nonuniform rational B-spline (NURBS) curve model that converts reconstruction of a 3D curve into reconstruction of control points and weights of a NURBS representation of the curve, accordingly bypassing the error-prone point-to-point correspondence matching. Perspective invariance of NURBS curves and constraints deduced on stereo NURBS curves are employed to formulate the 3D curve reconstruction problem into a constrained nonlinear optimization. A parallel rectification technique is then adopted to simplify the constraints, and the Levenberg-Marquardt algorithm is applied to search for the optimal solution of the simplified problem. The results from our experiments show that the proposed framework works stably in the presence of different data samplings, randomly posed noise, and partial loss of data and is potentially suitable for real scenes.