Open Source Point Cloud Library Research Articles

AN AUTOMATED PROCESS TO DETECT EDGES IN UNORGANIZED POINT CLOUDS

Abstract. This paper presents an automated and effective method for detecting planes and their intersections as edges in unorganized point clouds. The edges are subsequently extracted as vectors to a CAD environment. The software was developed within the Microsoft Visual Studio and the open source Point Cloud Library (PCL, http://pointclouds.org/) was used. The Point Cloud Library is a standalone, large scale, open project for 2D/3D image and point cloud processing. The code was written in C++. For the detection of the planes in the point cloud the RANSAC algorithm was employed. Subsequently, and according to the standard theory of Analytic Geometry the edges were determined as the intersections of these planes with each other. A straight line in 3D space is defined by one of its points, which was determined with the Lagrangian Multipliers method and a parallel vector, which was determined with the help of the cross product of two vectors on space. Finally, the algorithm and the results of the implementation of the process with real data were evaluated by performing various checks, mainly aiming to determine the accuracy of the edge detection.

Loss of Significance and Its Effect on Point Normal Orientation and Cloud Registration

Point normal calculation and cloud registration are two of the most common operations in point cloud processing. However, both are vulnerable to issues of numerical precision and loss of significance. This paper documents how loss of significance in the open-source Point Cloud Library can create erroneous point normals and cause cloud registration to fail. Several test clouds are used to demonstrate how the loss of significance is caused by tight point spacing and clouds being shifted far from the origin of their coordinate system. The results show that extreme loss of significance can cause point normals to be calculated with a random orientation, and cause meters of error during cloud registration. Depending on the structure of the point cloud, loss of significance can occur when the cloud is at hundreds or even tens of meters from the origin of its coordinate system. Shifting to larger data types (e.g., from 32-bit “floats” to 64-bit “doubles”) can alleviate the problem but will not solve it completely. Several “best practice” recommendations for avoiding this issue are proposed. But the only solution guaranteed to eliminate loss of significance is de-meaning the entire cloud, or clusters of points before processing.

3D registration based on the direction sensor measurements

3D registration is a very active topic, spanning research areas such as computational geometry, computer graphics and pattern recognition. It aims to solve spatial transformation that aligns two point clouds. In this work we propose the use of a single direction sensor, such as an accelerometer or a magnetometer, commonly available on contemporary mobile platforms, such as tablets and smartphones. Both sensors have been heavily investigated earlier, but only for joint use with other sensors, such as gyroscopes and GPS. We show a time-efficient and accurate 3D registration method that takes advantage of only either an accelerometer or a magnetometer. We demonstrate a 3D reconstruction of individual point clouds and the proposed 3D registration method on a tablet equipped with an accelerometer or a magnetometer. However, we point out that the proposed method is not restricted to mobile platforms. Indeed, it can easily be applied in any 3D measurement system that is upgradable with some ubiquitous direction sensor, for example by adding a smartphone equipped with either an accelerometer or a magnetometer. We compare the proposed method against several state-of-the-art methods implemented in the open source Point Cloud Library (PCL). The proposed method outperforms the PCL methods tested, both in terms of processing time and accuracy.

Segmentation based building detection approach from LiDAR point cloud

Accurate building detection and reconstruction is an important challenge posed to the remote sensing community dealing with LiDAR point cloud. The inherent geometric nature of LiDAR point cloud provides a new dimension to the remote sensing data which can be used to produce accurate 3D building models at relatively less time compared to traditional photogrammetry based 3D reconstruction methods. 3D segmentation is a key step to bring out the implicit geometrical information from the LiDAR point cloud. This research proposes to use open source point cloud library (PCL) for 3D segmentation of LiDAR point cloud and presents a novel histogram based methodology to separate the building clusters from the non building clusters. The proposed methodology has been applied on two different airborne LiDAR datasets acquired over part of urban region around Niagara Falls, Canada and southern Washington, USA. An overall building detection accuracy of 100% and 82% respectively is achieved for the two datasets. The performance of proposed methodology has been compared with the commercially available Terrasolid software. The results show that the buildings detected using open source point cloud library produce comparable results with the buildings detected using commercial software (buildings detection accuracy: 86.3% and 89.2% respectively for the two datasets).

Registration with the Point Cloud Library: A Modular Framework for Aligning in 3-D

Registration is an important step when processing three-dimensional (3-D) point clouds. Applications for registration range from object modeling and tracking, to simultaneous localization and mapping (SLAM). This article presents the open-source point cloud library (PCL) and the tools available for point cloud registration. The PCL incorporates methods for the initial alignment of point clouds using a variety of local shape feature descriptors, as well as methods for refining initial alignments using different variants of the well-known iterative closest point (ICP) algorithm. This article provides an overview on registration algorithms, usage examples of their PCL implementations, and tips for their application. Since the choice and parameterization of the right algorithm for a particular type of data is one of the biggest problems in 3-D point cloud registration, we present three complete examples of data (and applications) and the respective registration pipeline in the PCL. These examples include dense red-green-blue-depth (RGB-D) point clouds acquired by consumer color and depth cameras, high-resolution laser scans from commercial 3-D scanners, and low-resolution sparse point clouds captured by a custom lightweight 3-D scanner on a microaerial vehicle (MAV).

Semantic parametric body shape estimation from noisy depth sequences

The paper proposes a complete framework for tracking and modeling articulated human bodies from sequences of range maps acquired from off-the-shelf depth cameras. In particular, we propose an original approach for fitting a pre-defined parametric shape model to depth data by exploiting the 3D body pose tracked through a sequence of range maps. To this goal, we make use of multiple types of constraints and cues embedded into a unique cost function, which is then efficiently minimized. Our framework is able to yield compact semantic tags associated to the estimated body shape by leveraging on semantic body modeling from MakeHuman and L1 relaxation, and relies on the tools and algorithms provided by the open source Point Cloud Library (PCL), representing a good integration of the functionalities available therein.

Real-time 3D semi-local surface patch extraction using GPGPU

Feature vectors can be anything from simple surface normals to more complex feature descriptors. Feature extraction is important to solve various computer vision problems: e.g. registration, object recognition and scene understanding. Most of these techniques cannot be computed online due to their complexity and the context where they are applied. Therefore, computing these features in real-time for many points in the scene is impossible. In this work, a hardware-based implementation of 3D feature extraction and 3D object recognition is proposed to accelerate these methods and therefore the entire pipeline of RGBD based computer vision systems where such features are typically used. The use of a GPU as a general purpose processor can achieve considerable speed-ups compared with a CPU implementation. In this work, advantageous results are obtained using the GPU to accelerate the computation of a 3D descriptor based on the calculation of 3D semi-local surface patches of partial views. This allows descriptor computation at several points of a scene in real-time. Benefits of the accelerated descriptor have been demonstrated in object recognition tasks. Source code will be made publicly available as contribution to the Open Source Point Cloud Library.