Registration of Laser Scanning Point Clouds: A Review
TL;DR: A comprehensive review of LiDAR data registration in the fields of photogrammetry and remote sensing is presented, and the lack of standard data and unified evaluation systems is identified as a factor limiting objective comparison of different methods.
Abstract: The integration of multi-platform, multi-angle, and multi-temporal LiDAR data has become important for geospatial data applications. This paper presents a comprehensive review of LiDAR data registration in the fields of photogrammetry and remote sensing. At present, a coarse-to-fine registration strategy is commonly used for LiDAR point clouds registration. The coarse registration method is first used to achieve a good initial position, based on which registration is then refined utilizing the fine registration method. According to the coarse-to-fine framework, this paper reviews current registration methods and their methodologies, and identifies important differences between them. The lack of standard data and unified evaluation systems is identified as a factor limiting objective comparison of different methods. The paper also describes the most commonly-used point cloud registration error analysis methods. Finally, avenues for future work on LiDAR data registration in terms of applications, data, and technology are discussed. In particular, there is a need to address registration of multi-angle and multi-scale data from various newly available types of LiDAR hardware, which will play an important role in diverse applications such as forest resource surveys, urban energy use, cultural heritage protection, and unmanned vehicles.
Citations
More filters
TL;DR: A thorough review of terrestrial laser scanner point cloud registration methods in terms of pairwise coarse registration, pairwise fine registration, and multiview registration, as well as analyzing their strengths, weaknesses, and future research trends are conducted.
Abstract: This study had two main aims: (1) to provide a comprehensive review of terrestrial laser scanner (TLS) point cloud registration methods and a better understanding of their strengths and weaknesses; and (2) to provide a large-scale benchmark data set (Wuhan University TLS: Whu-TLS) to support the development of cutting-edge TLS point cloud registration methods, especially deep learning-based methods. In particular, we first conducted a thorough review of TLS point cloud registration methods in terms of pairwise coarse registration, pairwise fine registration, and multiview registration, as well as analyzing their strengths, weaknesses, and future research trends. We then reviewed the existing benchmark data sets (e.g., ETH Dataset and Robotic 3D Scanning Repository) for TLS point cloud registration and summarized their limitations. Finally, a new benchmark data set was assembled from 11 different environments (i.e., subway station, high-speed railway platform, mountain, forest, park, campus, residence, riverbank, heritage building, underground excavation, and tunnel environments) with variations in the point density, clutter, and occlusion. In addition, we summarized future research trends in this area, including auxiliary data-guided registration, deep learning-based registration, and multi-temporal point cloud registration.
186 citations
TL;DR: A semi-automatic and target-less method for coarse registration of point clouds using geometric constraints of voxel-based 4-plane congruent sets (V4PCS), which can be effective for registering point clouds acquired from various scenes and is more efficient than other baseline methods when using the same hardware and software configuration conditions.
Abstract: To ensure complete coverage when measuring a large-scale urban area, pairwise registration between point clouds acquired via terrestrial laser scanning or stereo image matching is usually necessary when there is insufficient georeferencing information from additional GNSS and INS sensors. In this paper, we propose a semi-automatic and target-less method for coarse registration of point clouds using geometric constraints of voxel-based 4-plane congruent sets (V4PCS). The planar patches are firstly extracted from voxelized point clouds. Then, the transformation invariant, 4-plane congruent sets are constructed from extracted planar surfaces in each point cloud. Initial transformation parameters between point clouds are estimated via corresponding congruent sets having the highest registration scores in the RANSAC process. Finally, a closed-form solution is performed to achieve optimized transformation parameters by finding all corresponding planar patches using the initial transformation parameters. Experimental results reveal that our proposed method can be effective for registering point clouds acquired from various scenes. A success rate of better than 80% was achieved, with average rotation errors of about 0.5 degrees and average translation errors less than approximately 0.6 m. In addition, our proposed method is more efficient than other baseline methods when using the same hardware and software configuration conditions.
80 citations
14 Jun 2020
TL;DR: Wang et al. as discussed by the authors proposed a fast feature-metric point cloud registration framework, which enforces the optimisation of registration by minimising a featuremetric projection error without correspondences.
Abstract: We present a fast feature-metric point cloud registration framework, which enforces the optimisation of registration by minimising a feature-metric projection error without correspondences. The advantage of the feature-metric projection error is robust to noise, outliers and density difference in contrast to the geometric projection error. Besides, minimising the feature-metric projection error does not need to search the correspondences so that the optimisation speed is fast. The principle behind the proposed method is that the feature difference is smallest if point clouds are aligned very well. We train the proposed method in a semi-supervised or unsupervised approach, which requires limited or no registration label data. Experiments demonstrate our method obtains higher accuracy and robustness than the state-of-the-art methods. Besides, experimental results show that the proposed method can handle significant noise and density difference, and solve both same-source and cross-source point cloud registration.
79 citations
TL;DR: A comprehensive survey of urban applications and key techniques based on MLS point clouds is conducted, including classification methods, object recognition, data registration, data fusion, and 3D city modeling.
Abstract: Urban planning and management need accurate three-dimensional (3D) data such as light detection and ranging (LiDAR) point clouds. The mobile laser scanning (MLS) data, with up to millimeter-level accuracy and point density of a few thousand points/m2, have gained increasing attention in urban applications. Substantial research has been conducted in the past decade. This paper conducted a comprehensive survey of urban applications and key techniques based on MLS point clouds. We first introduce the key characteristics of MLS systems and the corresponding point clouds, and present the challenges and opportunities of using the data. Next, we summarize the current applications of using MLS over urban areas, including transportation infrastructure mapping, building information modeling, utility surveying and mapping, vegetation inventory, and autonomous vehicle driving. Then, we review common key issues for processing and analyzing MLS point clouds, including classification methods, object recognition, data registration, data fusion, and 3D city modeling. Finally, we discuss the future prospects for MLS technology and urban applications.
75 citations
Cites background from "Registration of Laser Scanning Poin..."
...Cheng et al. (2015, 2018) proposed a hierarchical, coarse-to-fine registration strategy for registering laser scanning point clouds [122,123]....
[...]
TL;DR: A thorough mixed scientometric and state-of-the-art review on the application of terrestrial laser scanners (TLS) in bridge engineering and explore investigations and recommendations of researchers in this area is provided.
Abstract: Over the last decade, particular interest in using state-of-the-art emerging technologies for inspection, assessment, and management of civil infrastructures has remarkably increased. Advanced technologies, such as laser scanners, have become a suitable alternative for labor intensive, expensive, and unsafe traditional inspection and maintenance methods, which encourage the increasing use of this technology in construction industry, especially in bridges. This paper aims to provide a thorough mixed scientometric and state-of-the-art review on the application of terrestrial laser scanners (TLS) in bridge engineering and explore investigations and recommendations of researchers in this area. Following the review, more than 1500 research publications were collected, investigated and analyzed through a two-fold literature search published within the last decade from 2010 to 2020. Research trends, consisting of dominated sub-fields, co-occurrence of keywords, network of researchers and their institutions, along with the interaction of research networks, were quantitatively analyzed. Moreover, based on the collected papers, application of TLS in bridge engineering and asset management was reviewed according to four categories including (1) generation of 3D model, (2) quality inspection, (3) structural assessment, and (4) bridge information modeling (BrIM). Finally, the paper identifies the current research gaps, future directions obtained from the quantitative analysis, and in-depth discussions of the collected papers in this area.
72 citations
References
More filters
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Abstract: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a substantial range of affine distortion, change in 3D viewpoint, addition of noise, and change in illumination. The features are highly distinctive, in the sense that a single feature can be correctly matched with high probability against a large database of features from many images. This paper also describes an approach to using these features for object recognition. The recognition proceeds by matching individual features to a database of features from known objects using a fast nearest-neighbor algorithm, followed by a Hough transform to identify clusters belonging to a single object, and finally performing verification through least-squares solution for consistent pose parameters. This approach to recognition can robustly identify objects among clutter and occlusion while achieving near real-time performance.
46,906 citations
TL;DR: New results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form that provide the basis for an automatic system that can solve the Location Determination Problem under difficult viewing.
Abstract: A new paradigm, Random Sample Consensus (RANSAC), for fitting a model to experimental data is introduced. RANSAC is capable of interpreting/smoothing data containing a significant percentage of gross errors, and is thus ideally suited for applications in automated image analysis where interpretation is based on the data provided by error-prone feature detectors. A major portion of this paper describes the application of RANSAC to the Location Determination Problem (LDP): Given an image depicting a set of landmarks with known locations, determine that point in space from which the image was obtained. In response to a RANSAC requirement, new results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form. These results provide the basis for an automatic system that can solve the LDP under difficult viewing
23,396 citations
"Registration of Laser Scanning Poin..." refers methods in this paper
...Random sample consensus (RANSAC) methods were proposed by Fischler and Bolles [128], and have been widely used in 2D and 3D data processing; they have also been studied for use in image registration [129–132]....
[...]
...Random Sample Consensus Methods Random sample consensus (RANSAC) methods were proposed by Fischler and Bolles [128], and have been widely used in 2D and 3D data processing; they have also been studied for use in image registration [129–132]....
[...]
TL;DR: In this paper, the authors describe a general-purpose representation-independent method for the accurate and computationally efficient registration of 3D shapes including free-form curves and surfaces, based on the iterative closest point (ICP) algorithm, which requires only a procedure to find the closest point on a geometric entity to a given point.
Abstract: The authors describe a general-purpose, representation-independent method for the accurate and computationally efficient registration of 3-D shapes including free-form curves and surfaces. The method handles the full six degrees of freedom and is based on the iterative closest point (ICP) algorithm, which requires only a procedure to find the closest point on a geometric entity to a given point. The ICP algorithm always converges monotonically to the nearest local minimum of a mean-square distance metric, and the rate of convergence is rapid during the first few iterations. Therefore, given an adequate set of initial rotations and translations for a particular class of objects with a certain level of 'shape complexity', one can globally minimize the mean-square distance metric over all six degrees of freedom by testing each initial registration. One important application of this method is to register sensed data from unfixtured rigid objects with an ideal geometric model, prior to shape inspection. Experimental results show the capabilities of the registration algorithm on point sets, curves, and surfaces. >
17,598 citations
TL;DR: A review of recent as well as classic image registration methods to provide a comprehensive reference source for the researchers involved in image registration, regardless of particular application areas.
6,842 citations
TL;DR: This paper organizes this material by establishing the relationship between the variations in the images and the type of registration techniques which can most appropriately be applied, and establishing a framework for understanding the merits and relationships between the wide variety of existing techniques.
Abstract: Registration is a fundamental task in image processing used to match two or more pictures taken, for example, at different times, from different sensors, or from different viewpoints. Virtually all large systems which evaluate images require the registration of images, or a closely related operation, as an intermediate step. Specific examples of systems where image registration is a significant component include matching a target with a real-time image of a scene for target recognition, monitoring global land usage using satellite images, matching stereo images to recover shape for autonomous navigation, and aligning images from different medical modalities for diagnosis.Over the years, a broad range of techniques has been developed for various types of data and problems. These techniques have been independently studied for several different applications, resulting in a large body of research. This paper organizes this material by establishing the relationship between the variations in the images and the type of registration techniques which can most appropriately be applied. Three major types of variations are distinguished. The first type are the variations due to the differences in acquisition which cause the images to be misaligned. To register images, a spatial transformation is found which will remove these variations. The class of transformations which must be searched to find the optimal transformation is determined by knowledge about the variations of this type. The transformation class in turn influences the general technique that should be taken. The second type of variations are those which are also due to differences in acquisition, but cannot be modeled easily such as lighting and atmospheric conditions. This type usually effects intensity values, but they may also be spatial, such as perspective distortions. The third type of variations are differences in the images that are of interest such as object movements, growths, or other scene changes. Variations of the second and third type are not directly removed by registration, but they make registration more difficult since an exact match is no longer possible. In particular, it is critical that variations of the third type are not removed. Knowledge about the characteristics of each type of variation effect the choice of feature space, similarity measure, search space, and search strategy which will make up the final technique. All registration techniques can be viewed as different combinations of these choices. This framework is useful for understanding the merits and relationships between the wide variety of existing techniques and for assisting in the selection of the most suitable technique for a specific problem.
4,769 citations