Ershuai Xu

Reliable registration of terrestrial laser scanning (TLS) data is needed to assemble spatially consistent three-dimensional observations of built and vegetated environments. Repetitive structures can generate mutually compatible false correspondences, causing locally plausible alignments that misplace entire scans. We propose a robust registration method built on a 4-degrees of freedom (4-DoF) consistency graph and a global sampling verification strategy. First, guided by the gravity prior, we construct a 4-DoF graph from initial correspondences using distance and inclination consistency, effectively suppressing distance-consistent but orientation-inconsistent spurious edges. Next, we extract key nodes and combine them with their neighbors to form 2-point congruent sets, from which a bounded set of transformation hypotheses is generated via an angle quantization strategy. Finally, we verify each hypothesis against globally sampled point clouds using cumulative truncated absolute residuals (CTAR), thereby rejecting transformations that are correspondence-consistent but globally incorrect. We evaluate our method on five repetitive scenes from the WHU-TLS benchmark and the ETH dataset. Results demonstrate that the proposed method achieves the highest or joint-highest successful registration rate (SRR) among state-of-the-art methods. Notably, on the highly repetitive 'Railway' scene, our method succeeds on five out of seven pairs, whereas all competing methods fail completely. Moreover, the proposed method attains 100% success on both the 'Arch' and 'Trees' scenes. The source code is planned to be released at https://github.com/MasterFlashQ/GSPCR.

Pile inventory is a common practice in terrestrial laser scanner applications. However, there are two main challenges when using the traditional terrestrial laser scanning (TLS) for pile inventory. One is the high cost and the other is the unreachability problem within a limited space. This letter develops a cost-effective system combining two single-pulse scanners and a rangefinder. The sensors are coupled together on a sliding rail to collect 3-D points for pile inventory. The proposed system is applied to an indoor scenario in a gold and copper open-pit mine. We investigate the effect of inclination angles on the point cloud. In addition, the generated point clouds are compared with those obtained by an advanced scanner in simultaneous localization and mapping configuration. The comparison shows higher completeness when using our proposed system. Cross-validation results show ~99.9% repeatability of the proposed system for pile inventory.

The registration of terrestrial point clouds is a crucial technique to obtaining the entire scene geometry. However, urban scenes, characterized by repetitive components, symmetrical structures, and object occlusion, pose ambiguity challenge of matches in the accurate registration of terrestrial point clouds. This article proposes a coarse registration approach using 2-lines congruent sets (2LCS) for urban point clouds. 3-D line features are extracted in the point clouds and classified into two categories according to directions. With that, a pair of 3-D line features from different categories is selected in the target point cloud to construct the 2-lines base with significant geometric characteristics. Next, the congruent 2-lines bases are identified in the source point cloud using geometric constraints, leading to the 2LCS. The 2LCS are then used to estimate the rigid motion between pairwise point cloud, leading to a set of candidate transformation parameters. The largest common point (LCP) set and maximum line structure consistency (MLSC) are integrated to evaluate the transformations. Finally, the procedure is repeated based on the RANSAC scheme to achieve optimal transformation values. We applied the proposed method to nine urban scenes with varying conditions and compared its performance with other state-of-the-art methods. The results show that our proposed approach is more robust for registering terrestrial point clouds in urban scenes with repetitive components, symmetrical structures, and limited overlap, leading to optimal or near-optimal results after fine registration optimization.

Social distancing protocols have been highly recommended by the World Health Organization (WHO) to curb the spread of COVID-19. However, one major challenge to enforcing social distancing in public areas is how to perceive people in three dimensions. This paper proposes an innovative pedestrian 3D localization method using monocular images combined with terrestrial point clouds. In the proposed approach, camera calibration is achieved based on the correspondences between 2D image points and 3D world points. The vertical coordinates of the ground plane where pedestrians stand are extracted from the point clouds. Then, using the assumption that the pedestrian is always perpendicular to the ground, the 3D coordinates of the pedestrian’s feet and head are calculated iteratively using collinear equations. This allows the three-dimensional localization and height determination of pedestrians using monocular cameras, which are widely distributed in many major cities. The performance of the proposed method was evaluated using two different datasets. Experimental results show that the pedestrian localization error of the proposed approach was less than one meter within tens of meters and performed better than other localization techniques. The proposed approach uses simple and efficient calculations, obtains accurate location, and can be used to implement social distancing rules. Moreover, since the proposed approach also generates accurate height values, exclusionary schemes to social distancing protocols, particularly the parent-child exemption, can be introduced in the framework.

Terrestrial laser scanning (TLS) techniques have been widely used in open-pit mine applications. It is a crucial task to measure the exploitative volume of open-pit mines, within a specific time interval. One major challenge is posed, however, when conducting accurate registrations for temporal TLS surveys in continuously changing areas, created by excavation activities. In this paper, we propose a coarse-to-fine registration method, based on terrain-invariant regions (TIR), for temporal TLS surveys. More specifically, an approximate four-point congruent set (4PCS) of temporal TLS surveys is first identified, based on affine invariant rules. Second, a set of correspondences among temporal TLS surveys were collected by matching multi-scale sparse features of the 3D neighbors, centered at the approximate 4PCS. Third, the correspondences were used to estimate a rigid motion between the overlapping TLS surveys for the coarse registration, according to which the initial TIR from temporal TLS surveys were identified. Finally, the rigid motion between temporal TLS was iteratively optimized, based on the point clouds, only from the TIR. Based on the fine-level registered TLS surveys, Digital Elevation Models (DEMs) can be generated to calculate the exploitative volume, through a DEM differential. We applied the proposed method to two open-pit mines in China, and also compared our method with five state-of-the-art methods for registering temporal TLS surveys. Experimental results indicated that the proposed method achieved a higher registration accuracy than the state-of-the-art methods. Based on the registered result, our method achieved a 98.03% overall accuracy for measuring the exploitative volume, compared to in-situ measurement.

The 4-points congruent sets (4PCS) techniques have widely been used for global registration of point clouds in terrestrial laser scanning (TLS) applications. Nevertheless, due to many 4PCS methods adopt a downsampling strategy in the collection of correspondences; it is challenging to obtain a real congruent set of tuples in different point clouds with varying density. This letter embeds multiscale sparse features (MSSF) into 4PCS to enable efficient global registration of TLS clouds. Specifically, multiscale clusters are used to extract point features, among which a sparse coding is performed to obtain the representative MSSF. The obtained MSSF are then embedded into the 4PCS variants, taking both geometrical structure and representative feature similarity into account when performing a four-point congruent tuples matching. Moreover, a normal constraint is considered in the selection of noncoplanar four-point bases rather than coplanar ones in the source cloud. This configuration decreases the number of four-point bases and thus improves the processing efficiency and registration accuracy. The proposed method was applied to two experiments with TLS point clouds from building and hillslope scenarios, respectively. In addition, the proposed MSSF configuration was embedded in two 4PCS variants, and compared with the original methods for global registration. The comparison shows evident improvements in terms of the registration accuracy and efficiency if our embedment is used.