With the remarkable progress of 3D scanning technique, the captured indoor scenes appear increasingly in last decade. Generating orientation-consistent normals for indoor point clouds is a fundamental and important task. The existing orientation rectification methods pay more attention to object-level targets with connected surface. However, it is challenging to compute consistent surface orientation for real scanned indoor point clouds. In this paper, we analyze the causes of this difficulty and propose a new normal reorienting framework for indoor scene consistency, namely NRSC. It first estimates normals for an indoor point cloud and extracts all the connected regions. We then design and construct an abstract orientation bridging tree (OBT) to organize the extracted regions in a hierarchical way. For all node regions, NRSC iteratively implements a set of orientation propagations to generate locally orientation-consistent regions. Moreover, we define an auxiliary viewpoint set for each pairwise parent-child node regions and introduce a voting mechanism to rectify the region orientation of child node according to its parent. After processing all the child node regions along OBT, we finally eliminate the orientation inconsistencies between related regions. Multi-groups of experimental results on both fused indoor scenes and single-view-scenes show that our method generates globally consistent orientation for indoor point clouds.

Identifying geometric features from sampled surfaces is a significant and fundamental task. The existing curvature-based methods that can identify ridge and valley features are generally sensitive to noise. Without requiring high-order differential operators, most statistics-based methods sacrifice certain extents of the feature descriptive powers in exchange for robustness. However, neither of these types of methods can treat the surface boundary features simultaneously. In this paper, we propose a novel neighbor reweighted local centroid (NRLC) computational algorithm to identify geometric features for point cloud models. It constructs a feature descriptor for the considered point via decomposing each of its neighboring vectors into two orthogonal directions. A neighboring vector starts from the considered point and ends with the corresponding neighbor. The decomposed neighboring vectors are then accumulated with different weights to generate the NRLC. With the defined NRLC, we design a probability set for each candidate feature point so that the convex, concave and surface boundary points can be recognized concurrently. In addition, we introduce a pair of feature operators, including assimilation and dissimilation, to further strengthen the identified geometric features. Finally, we test NRLC on a large body of point cloud models derived from different data sources. Several groups of the comparison experiments are conducted, and the results verify the validity and efficiency of our NRLC method.

Classifying tree species from point clouds acquired by light detection and ranging (LiDAR) scanning systems is important in many applications, including remote sensing, virtual reality, and forestry inventory. Compared with terrestrial laser scanning systems, airborne laser scanning (ALS) systems can acquire large-scale tree point clouds from only a single scan. However, ALS point clouds have the disadvantages of low density, uneven distribution, and unclear branch structure, making the classification of tree species from ALS point clouds a challenging task. Recently, deep learning-based classification approaches, such as PointNet++, which can operate directly on 3-D point sets, have been intensively studied in scene classification. However, the classification precision of learning-based approaches for point clouds relies on point coordinates and features, such as normals. Unlike the face normals of regular objects, trees have complex branch structures and detailed leaves, which are difficult to capture using ALS systems. Hence, it might be inappropriate to use the normals of ALS tree points for classification. In this letter, we propose a novel convex hull-based feature descriptor for tree species classification using the deep learning network PointNet++. To evaluate the effectiveness of our approach, three additional feature descriptors (normal descriptor, alpha shape-based descriptor, and covariance descriptor) are also investigated with PointNet++. The results show that the convex hull-based feature descriptor can achieve 86.6% overall accuracy in tree species classification, which is notably higher than the other three descriptors.

This paper aims to automate the process of generating a meaningful single still image from a temporal input of scene sequences. The success of our extraction relies on evaluating the optimal pose of characters selection, which should maximize the information conveyed. We define the information entropy of the still image candidates as the evaluation criteria.

In order to interpolate a given triangle mesh into G1smooth surface, in this paper, a new bi-cubic triangular Gregory patch is used. It guarantees G1continuity along common boundary only depending on boundary control points and corresponding interior control points of two adjacent triangular meshes. Some interpolated examples demonstrate that global G1smooth surfaces can be easily constructed by using the new bi-cubic triangular Gregory patch.