Indoor–Outdoor Point Cloud Alignment Using Semantic–Geometric Descriptor

Abstract

Aligning indoor and outdoor point clouds is a challenging problem since the overlapping area is usually limited, thus resulting in a lack of correspondence features. The windows and doors can be observed from both sides and are usually utilized as shared features to make connections between indoor and outdoor models. However, the registration performance using the geometric features of windows and doors is limited due to the considerable number of extracted features and the mismatch of similar features. This paper proposed an indoor/outdoor alignment framework with a semantic feature matching method to solve the problem. After identifying the 3D window and door instances from the point clouds, a novel semantic–geometric descriptor (SGD) is proposed to describe the semantic information and the spatial distribution pattern of the instances. The best object match is identified with an improved Hungarian algorithm using indoor and outdoor SGDs. The matching method is effective even when the numbers of objects are not equal in the indoor and outdoor models, which is robust to measurement occlusions and feature outliers. The experimental results conducted in the collected dataset and the public dataset demonstrated that the proposed method could identify accurate object matches under complicated conditions, and the alignment accuracy reached the centimeter level.

Exploring Sensor Placement Optimization in Point Cloud-Derived Environment Models

“…An alternative approach identified indoor walls by projecting all points onto a floor plane and using distribution histograms with the Hough transform [15], [16]. This field has since been enriched with methods for room segmentation [17]- [20], opening detection [19]- [21], and reconstruction of curved elements [22] to gain more accurate space models. More recent approaches use machine learning methods to address more intricate edge cases in extracting a floorplan of an indoor environment from 3D scans with fewer restrictions and assumptions regarding the shape of the space [18], [23], [24].…”

Registration for Urban Modeling Based on Linear and Planar Features

“…Let us justify the distance (7). First, if all segments of S 2 are too far from s i (D(s i , s j ) ≥ d 2 ), all terms under the sum vanish and a nominal cost d 2 is paid.…”

“…The choice of planar polygons as appropriate attributes is grounded on the fact that they have a spatial extent limited to the areas where they have supporting points in the input data, so they form a good abstraction of the LiDAR scans. A semantic feature-matching method has been proposed in [7] to align an indoor and an outdoor point cloud. The basic idea is to include both the objects' semantic information and spatial distribution pattern by designing a semantic geometric descriptor (SGD).…”