Semantic Segmentation of Indoor Point Clouds Using Convolutional Neural Network

Abstract

ABSTRACT:As Building Information Modelling (BIM) thrives, geometry becomes no longer sufficient; an ever increasing variety of semantic information is needed to express an indoor model adequately. On the other hand, for the existing buildings, automatically generating semantically enriched BIM from point cloud data is in its infancy. The previous research to enhance the semantic content rely on frameworks in which some specific rules and/or features that are hand coded by specialists. These methods immanently lack generalization and easily break in different circumstances. On this account, a generalized framework is urgently needed to automatically and accurately generate semantic information. Therefore we propose to employ deep learning techniques for the semantic segmentation of point clouds into meaningful parts. More specifically, we build a volumetric data representation in order to efficiently generate the high number of training samples needed to initiate a convolutional neural network architecture. The feedforward propagation is used in such a way to perform the classification in voxel level for achieving semantic segmentation. The method is tested both for a mobile laser scanner point cloud, and a larger scale synthetically generated data. We also demonstrate a case study, in which our method can be effectively used to leverage the extraction of planar surfaces in challenging cluttered indoor environments.

Dynamically loading IFC models on a web browser based on spatial semantic partitioning

“…For example, Held et al [25] proposed a method that incorporates spatial, temporal, and semantic cues in a coherent probabilistic framework for spatial partitioning. Babacan et al [26] proposed a semantic segmentation method for indoor point clouds via a convolutional neural network. However, the aforementioned semantic partitioning methods mainly focused on extracting and generating semantic information for 3D data of shapes or scenes in their applications, and this is not appropriate for IFC models.…”

Automatic Generation of Semantically Rich As‐Built Building Information Models Using 2D Images: A Derivative‐Free Optimization Approach

“…Ad hoc surface fitting heuristics such as improved random sample consensus (RANSAC) (Schnabel et al., ; Lagüela et al., ) and parametric curved surfaces (Zhang et al., ; Dimitrov et al., ) are employed to segment expected surfaces from real‐world noisy data. Object recognition and machine learning techniques such as SVM (Adan and Huber, ; Koppula et al., ; Perez‐Perez et al., ; Wang et al., ) and convolutional neural networks (Babacan et al., ) are also adapted to identify semantic labels. Regarding directly generating BIM from images by using data‐driven methods, Criminisi et al.…”

“…Babacan et al. () found the precision of segmentation by deep learning varied from about 40% for beams to over 90% for walls and floors, recall varied from about 55% for doors to 99% for floors. In general, the generalization of computerized object recognition methods in the uncontrolled environments of real‐life scenarios can often be unsatisfactory (Andreopoulos and Tsotsos, ).…”

Detection of Indoor Attached Equipment From TLS Point Clouds Using Planar Region Boundary

“…To detect objects in the point clouds, recently, machine learning and classification can be used for several outdoor and indoor environments. After the supervised learning, the classifiers recognize scanned points of not only basic structures but also desks, chairs, and tables (Babacan et al, 2017, Qi et al, 2017a, Qi et al, 2017b, Su et al, 2018. Furthermore, model-based object recognition can be used for detecting specific shape objects from point clouds (Johnson, Hebert, 1999, Drost et al, 2010, Date et al, 2012, Salti et al, 2014.…”