Feasibility of Using Grammars to Infer Room Semantics

Hu, Xuke; Fan, Hongchao; Noskov, Alexey; Zipf, Alexander; Wang, Zhiyong; Shang, Jing

doi:10.3390/rs11131535

Cited by 9 publications

(9 citation statements)

References 58 publications

(80 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, procedural modeling is used by several researchers for façade modeling and indoor modeling, but in most cases they produce synthetic models for virtual cities and gaming applications (Aliaga, Demir, Benes, & Wand, 2016; Mathias, Martinović, Weissenberg, & Van Gool, 2011; Müller, Wonka, Haegler, Ulmer, & Van Gool, 2006). There are some recent examples for indoor modeling and using grammar which result in more complex models from point clouds (Dehbi, Hadiji, Gröger, Kersting, & Plümer, 2017; Tran, Khoshelham, Kealy, & Díaz‐Vilariño, 2019b; Tran & Khoshelham, 2020) or inferring the semantics of rooms (Hu et al, 2019), but none of these methods offer a complementary solution to check the correctness of the final model. Figure 1 illustrates the evolution of grammar applications from the early stage to this time.…”

Section: Scientific Backgroundmentioning

confidence: 99%

Consistency grammar for 3D indoor model checking

Nikoohemat

Diakité

Lehtola

et al. 2020

Transactions in GIS

View full text Add to dashboard Cite

Indoor 3D models are digital representations of building interiors reconstructed from scanned data acquired by laser scanners, digital depth (RGBD) cameras, and CAD drawings. Consequently, there is noise in the source data and a notable variety in the methods used to treat the noise and to process these data into reconstructed models. Alas, the correctness of these reconstructions and thus their suitability for a given application are uncertain. There is a lack of a robust base logic that would allow for controlling the consistency of these (automatically) generated models. Fortunately, correctness criteria are well‐defined through existing international standards. Hence, we propose a conceptual framework based on formal grammars to check the semantic, geometric, and topological consistency of a reconstructed 3D model. The proposed method proceeds in three steps to validate the model: (1) correctness checking of individual components; (2) consistency verification of instances’ interactions; and (3) model consistency check for targeted applications. Our method identifies the components in the model that violate the given rules derived from the current standards and expert knowledge. Ultimately, we propose a quantified formulation of our method that may be straightforwardly integrated into industrial‐level model checkers. The approach is independent of level of details and reconstruction method.

show abstract

Section: Scientific Backgroundmentioning

confidence: 99%

Consistency grammar for 3D indoor model checking

Nikoohemat

Diakité

Lehtola

et al. 2020

Transactions in GIS

View full text Add to dashboard Cite

show abstract

“…Hu et al. (2019) proposed inferring the room usage of university research buildings by using grammars and Bayesian inference based on geometric maps. The approach was evaluated based on 15 maps with 408 rooms and a promising tagging accuracy of 0.84 was achieved.…”

Section: Related Workmentioning

confidence: 99%

“…Most indoor venues do not have check‐in information. Hu et al (2019) proposed inferring the room usage of research buildings at universities by using grammars and Bayesian inference based on geometric maps. However, the grammar rules defined can only cover partial research buildings, and cannot be applied in other styles of research buildings.…”

Section: Introductionmentioning

confidence: 99%

Room semantics inference using random forest and relational graph convolutional networks: A case study of research building

Fan²,

Noskov

et al. 2020

Transactions in GIS

Self Cite

View full text Add to dashboard Cite

Semantically rich maps are the foundation of indoor location‐based services. Many map providers such as OpenStreetMap and automatic mapping solutions focus on the representation and detection of geometric information (e.g., shape of room) and a few semantics (e.g., stairs and furniture) but neglect room usage. To mitigate the issue, this work proposes a general room tagging method for public buildings, which can benefit both existing map providers and automatic mapping solutions by inferring the missing room usage based on indoor geometric maps. Two kinds of statistical learning‐based room tagging methods are adopted: traditional machine learning (e.g., random forests) and deep learning, specifically relational graph convolutional networks (R‐GCNs), based on the geometric properties (e.g., area), topological relationships (e.g., adjacency and inclusion), and spatial distribution characteristics of rooms. In the machine learning‐based approach, a bidirectional beam search strategy is proposed to deal with the issue that the tag of a room depends on the tag of its neighbors in an undirected room sequence. In the R‐GCN‐based approach, useful properties of neighboring nodes (rooms) in the graph are automatically gathered to classify the nodes. Research buildings are taken as examples to evaluate the proposed approaches based on 130 floor plans with 3,330 rooms by using fivefold cross‐validation. The experiments conducted show that the random forest‐based approach achieves a higher tagging accuracy (0.85) than R‐GCN (0.79).

show abstract

“…The idea of this study is inspired by the fact that there exists strong association between the spatial (particular building) elements in the real world as the buildings are man-made structures that are constructed with plans made by people. That is, given partial spatial elements, the other element can be inferred based on the association relationship (Hu, Fan, and Noskov 2018;Hu et al 2019Hu et al , 2020. Intuitively, the entrance is associated with two kinds of spatial elements: (1) The location of the main entrance of a public building is correlated with the shape of its footprint.…”

Section: Introductionmentioning

confidence: 99%

Tagging the main entrances of public buildings based on OpenStreetMap and binary imbalanced learning

Noskov

Fan

et al. 2021

International Journal of Geographical Information Science

Self Cite

View full text Add to dashboard Cite

The entrance of buildings is an important feature that connects their internal and external environments. Most frequently, automatic approaches for detecting building entrances are based on street-level images, which, however, are not widely available. To address this issue, we propose a more general approach for inferring the location of the main entrance of public buildings based on the association between spatial elements extracted from OpenStreetMap. In particular, we adopt three binary classification approaches: Weighted Random Forest, Balanced Random Forest, and SmoteBoost to model the association relationship. The features considered in the classification are of two types: (1) intrinsic features derived from the footprint, such as the distance to the centroid of the footprint, and (2) extrinsic features derived from spatial contexts, such as the shortest path distance to the main roads. Extensive experiments have been conducted on 320 public buildings with an average perimeter of 350 meters. The experimental results showed that a mean linear distance error of 21 meters and a mean path distance error of 22 meters were achieved by using the Weighted Random Forest and Balanced Random Forest models, ruling out 90% of the incorrect locations of the main entrance at buildings. Our work finds relevance, for example, in saving pedestrians' way-finding efforts.

show abstract

Feasibility of Using Grammars to Infer Room Semantics

Cited by 9 publications

References 58 publications

Consistency grammar for 3D indoor model checking

Consistency grammar for 3D indoor model checking

Room semantics inference using random forest and relational graph convolutional networks: A case study of research building

Tagging the main entrances of public buildings based on OpenStreetMap and binary imbalanced learning

Contact Info

Product

Resources

About