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

Abstract

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).

IFC BIM Model Enrichment with Space Function Information Using Graph Neural Networks

“…A recent paper by Paudel et al [21] solved room-type classification based on the floor plan data of single apartments using various graph neural networks. Hu et al [22] presented room-type classification based on the floor plans of university buildings using random forest and graph convolutional networks. All these studies report high (around 80%) classification accuracy.…”

Relational graph convolutional networks: a closer look

“… Mylavarapu et al (2020) have shown that spatial information for dynamic scene understanding can be encoded as relations between objects using RGCNs. RGCNs can complement traditional machine learning approaches by reasoning on contextual information ( Hu et al, 2021 ). Furthermore, RGCNs have contributed to the field of natural language processing by improving dependency tree extraction ( Guo et al, 2021 ).…”

Online Object-Oriented Semantic Mapping and Map Updating

“…Semantic maps describe the environment by assigning labels to detected features, which can be either objects [9]- [11] or more abstract places in the environment [4], [12]- [14]. The application areas of semantic maps range from small indoor environments [15] to whole buildings [16] up to outdoor environments, e.g., streets or parks [17].…”