CubiCasa5K: A Dataset and an Improved Multi-task Model for Floorplan Image Analysis

Kalervo, Ahti; Ylioinas, Juha; Häikiö, Markus; Karhu, Antti; Kannala, Juho

doi:10.1007/978-3-030-20205-7_3

Cited by 78 publications

(57 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The IoU metric obtained on the test set of source data presented in our dataset is presented in Table 3 . The results of training on the public floor plan dataset [ 20 ] are also presented. The public dataset contains 5000 images with labels for segmentation; 1000 of them were used for training, 200 for validation, and 3800 for testing.…”

Section: Methodsmentioning

confidence: 99%

Floor Plan Recognition and Vectorization Using Combination UNet, Faster-RCNN, Statistical Component Analysis and Ramer-Douglas-Peucker

Surikov

Nakhatovich

Belyaev

et al. 2020

Communications in Computer and Information Science

View full text Add to dashboard Cite

The floor plan recognition and vectorization problem from the image has a high market response due to the ability to be applied in such domains as design, automatic furniture fitting, property cost estimation, etc. Several approaches already exist on the market. Many of them are using just statistical or deep machine learning methods capable of recognizing a limited set of floor plan types or providing a semi-automatic tool for recognition. This paper introduces the approach based on the combination of statistical image processing methods in a row of machine learning techniques that allow training robust model for the different floor plan topologies. Faster R-CNN for the floor object detection with a mean average precision of 86% and UNet for the wall segmentation has shown the IoU metric results of about 99%. Both methods, combined with functional and component filtration, made it possible to implement the new approach for vectoring the floor plans.

show abstract

Section: Methodsmentioning

confidence: 99%

Floor Plan Recognition and Vectorization Using Combination UNet, Faster-RCNN, Statistical Component Analysis and Ramer-Douglas-Peucker

Surikov

Nakhatovich

Belyaev

et al. 2020

Communications in Computer and Information Science

View full text Add to dashboard Cite

show abstract

“…The CubiCasa5K [28] (CubiCasa) dataset consists of 5000 different apartment floor plans. The quality of the floor plan images varies from clean, noise-free ones to scribbled or noisy ones.…”

Section: Datasetsmentioning

confidence: 99%

Framework for Indoor Elements Classification via Inductive Learning on Floor Plan Graphs

Song

2021

IJGI

View full text Add to dashboard Cite

This paper presents a new framework to classify floor plan elements and represent them in a vector format. Unlike existing approaches using image-based learning frameworks as the first step to segment the image pixels, we first convert the input floor plan image into vector data and utilize a graph neural network. Our framework consists of three steps. (1) image pre-processing and vectorization of the floor plan image; (2) region adjacency graph conversion; and (3) the graph neural network on converted floor plan graphs. Our approach is able to capture different types of indoor elements including basic elements, such as walls, doors, and symbols, as well as spatial elements, such as rooms and corridors. In addition, the proposed method can also detect element shapes. Experimental results show that our framework can classify indoor elements with an F1 score of 95%, with scale and rotation invariance. Furthermore, we propose a new graph neural network model that takes the distance between nodes into account, which is a valuable feature of spatial network data.

show abstract

“…CubiCasa5K [29] (CubiCasa) dataset consists of 5000 different apartment floor plans. The quality of the floor plan images varies from clean, noise-free ones to scribbled or noisy ones.…”

Section: Datasetsmentioning

confidence: 99%

Framework for Indoor Elements Classification via Inductive Learning on Floor Plan Graphs

Song¹,

Yu²

2021

Preprint

View full text Add to dashboard Cite

This paper presents a new framework to classify floor plan elements and represent them in a vector format. Unlike existing approaches using image-based learning frameworks as the first step to segment the image pixels, we first convert the input floor plan image into vector data and utilize graph neural network. Our framework consists of three steps. (1) image pre-processing and vectorization of the floor plan image. (2) region adjacency graph conversion. (3) graph neural network on converted floor plan graphs. Our approach is able to capture different types of indoor elements including basic elements such as walls, doors, and symbols as well as spatial elements such as rooms and corridors. In addition, the proposed method can also detect element shapes. Experimental results show that our framework can classify indoor elements with an F1 score of 95%, with scale and rotation invariance. Furthermore, we propose a new graph neural network model that takes the distance between nodes into account, which is a valuable feature of spatial network data.

show abstract

CubiCasa5K: A Dataset and an Improved Multi-task Model for Floorplan Image Analysis

Cited by 78 publications

References 18 publications

Floor Plan Recognition and Vectorization Using Combination UNet, Faster-RCNN, Statistical Component Analysis and Ramer-Douglas-Peucker

Floor Plan Recognition and Vectorization Using Combination UNet, Faster-RCNN, Statistical Component Analysis and Ramer-Douglas-Peucker

Framework for Indoor Elements Classification via Inductive Learning on Floor Plan Graphs

Framework for Indoor Elements Classification via Inductive Learning on Floor Plan Graphs

Contact Info

Product

Resources

About