Floor Plan Images Research Articles

Predicting Signal Reception Information from GNSS Satellites in Indoor Environments without Site Survey: Towards Opportunistic Indoor Positioning Based on GNSS Fingerprinting

While traditional GPS localization is impractical in certain indoor environments, GPS satellites offer a valuable source of indoor contextual information, particularly around window-side areas where signals are more accessible. This study introduces a new method that predicts GPS signal reception information in a target indoor environment without the need for actual data collection in the target environment. By predicting the strengths of GPS signals that are expected to be measured at various indoor positions, we can construct a GPS signal reception map of a target environment, which functions similarly to a Wi-Fi fingerprinting map surrounding window-side areas, offering a new dimension in indoor positioning systems. For instance, it aids in the correction of accumulated errors in pedestrian dead reckoning (PDR) systems. Our proposed method leverages easily accessible inputs, including satellite location data, indoor floorplan image of the target floor, and 3D mapping of the surrounding buildings, to predict signal reception at each position in the target environment. We developed a specialized neural network, named multi-scale branch fusion network (MSBF-Net), designed to process and integrate data of varying scales, such as the floorplan image of the target environment and 3D map of the surrounding area obtained from Google Earth, with a specific focus on understanding the line-of-sight (LOS) and multi-path effects caused by internal obstacles and surrounding buildings. This advanced capability enables the network to effectively interpret complex signal interactions within urban environments, enhancing its predictive accuracy for GPS signal reception. The effectiveness of our method was rigorously evaluated using real-world environments. In addition, we employed our method to implement opportunistic GPS fingerprint-based indoor positioning, where position estimates are provided when a strong signal is observed from at least one satellite. Surprisingly, the positioning method achieved a positioning error of only 2.8 meters when a smartphone is close to window-side areas even though the method does not rely on labeled training data collected in a target environment and signal infrastructures installed in the target environment.

FloorDiffusion: Diffusion model-based conditional floorplan image generation method using parameter-efficient fine-tuning and image inpainting

The conditional generation of high-quality floorplan images using deep-learning methods is challenging because the generated floorplans are required to match specific conditions, such as floorplan silhouettes and spatial layouts. Recently, diffusion models have emerged as alternatives of conditional generative adversarial networks in image generation, offering higher image quality, pairing-free training datasets, and adaptability to various image domains via parameter fine-tuning of pretrained diffusion models. However, diffusion models are rarely used for floorplan generation because when fine-tuning them on image domains that were not learned in pretraining, such as floorplans, the quality of the generated images is poor and tuning takes a long time. This phenomenon arises from the so-called catastrophic forgetting problem, where traditional fine-tuning methods that update all parameters easily destroy the knowledge of pretrained diffusion models. To address this problem, we propose FloorDiffusion, a diffusion model-based conditional floorplan generation method. In this method, only a few key parameters of the pre-trained diffusion model are fine-tuned, which allows adaptation to the floorplan domain while retaining its useful knowledge. Then, the fine-tuned diffusion model performs conditional floorplan generation by inpainting the unfinished regions of the input conditional image. Comparative experiments with existing methods demonstrate that our method can produce more architecturally realistic floorplan images with up to 72 % image quality improvement. It can also generate various floorplan images for a single input condition image. Finally, ablation studies show that all components of the proposed method are essential for optimal operation.

Tape-Shaped, Multiscale, and Continuous-Readable Fiducial Marker for Indoor Navigation and Localization Systems.

The present study proposes a fiducial marker for location systems that uses computer vision. The marker employs a set of tape-shaped markers that facilitate their positioning in the environment, allowing continuous reading to cover the entire perimeter of the environment and making it possible to minimize interruptions in the location service. Because the marker is present throughout the perimeter of the environment, it presents hierarchical coding patterns that allow it to be robust against multiple detection scales. We implemented an application to help the user generate the markers with a floor plan image. We conducted two types of tests, one in a 3D simulation environment and one in a real-life environment with a smartphone. The tests made it possible to measure the performance of the tape-shaped marker with readings at multiple distances compared to ArUco, QRCode, and STag with detections at distances of 10 to 0.5 m. The localization tests in the 3D environment analyzed the time of marker detection during the journey from one room to another in positioning conditions (A) with the markers positioned at the baseboard of the wall, (B) with the markers positioned at camera height, and (C) with the marker positioned on the floor. The localization tests in real conditions allowed us to measure the time of detections in favorable conditions of detections, demonstrating that the tape-shaped-marker-detection algorithm is not yet robust against blurring but is robust against lighting variations, difficult angle displays, and partial occlusions. In both test environments, the marker allowed for detection at multiple scales, confirming its functionality.

Integrating Pix2Pix and computational fluid dynamics for enhanced indoor airflow prediction: A case study with wing-walls

Computational Fluid Dynamics (CFD) is often used for analyzing natural ventilation but is limited in early design stages due to its high computational demands and the need for detailed inputs. To overcome such limitations of CFD simulation, this paper proposes a method using a conditional Generative Adversarial Network (cGAN) based image-to-image translation (Pix2Pix) to predict the indoor airflow condition. Compared to other traditional machine learning models that predict averaged values like indoor air velocity, Pix2Pix can predict contour plot of indoor airflow for the given building floor plan image, which provides more intuitive feedback to designers. The proposed method was tested to understand indoor air movement caused by wing-walls attached to the windows. The model was trained using 1153 pairs of floor plan images, incorporating variations in window widths, wing-wall depth, wing-wall angle, wind speed, and wind direction. It achieved a prediction accuracy of 94 % and produced results in less than a second. Moreover, the model showed relatively better performance with the changes in windows and wing-walls properties rather than wind properties. This high performance indicates that Pix2Pix can serve as an efficient proxy model of conventional CFD simulations, helping designers optimize ventilation in building designs at an early stage without the need for complex inputs.

FVCap: An Approach to Understand Scanned Floor Plan Images Using Deep Learning and its Applications

FVCap: An Approach to Understand Scanned Floor Plan Images Using Deep Learning and its Applications

Quantification of Architects’ Expertise using Floor Plan Images of Detached Houses

Quantification of Architects’ Expertise using Floor Plan Images of Detached Houses

Extracting real estate values of rental apartment floor plans using graph convolutional networks

Access graphs that indicate adjacency relationships from the perspective of flow lines of rooms are extracted automatically from a large number of floor plan images of a family-oriented rental apartment complex in Osaka Prefecture, Japan, based on a recently proposed access graph extraction method with slight modifications. We define and implement a graph convolutional network (GCN) for access graphs and propose a model to estimate the real estate value of access graphs as the floor plan value. The model, which includes the floor plan value and hedonic method using other general explanatory variables, is used to estimate rents, and their estimation accuracies are compared. In addition, the features of the floor plan that explain the rent are analyzed from the learned convolution network. The results show that the proposed method significantly improves the accuracy of rent estimation compared to that of conventional models, and it is possible to understand the specific spatial configuration rules that influence the value of a floor plan by analyzing the learned GCN.

Emergency Floor Plan Digitization Using Machine Learning.

An increasing number of special-use and high-rise buildings have presented challenges for efficient evacuations, particularly in fire emergencies. At the same time, however, the use of autonomous vehicles within indoor environments has received only limited attention for emergency scenarios. To address these issues, we developed a method that classifies emergency symbols and determines their location on emergency floor plans. The method incorporates color filtering, clustering and object detection techniques to extract walls, which were used in combination to generate clean, digitized plans. By integrating the geometric and semantic data digitized with our method, existing building information modeling (BIM) based evacuation tools can be enhanced, improving their capabilities for path planning and decision making. We collected a dataset of 403 German emergency floor plans and created a synthetic dataset comprising 5000 plans. Both datasets were used to train two distinct faster region-based convolutional neural networks (Faster R-CNNs). The models were evaluated and compared using 83 floor plan images. The results show that the synthetic model outperformed the standard model for rare symbols, correctly identifying symbol classes that were not detected by the standard model. The presented framework offers a valuable tool for digitizing emergency floor plans and enhancing digital evacuation applications.

The power of progressive active learning in floorplan images for energy assessment

Floorplan energy assessments present a highly efficient method for evaluating the energy efficiency of residential properties without requiring physical presence. By employing computer modelling, an accurate determination of the building’s heat loss or gain can be achieved, enabling planners and homeowners to devise energy-efficient renovation or redevelopment plans. However, the creation of an AI model for floorplan element detection necessitates the manual annotation of a substantial collection of floorplans, which poses a daunting task. This paper introduces a novel active learning model designed to detect and annotate the primary elements within floorplan images, aiming to assist energy assessors in automating the analysis of such images–an inherently challenging problem due to the time-intensive nature of the annotation process. Our active learning approach initially trained on a set of 500 annotated images and progressively learned from a larger dataset comprising 4500 unlabelled images. This iterative process resulted in mean average precision score of 0.833, precision score of 0.972, and recall score of 0.950. We make our dataset publicly available under a Creative Commons license.

CB-SAGE: A novel centrality based graph neural network for floor plan classification

Graph Neural Networks (GNNs) have emerged as one of the most prominent research areas in accomplishing machine learning tasks over graphical networks. GNNs are prominently used in performing tasks like semi-supervised node classification, link prediction, and community detection. GraphSAGE is one of the most recent GNN models which is being used to accomplish these tasks. A floor plan is an architectural design of a building that represents various floor compartments. In this paper, we represent floor plan(s) as graph(s). We characterize floor room (compartment) classification as a node classification problem. We propose a variation of the traditional GraphSAGE (sample and aggregation) algorithm: Centrality based GraphSAGE (CB-SAGE), which captures the structural properties of the network. We use the average clustering coefficient and average betweenness centrality to capture structure properties. We compute CB scores for all the floor plan graphs. Top 70% nodes (based on CB scores) are selected for the training. During the training, we append the betweenness centrality score of each node as an additional feature in the feature matrix for the embedding process. We conduct experiments on the House-GAN dataset, which contains 1,43,184 vectorized floor plan images. The proposed method outperforms the current state-of-art models in accomplishing the task of floor plan classification. We compare our results with the traditional machine learning approach (MLP) and other GNN-based methods. Our approach achieves an accuracy of 96.70%, which is significantly (approximately 16%) higher than other state-of-the-art methods.

Route Planning for Emergency Evacuation Using Graph Traversal Algorithms

The automatic identification of various design elements in a floor-plan image has gained increasing attention in recent research. Emergency-evacuation applications can benefit greatly from automated floor-plan solutions, as they allow for the development of horizontal solutions instead of vertical solutions targeting a specific audience. In addition to that, current evacuation plans rely on static signs without taking into account the dynamic characteristics of each emergency case. This work aims to extract information from a floor-plan image and transform it into a graph that is used for pathfinding in an emergency evacuation. First, the basic elements of the floor-plan image, i.e., walls, rooms and doors, are identified. This is achieved using Panoptic-DeepLab, which is a state-of-the-art deep neural network for the panoptic segmentation of images, and it is available from DeepLab2, an image segmentation library. The neural network was trained using CubiCasa5K, a large-scale floor-plan image dataset containing 5000 samples, annotated into over 80 floor-plan object categories. Then, using the prediction of each pixel, a graph that shows how rooms and doors are connected is created. An application that presents this information in a user-friendly manner and provides graph editing capabilities was developed. Finally, the exits are set, and the optimal path for evacuation is calculated from each node using Dijkstra’s algorithm.

Optimal location and performance prediction of portable air cleaner in composite room shapes using convolutional neural network

Portable air cleaners are commonly used to eliminate hazardous indoor air pollutants such as particulate matters and infectious viruses. The effectiveness of portable air cleaners heavily relies on their installation location, which affects the patterns of airflow carrying the pollutants. Herein, we propose a methodology for optimizing the portable air cleaner placement to maximize its effectiveness using artificial intelligence technology. To build an artificial intelligence model, we obtained the data on airflow patterns for different room shapes and locations of the portable air cleaner through numerical simulations. We utilized floor-plan image data to simplify the handling of complex geometric information related to portable air cleaner placements. The artificial intelligence model extracted geometric features from the floor plan and predicted the effectiveness of the portable air cleaner. The predicted results revealed that the model recommended the location with the highest effectiveness as optimal. The artificial intelligence model achieved a high prediction accuracy of 91.2% and precisely determined the optimal location in rooms with varying shapes. This approach can elucidate the complex relationship between geometric placements and airflow characteristics. Furthermore, the artificial intelligence model can be used as a powerful decision-making tool for indoor air quality management in the building environment.

RC-Net: Row and Column Network with Text Feature for Parsing Floor Plan Images

RC-Net: Row and Column Network with Text Feature for Parsing Floor Plan Images

Floor Segmentation Approach Using FCM and CNN

Floor plans play an essential role in the architecture design and construction, which serves as an important communication tool between engineers, architects and clients. Automatic identification of various design elements in a floor plan image can improve work efficiency and accuracy. This paper proposed a method consists of two stages, Fuzzy C-Means (FCM) segmentation and Convolutional Neural Network (CNN) segmentation. In FCM stage, the given input image was partitioned into homogeneous regions based on similarity for merging. In CNN stage, the interactive information was introduced as markers of the object area and background area, which were input by the users to roughly indicate the position and main features of the object and background. The segmentation evaluation was measured using probabilistic rand index, variation of information, global consistency error, and boundary displacement error. Experiments were conducted on real dataset to evaluate performance of the proposed model. The experimental results revealed the proposed model was successful.

Subjective Functionality and Comfort Prediction for Apartment Floor Plans and Its Application to Intuitive Online Property Search

This paper presents a new user experience for online apartment search using functionality and comfort as query items. Specifically, it has three technical contributions. First, we present a new dataset on the perceived functionality and comfort scores of residential floor plans using nine question statements about the level of comfort, openness, privacy, etc. Second, we propose an algorithm to predict the scores from the floor plan images. Lastly, we implement a new apartment search system and conduct a large-scale usability study using crowdsourcing. The experimental results show that our apartment search system can provide a better user experience. To the best of our knowledge, this is the first work to propose a highly accurate machine learning model for predicting the subjective functionality and comfort of apartments.

Connecting the Portuguese system of evolutive housing with building information modeling: From analogical to digital methods

In Portugal, in the 1960s and 1970s, there was research concerning a system of the architectural design of housing for economically less favored populations, which related sociological information with analogical computational methods and culminated with its application in the Local Ambulatory Support Service (SAAL). This article presents the digitization process of these methods for the development of an architectural design system for social housing. The main goal is to improve methodological procedures for the original research and, specifically, to adapt them to computational design and modeling processes. To this end, this research transposed the aforementioned methodology into an algorithmic model that matches sociological information acquired from an online form with a database of social housing floor plan images to generate a building information modeling (BIM) directly from the selected image source. The result is an algorithmic model informed by sociological data linked with a BIM model to enable further rationalization of architectural design.

Deep learning-based text detection on architectural floor plan images

Architectural drawings are an important source of information for many construction-related tasks, as they contain geometric and semantic information about building parts. However, the manual extraction of room stamps and the insertion of such gleaned information into facility management systems is quite laborious and, thus, its automation is anticipated. In this paper, a method is proposed to detect and classify obscure or illegible text elements on legacy 2D architectural drawings of possibly poor quality. In contrast to existing approaches, a deep learning model is specifically trained for the task at hand rather than making use of transfer learning approaches. The resulting text snippets can be further processed with natural language processing tools to be fed into a facility management system automatically. Other conceivable applications include the extraction of drawing header information, material type or any additional text given on the drawing, to facilitate the enrichment of digital twins of existing structures with semantic data. To provide training data, two floor plan datasets are annotated in a consistent manner. The influence of different data augmentation techniques is investigated systematically. With regard to performance and efficiency, the presented method is compared to alternative tools for the task at hand.

Automatic Extraction of Indoor Spatial Information from Floor Plan Image: A Patch-Based Deep Learning Methodology Application on Large-Scale Complex Buildings

Automatic floor plan analysis has gained increased attention in recent research. However, numerous studies related to this area are mainly experiments conducted with a simplified floor plan dataset with low resolution and a small housing scale due to the suitability for a data-driven model. For practical use, it is necessary to focus more on large-scale complex buildings to utilize indoor structures, such as reconstructing multi-use buildings for indoor navigation. This study aimed to build a framework using CNN (Convolution Neural Networks) for analyzing a floor plan with various scales of complex buildings. By dividing a floor plan into a set of normalized patches, the framework enables the proposed CNN model to process varied scale or high-resolution inputs, which is a barrier for existing methods. The model detected building objects per patch and assembled them into one result by multiplying the corresponding translation matrix. Finally, the detected building objects were vectorized, considering their compatibility in 3D modeling. As a result, our framework exhibited similar performance in detection rate (87.77%) and recognition accuracy (85.53%) to that of existing studies, despite the complexity of the data used. Through our study, the practical aspects of automatic floor plan analysis can be expanded.

Towards Robust Object Detection in Floor Plan Images: A Data Augmentation Approach

Object detection is one of the most critical tasks in the field of Computer vision. This task comprises identifying and localizing an object in the image. Architectural floor plans represent the layout of buildings and apartments. The floor plans consist of walls, windows, stairs, and other furniture objects. While recognizing floor plan objects is straightforward for humans, automatically processing floor plans and recognizing objects is challenging. In this work, we investigate the performance of the recently introduced Cascade Mask R-CNN network to solve object detection in floor plan images. Furthermore, we experimentally establish that deformable convolution works better than conventional convolutions in the proposed framework. Prior datasets for object detection in floor plan images are either publicly unavailable or contain few samples. We introduce SFPI, a novel synthetic floor plan dataset consisting of 10,000 images to address this issue. Our proposed method conveniently exceeds the previous state-of-the-art results on the SESYD dataset with an mAP of 98.1%. Moreover, it sets impressive baseline results on our novel SFPI dataset with an mAP of 99.8%. We believe that introducing the modern dataset enables the researcher to enhance the research in this domain.

3DPlanNet: Generating 3D Models from 2D Floor Plan Images Using Ensemble Methods

Research on converting 2D raster drawings into 3D vector data has a long history in the field of pattern recognition. Prior to the achievement of machine learning, existing studies were based on heuristics and rules. In recent years, there have been several studies employing deep learning, but a great effort was required to secure a large amount of data for learning. In this study, to overcome these limitations, we used 3DPlanNet Ensemble methods incorporating rule-based heuristic methods to learn with only a small amount of data (30 floor plan images). Experimentally, this method produced a wall accuracy of more than 95% and an object accuracy similar to that of a previous study using a large amount of learning data. In addition, 2D drawings without dimension information were converted into ground truth sizes with an accuracy of 97% or more, and structural data in the form of 3D models in which layers were divided for each object, such as walls, doors, windows, and rooms, were created. Using the 3DPlanNet Ensemble proposed in this study, we generated 110,000 3D vector data with a wall accuracy of 95% or more from 2D raster drawings end to end.