Dessislava Petrova-Antonova

Delineating and modelling building roof plane structures is an active research direction in urban-related studies, as understanding roof structure provides essential information for generating highly detailed 3D building models. Traditional deep-learning models have been the main focus of most recent research endeavors aiming to extract pixel-based building roof plane areas from remote-sensing imagery. However, significant challenges arise, such as delineating complex roof boundaries and invisible boundaries. Additionally, challenges during the post-processing phase, where pixel-based building roof plane maps are vectorized, often result in polygons with irregular shapes. In order to address this issue, this study explores a state-of-the-art method for planar graph reconstruction applied to building roof plane extraction. We propose a framework for reconstructing regularized building roof plane structures using aerial imagery and cadastral information. Our framework employs a holistic edge classification architecture based on an attention-based neural network to detect corners and edges between them from aerial imagery. Our experiments focused on three distinct study areas characterized by different roof structure topologies: the Stadsveld–‘t Zwering neighborhood and Oude Markt area, located in Enschede, The Netherlands, and the Lozenets district in Sofia, Bulgaria. The outcomes of our experiments revealed that a model trained with a combined dataset of two different study areas demonstrated a superior performance, capable of delineating edges obscured by shadows or canopy. Our experiment in the Oude Markt area resulted in building roof plane delineation with an F-score value of 0.43 when the model trained on the combined dataset was used. In comparison, the model trained only on the Stadsveld–‘t Zwering dataset achieved an F-score value of 0.37, and the model trained only on the Lozenets dataset achieved an F-score value of 0.32. The results from the developed approach are promising and can be used for 3D city modelling in different urban settings.

People tend to spend the majority of their time indoors. Indoor air properties can significantly affect humans’ comfort, health, and productivity. This study utilizes measurement data of indoor conditions in a kindergarten in Sofia, Bulgaria. Autoregressive integrated moving average (ARIMA) and long short-term memory (LSTM) recurrent neural network (RNN) models were developed to predict CO2 levels in the educational facility over the next hour based on 2.5 h of past data and allow for near real-time decision-making. The better-performing model, LSTM, is also used for temperature and relative humidity forecasting. Global comfort is then estimated based on threshold values for temperature, humidity, and CO2. The predicted R2 values ranged between 0.938 and 0.981 for the three parameters, while the prediction of global comfort conditions achieved a 91/100 accuracy.