Window detection in facade images for risk assessment in tunneling

Abstract

Background: Settlements induced by tunneling in inner urban areas can easily damage above ground structures. This already has to be considered in early planning of tunneling routes. Assessing the risk of damages to structures on hypothetical tunneling routes inflicted by such settlements beforehand enables routes' comparability. Hereby, it facilitates the choice of the optimal tunneling route in terms of potential damages and of suitable countermeasures. Risk analyses of structures establishing the assessment obtain relevant data from various sources. Some data even has to be gathered manually. Virtual building models could ease this process and facilitate analyses for entire districts as they combine several required information in a single data set. Commonly, these are yet modelled very coarse. Relevant details like facade openings, which highly affect a structures stiffness, are not included. Methods: In this paper, we propose a system which detects windows in facade images. This is used to subsequently enrich existing virtual building models allowing for a precise risk assessment. For this, we apply a sliding window detector which employs a cascaded classifier to obtain windows in images patches. Results: Our system yields sufficient results on facade images of several countries showing its general applicability despite regional and architectural variation in the facades' and windows' appearance. In an ensuing case study, we assess the risk of damages to structures based on detections of our system using different analysis methods. Conclusions: We contrast these results to assessments using manually gathered data. Hereby, we show that the detection rate of our proposed system is sufficient for a reliable estimation of a structure's damage class.

Cross Field-Based Segmentation and Learning-Based Vectorization for Rectangular Windows

“…All objects are annotated as rectangles, limited by the image scope in size and position, while overlap is allowed. This dataset has been widely used as benchmark for window detection or fac ¸ade segmentation tasks [64], [65], [66].…”

Detailed Three-Dimensional Building Façade Reconstruction: A Review on Applications, Data and Technologies

“…One of the important aspects considered by civil engineers is an assessment of the stiffness of buildings, the resistance of which can be weakened by ground movements (e.g., caused by underground construction or geohazards). In this case, information about building openings, and in particular windows, is considered since they affect the overall stiffness of the building structure [8,49,50]. Information on façade openings is also critical for evacuation planning and emergency response, where not only a geometrical representation of façade openings are essential, but also their semantic representations [4].…”

“…In that review, the methods are categorized into the following groups: grammar-based [137], image processing [138] and machine learning [122]. The same author has since focused on window detection from image data through a series of studies on window detection for risk assessment analysis [8,50,139].…”

“…Nevertheless, despite their usefulness, the publicly available 3D building models are often presented as coarse, solid blocks in most cases. Occasionally, these block models are augmented with simplified roof shapes and image texture [8]. However, details of the building openings (windows and doors) are often missing.…”

Comparison of Training Strategies for Convnets on Multiple Similar Datasets for Facade Segmentation

“…Rahmani et al (2017) used a Structured Random Forest (SRF) for pixel-wise labeling and extended their work in (Rahmani and Mayer, 2018) by adding proposals of a Region Proposal Network to the input of the SRF and by applying deterministic rectangular fitting. A sliding window detector, utilizing a cascade of weak classifiers, is proposed in (Neuhausen et al, 2018).…”