Bounding-box object augmentation with random transformations for automated defect detection in residential building façades

Defects in residential building façades affect the structural integrity of buildings and degrade external appearances. Defects in a building façade are typically managed using manpower during maintenance. This approach is time-consuming, yields subjective results, and can lead to accidents or casualties. To address this, we propose a building façade monitoring system that utilizes an object detection method based on deep learning to efficiently manage defects by minimizing the involvement of manpower. The dataset used for training a deep-learning-based network contains actual residential building façade images. Various building designs in these raw images make it difficult to detect defects because of their various types and complex backgrounds. We employed the faster regions with convolutional neural network (Faster R-CNN) structure for more accurate defect detection in such environments, achieving an average precision (intersection over union (IoU) = 0.5) of 62.7% for all types of trained defects. As it is difficult to detect defects in a training environment, it is necessary to improve the performance of the network. However, the object detection network employed in this study yields an excellent performance in complex real-world images, indicating the possibility of developing a system that would detect defects in more types of building façades.

Download Full-text

Airborne Algal growth on roofs of membrane-structured residences in cold area of Japan

Journal of Building Physics ◽

10.1177/1744259120980034 ◽

2020 ◽

pp. 174425912098003

Author(s):

Makiko Nakajima ◽

Daisuke Masueda ◽

Shuichi Hokoi ◽

Takayuki Matsushita

Keyword(s):

Algal Growth ◽

Residential Building ◽

Growth Conditions ◽

Building Structure ◽

Transparent Film ◽

Cold Region ◽

Algal Population ◽

Building Facades ◽

Cold Area ◽

Survey Results

The discoloration of building facades due to airborne algae is observed in our surroundings. The growth conditions of these algae are not yet fully understood, and efficient measures for preventing the growth of the algae are not presently available. The objective of this study was to investigate the effects of the ambient environment and building structure on algal growth. A residential building in a cold region of Japan was surveyed. The roof was a multi-layered structure comprising a semi-transparent film, an air layer, and a layer of insulation from the outside, supported by rafters. The soiled state was visually observed by taking photographs. On the northeast (NE) and northwest (NW) roofs, several black stripes appeared 4 months after cleaning. The soiling increased in the spring and autumn. The soiling first appeared on the film backed by the rafter and then extended to the film backed by the air layer. The condensation time during the day in the rafter part was longer than that in the air-layer part. Condensation occurred during the night, but its frequency exhibited no dependence on the orientation of the roof. Algae tend to die when exposed to an environment with a temperature higher than 45°C. The NE roof had the shortest period with a surface temperature of >45°C. These measurements agreed well with the survey results, which indicated that the soiling mainly occurred on the NE and NW sides of the roofs. The time for algal growth was estimated under the assumption that algae can grow at surface temperatures ranging from 0 to 45°C, in agreement with the observed soiling. The observed soiling changes were well explained by the algal population calculated via a growth predictive model according to the algal temperature and relative humidity.

Download Full-text

Ventilated cladding systems: structural and drainability performance criteria

Ambiente Construído ◽

10.1590/s1678-86212018000300285 ◽

2018 ◽

Vol 18 (3) ◽

pp. 341-358 ◽

Cited By ~ 1

Author(s):

Luiz Fernando Batista da Silva ◽

Ercio Thomaz ◽

Luciana Alves de Oliveira

Keyword(s):

Vertical Wall ◽

Impact Resistance ◽

Residential Building ◽

Test Methods ◽

Performance Criteria ◽

Structural Safety ◽

Practical Case ◽

Performance Requirements ◽

Efficient Measure ◽

Building Facades

Abstract Cladding systems have significant effect on the performance and durability of building façades, contributing to the building watertightness, property valuation, aesthetic finishing, and decoration. Non-adherent cladding, also named rainscreen cladding or ventilated cladding, is currently used in residential and commercial buildings, new constructions, or retrofit operations, and it is considered an efficient measure to improve the moisture safety of building envelopes. Therefore, the absence of Brazilian normalization to ventilated cladding systems is one of the difficulties limiting its increased local application. In Brazil, a technical standard, NBR 15575, parts 1-6, (2013), establish the general performance requirements and test methods to evaluate residential building systems including structure, wall, floor, coverage, and hydraulic installation. However, this standard cannot be integrally applied to the cladding systems because it was developed considering the vertical wall system as a whole. In this study, we propose the criteria and test methods for assessing ventilated cladding systems while taking into account the structural safety (wind loads resistance, hard and soft impact resistance) and drainability requirements. The following activities are performed: literature review, practical case study, and tests on prototypes for validation of the proposal. The tests allow verification of the feasibility of the criteria and tests methods proposed. In addition, the proposal makes it possible to guide design, construction, and maintenance needs, thereby inducing the growth of this technology in Brazil.

Download Full-text

THE PHENOMENON OF REUSING ELEMENTS OF THE ITALIAN ARCHITECTURE STYLE IN THE 21 TH CENTURY CASE STUDY; RESIDENTIAL BUILDING FACADES AT ALEXANDRIA

JES. Journal of Engineering Sciences ◽

10.21608/jesaun.2017.116284 ◽

2017 ◽

Vol 45 (4) ◽

pp. 460-483

Author(s):

Mona Awad Alwazzir

Keyword(s):

Residential Building ◽

Building Facades ◽

Architecture Style ◽

Italian Architecture

Download Full-text

Influence of the Passive Design of a Building Facade on the Indoor Thermal Comfort of Residential Buildings

E3S Web of Conferences ◽

10.1051/e3sconf/202123703006 ◽

2021 ◽

Vol 237 ◽

pp. 03006

Author(s):

Pengfei Zhou ◽

Chi Zhang ◽

Jiang Wang

Keyword(s):

Thermal Comfort ◽

Thermal Environment ◽

Residential Buildings ◽

Residential Building ◽

Wall Material ◽

Design Strategies ◽

Indoor Thermal Comfort ◽

Building Facade ◽

Building Facades ◽

Passive Design

Building facades have evident effects on indoor thermal comfort. Hence, on the basis of a multifunctional residential building in Sydney, Australia, this research uses DesignBuilder software to optimize passive system design on building facades. This research also analyses the influences of changing window glazing type, adding additional shading devices and changing the material of the exterior wall on indoor thermal comfort. Results show that the number of uncomfortable hours can be reduced by 446, 186 and 874 hours by using a double-layer Low-E glass, adding extra shading device and adopting an external wall material with low thermal conductivity, respectively. When the three aforementioned passive design strategies are combined, indoor thermal environment discomfort time can be reduced by 24%. Therefore, the indoor thermal comfort of a building can be considerably improved through effective passive designs of the building facade.

Download Full-text

The Correlations between Building Heights and Wind Speed in Determining the Dimension of Windows in a High-rise Residential Building Façade

IOP Conference Series Earth and Environmental Science ◽

10.1088/1755-1315/903/1/012002 ◽

2021 ◽

Vol 903 (1) ◽

pp. 012002

Author(s):

S S Napitupulu ◽

G Hardiman ◽

RR Tobing

Keyword(s):

Residential Building ◽

Essential Factor ◽

Case Study Method ◽

High Rise ◽

Surrounding Environment ◽

Building Facades ◽

Technological Developments ◽

Wind Intensity ◽

Main Factor

Abstract Climate change due to architecture occurs as a result of technological developments that support the development of materials, electrical mechanics, structures, and building shapes that play a role in increasing emission levels in the air. One type of building in Indonesia that contributes to increasing emissions is the residential building known as rumah susun. This research employs the case study method, observing the Rumah Susun Jatinegara Barat, located in East Jakarta. The case study shows that the use of prototypes that are not environmentally friendly makes a building’s performance worse. The use of precast, which resulted in monotonous window dimensions, is considered the main factor causing the failure of this Rumah Susun Jatinegara Barat to adapt to the surrounding environment. This problem occurred because the openings in the building façades had a monotonous dimension while the wind intensity that hit the building was increasing. The final result shows that the windows on the façades of the case study were not functioning except if all the openings in the residential unit are open. These results prove that the height of a building is an essential factor in planning high-rise flats, especially in Jakarta.

Download Full-text

Simultaneous pixel-level concrete defect detection and grouping using a fully convolutional model

Structural Health Monitoring ◽

10.1177/1475921720985437 ◽

2021 ◽

pp. 147592172098543

Author(s):

Chaobo Zhang ◽

Chih-chen Chang ◽

Maziar Jamshidi

Keyword(s):

Deep Learning ◽

Defect Detection ◽

Visual Inspection ◽

Surface Defects ◽

Semantic Segmentation ◽

Input Image ◽

Image Size ◽

Bounding Box ◽

Proposed Model ◽

Image Pixels

Deep learning techniques have attracted significant attention in the field of visual inspection of civil infrastructure systems recently. Currently, most deep learning-based visual inspection techniques utilize a convolutional neural network to recognize surface defects either by detecting a bounding box of each defect or classifying all pixels on an image without distinguishing between different defect instances. These outputs cannot be directly used for acquiring the geometric properties of each individual defect in an image, thus hindering the development of fully automated structural assessment techniques. In this study, a novel fully convolutional model is proposed for simultaneously detecting and grouping the image pixels for each individual defect on an image. The proposed model integrates an optimized mask subnet with a box-level detection network, where the former outputs a set of position-sensitive score maps for pixel-level defect detection and the latter predicts a bounding box for each defect to group the detected pixels. An image dataset containing three common types of concrete defects, crack, spalling and exposed rebar, is used for training and testing of the model. Results demonstrate that the proposed model is robust to various defect sizes and shapes and can achieve a mask-level mean average precision ( mAP) of 82.4% and a mean intersection over union ( mIoU) of 75.5%, with a processing speed of about 10 FPS at input image size of 576 × 576 when tested on an NVIDIA GeForce GTX 1060 GPU. Its performance is compared with the state-of-the-art instance segmentation network Mask R-CNN and the semantic segmentation network U-Net. The comparative studies show that the proposed model has a distinct defect boundary delineation capability and outperforms the Mask R-CNN and the U-Net in both accuracy and speed.

Download Full-text