Management of UAV-Captured Data for Building Facade Inspections

Building facades, serving mainly to protect occupants and structural components from natural forces, require periodic inspections for the detection and assessment of building façade anomalies. Over the past years, a growing trend of utilizing camera-equipped drones for periodical building facade inspection has emerged. Building façade anomalies, such as cracks and erosion, can be detected through analyzing drone-captured video, photographs, and infrared images. Such anomalies are known to have an impact on various building performance aspects, e.g., thermal, energy, moisture control issues. Current research efforts mainly focus on the design of drone flight schema for building inspection, 3D building model reconstruction through drone-captured images, and the detection of specific façade anomalies with these images. However, there are several research gaps impeding the improvement of automation level during the processes of building façade inspection with UAS (Unmanned Aerial System). These gaps are (1) lack the fusion of multi-type data captured by drones for cyclic façade inspections, (2) lack the management of large amounts and multi-media inspection information collected by drones, and (3) lack the accesses to image-based tools for the detection of building façade anomalies with drone-captured image data. Meanwhile, when seeking inspirations from nature, the process of drone-based facade inspection can be compared with some biological behaviors such as birds’ foraging food (worms, seeds) and visual sensing. This dissertation aims at investigating ways to improve the data management of UAS-based periodic façade inspection through these three aspects with the inspirations from the biology field. To achieve this goal, a 2D spatial model for building façades is developed for the fusion of diverse UAS-captured images based on their spatial information inspired by caching birds’ spatial memory. Secondly, a database for the management of UAS-collected spatial, temporal, and multimedia data will be designed with the reference of data management in the bioinformatics field. Thirdly, computational methods like computer vision, which is inspired by biological vision, and machine learning will be reviewed and tested for the automatic detection of different types of façade anomalies. This research will improve the capabilities of data query and data analysis of UAS-based cyclic façade inspection during a building’s service life. It has promising potential for supporting decision-makings of the building façade maintenance to prevent façade failures and improve building performance.

Funded by

Internal

Duration

2016-2020

Linked Faculty & Students

Doctoral Student
2016 - 2020

Professor, Department of Building Construction

Associate Professor, School of Architecture + Design