Automatic detection of unreinforced masonry buildings from street view images using deep learning-based image segmentation

Abstract Mitigation of seismic risk is a challenge for 70+ countries in the world. Screening the building stock for potential structural defects is one way to locate structures that are vulnerable to strong ground motion. Often in developing countries, masonry buildings are not reinforced or confined to withstand earthquake loads. It has been observed that such buildings cannot withstand the lateral loads imposed by an earthquake. An estimated 77 percent of the fatalities in the earthquakes during the last 100 years were caused mainly by the collapse of masonry buildings. Given the probability of severe damage or collapse in the event of an earthquake, identification and retrofit of such masonry buildings are critical. Screening of masonry buildings by conventional methods is usually a time-consuming and labor-intensive process. This research presents an automated workflow for segmenting the presence of such buildings through the use of street-view images. The method uses deep learning techniques. An inventory composed of a set of street view images was collected from the streets of Oaxaca State, Mexico using a 360° camera mounted on a car. These images were then annotated by trained engineers. Using the annotated dataset, an instance segmentation model was trained to detect and classify masonry buildings from the street view images. Using the model, we performed city scale detections of masonry buildings. We found the spatial distribution pattern of masonry buildings is correlated with the urbanization paths of the cities. The model could be used to produce large-scale automated detection of buildings at a fraction of the cost and in the fraction of the time of the alternatives. With affordable, accurate and massive screenings, governments can target these buildings for retrofit efforts and companies can assess the business opportunity of prevention (or “Building Better Before”).