Towards Detecting Building Facades with Graffiti Artwork Based on Street View Images

Abstract

As a recognized type of art, graffiti is a cultural asset and an important aspect of a city’s aesthetics. As such, graffiti is associated with social and commercial vibrancy and is known to attract tourists. However, positional uncertainty and incompleteness are current issues of open geo-datasets containing graffiti data. In this paper, we present an approach towards detecting building facades with graffiti artwork based on the automatic interpretation of images from Google Street View (GSV). It starts with the identification of geo-tagged photos of graffiti artwork posted on the photo sharing media Flickr. GSV images are then extracted from the surroundings of these photos and interpreted by a customized, i.e., transfer learned, convolutional neural network. The compass heading of the GSV images classified as containing graffiti artwork and the possible positions of their acquisition are considered for scoring building facades according to their potential of containing the artwork observable in the GSV images. More than 36,000 GSV images and 5000 facades from buildings represented in OpenStreetMap were processed and evaluated. Precision and recall rates were computed for different facade score thresholds. False-positive errors are caused mostly by advertisements and scribblings on the building facades as well as by movable objects containing graffiti artwork and obstructing the facades. However, considering higher scores as threshold for detecting facades containing graffiti leads to the perfect precision rate. Our approach can be applied for identifying previously unmapped graffiti artwork and for assisting map contributors interested in the topic. Furthermore, researchers interested on the spatial correlations between graffiti artwork and socio-economic factors can profit from our open-access code and results.

Digital Humanities, Corpus and Language Technology: A look from diverse case studies

“…Piero Fevere tapestry (Dal Fovo, et al, 2020), on detecting the presence of graffiti art on building facades using Deep Learning models (Novack et al, 2020), or on generating pop art-like images from photographic images using binomial distribution methods (Hiraoka, 2020), among many others. However, this does not occur with outsider art, where we can refer to only two works in computer science: Roberto & Davis (2020) and .…”

Vernacular architecture in Brazilian semiarid region: survey and memory in the state of Sergipe

“…Furthermore, Google Street View is being used in studies that aim to verify its feasibility to verify changes caused by environmental disasters, such as hurricanes (Zhai & Peng, 2020), and vulnerability in floods (D'Ayala et al, 2020) as well as accidents with nuclear power plants (Mabon, 2016). In the area of architecture and urbanism, there are studies focused on the detection and analysis of urban art in facades, such as graffiti (Novack et al, 2020), urban landscape analysis (Hong, 2020), and (Kim et al, 2021), among others. Despite the increasing use of GSV, few studies yet use it to analyze the existence of building's materials and housing conditions.…”

Development of a City-Scale Approach for Façade Color Measurement with Building Functional Classification Using Deep Learning and Street View Images

“…To achieve our research objectives and bridge the gap, the following challenges are worth noting. First, for data acquisition and cleaning, many studies measuring physical elements at large scales from street-level images have achieved great success, such as urban canyon classification [26], green view segmentation [27], and detection of building façades [28]. However, weather and sunlight can have an impact on the quality of street view images, affecting the accuracy of color-based calculation and image classification.…”