Deep Learning-Based Graffiti Detection: A Study Using Images from the Streets of Lisbon

Abstract

This research work comes from a real problem from Lisbon City Council that was interested in developing a system that automatically detects in real-time illegal graffiti present throughout the city of Lisbon by using cars equipped with cameras. This system would allow a more efficient and faster identification and clean-up of the illegal graffiti constantly being produced, with a georeferenced position. We contribute also a city graffiti database to share among the scientific community. Images were provided and collected from different sources that included illegal graffiti, images with graffiti considered street art, and images without graffiti. A pipeline was then developed that, first, classifies the image with one of the following labels: illegal graffiti, street art, or no graffiti. Then, if it is illegal graffiti, another model was trained to detect the coordinates of graffiti on an image. Pre-processing, data augmentation, and transfer learning techniques were used to train the models. Regarding the classification model, an overall accuracy of 81.4% and F1-scores of 86%, 81%, and 66% were obtained for the classes of street art, illegal graffiti, and image without graffiti, respectively. As for the graffiti detection model, an Intersection over Union (IoU) of 70.3% was obtained for the test set.

Robust Detection of Critical Events in the Context of Railway Security Based on Multimodal Sensor Data Fusion

“…Killen et al conducted a comprehensive analysis of six studies on the social background and motivation behind railroad-related graffiti vandalism, as well as the technological and non-technological mitigation measures employed. In one of the studies, the authors presented a deep-learning-based methodology for robust graffiti detection, as reported in [4]. While CCTV surveillance and geographical information systems (GISs) are employed to record and identify geographical patterns in vandalism activities, it is also observed that the presence of surveillance can have unintended consequences.…”