4.6 Article

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

期刊

APPLIED SCIENCES-BASEL
卷 13, 期 4, 页码 -

出版社

MDPI
DOI: 10.3390/app13042249

关键词

graffiti; street art; classification; detection; computer vision

向作者/读者索取更多资源

This research work aims to develop a system that can automatically detect illegal graffiti in real-time in Lisbon using cars equipped with cameras. A classification model with an overall accuracy of 81.4% is used to classify images into street art, illegal graffiti, or no graffiti. Another model is trained to detect the coordinates of graffiti on an image, achieving an Intersection over Union (IoU) of 70.3% for the test set.
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.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据