Spotting Advertisements from Above: Billboard Detection and Segmentation in UAV Imagery
Ładowanie...
Data
2023
Autorzy
Tytuł czasopisma
ISSN czasopisma
Tytuł tomu
Wydawca
Wydawnictwo Politechniki Łódzkiej
Lodz University of Technology Press
Lodz University of Technology Press
Abstrakt
In this work, deep-learning methods were researched for billboard
detection in urban environments. Billboards are one of the adversarial
visual pollutants occurring in cities, causing over-saturation of visual stimulation.
Due to this, we develop an algorithm that helps in the analysis and
management of urban space. We utilise near real-time object detection methods
to detect and segment them on images registered by unmanned aerial
vehicles (UAVs). Research is based on recent algorithms from the YOLO
family with modified heads for the instance segmentation task. We gathered
images and prepared hand-annotated labels for training and evaluation purposes
of deep learning approaches. We reached the mAP@0.5 metric of 0.61
for detection and 0.60 for segmentation, enabling us to develop smart city
applications.
Opis
Słowa kluczowe
object detection, segmentation, deep learning, YOLO, UAV, detekcja obiektów, segmentacja, głębokie uczenie, YOLO, UAV
Cytowanie
Ptak B., Dominiak J., Kraft M., Spotting Advertisements from Above: Billboard Detection and Segmentation in UAV Imagery. W: Progress in Polish Artificial Intelligence Research 4, Wojciechowski A. (Ed.), Lipiński P. (Ed.)., Seria: Monografie Politechniki Łódzkiej Nr. 2437, Wydawnictwo Politechniki Łódzkiej, Łódź 2023, s. 67-72, ISBN 978-83-66741-92-8, doi: 10.34658/9788366741928.9.