Wydawnictwa Uczelniane / TUL Press
Stały URI zbioruhttp://hdl.handle.net/11652/17
Przeglądaj
2 wyniki
Wyniki wyszukiwania
Pozycja Transformers Neural Networks Applications in Different Computer Vision Tasks(Wydawnictwo Politechniki Łódzkiej, 2023) Brodzicki, Andrzej; Piekarski, Michał; Kostuch, Aleksander; Noworolnik, Filip; Aleksandrowicz, Maciej; Wójcicka, Anna; Jaworek-Korjakowska, JoannaTransformers architectures are one of the latest inventions in the field of deep learning. Originally dedicated to NLP, they begin to find use in computer vision too. In this paper, we briefly describe the idea behind vision transformers and present a few examples, where we utilised them in our research, focusing on the field of medical images and autonomous driving. We show, that vision transformers can be used in various tasks, such as detection or classification, as well as explain how some of their drawbacks can be mitigated with a transfer learning approach.Pozycja Spotting Advertisements from Above: Billboard Detection and Segmentation in UAV Imagery(Wydawnictwo Politechniki Łódzkiej, 2023) Ptak, Bartosz; Dominiak, Jan; Kraft, MarekIn 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.