Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikace
LIGOCKI, A. JELÍNEK, A.
Originální název
Transfer Learning for Deep Convolutional Neural Network from RGB to IR Domain
Typ
článek ve sborníku mimo WoS a Scopus
Jazyk
angličtina
Originální abstrakt
In this paper, we are presenting a proof of concept of our system for training of the YOLOv3 neural network for object detection of vehicles in thermal camera images. Our approach is unique in the way we are using a dataset containing a large number of synchronized range measurements as well as RGB and thermal images. We are using the existing YOLO toolkit to detect objects on the RGB images, we estimate detection distance by the LiDAR and later we reproject these detections into the IR image. In this way, we have created a large dataset of annotated thermal images that helped us to significantly improve the performance of the neural network at the IR domain.
Klíčová slova
Neural Networks, IR Camera, Object Detection, RGB to IR, Thermal imaging, YOLO, Transfer Learning
Autoři
LIGOCKI, A.; JELÍNEK, A.
Vydáno
24. 4. 2020
Strany počet
5
BibTex
@inproceedings{BUT163717, author="Adam {Ligocki} and Aleš {Jelínek}", title="Transfer Learning for Deep Convolutional Neural Network from RGB to IR Domain", year="2020", pages="5" }