Human Detection in Thermal Imaging Using YOLO (CROSBI ID 677324)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Ivašić-Kos, Marina ; Krišto, Mate ; Pobar, Miran
engleski
Human Detection in Thermal Imaging Using YOLO
In this paper, we consider the problem of automatic detection of humans in thermal videos and images. The thermal videos are recorded on a meadow with a small forest with up to three persons present on the scene at different positions and ranges from the camera. To simulate realistic conditions that can happen during surveillance and monitoring of protected areas, all videos are recorded at night but different weather conditions– clear weather, rain, and fog. We present the results of human detection on a custom dataset of thermal videos using the out-of-the-box YOLO convolutional neural network and the YOLO network trained on a subset of our dataset. YOLO is an object detector pretrained on the COCO image dataset of RGB images of various object classes. Test experimental results have shown significantly improved performance of human detection in thermal imaging in terms of average precision for trained YOLO model over the original model.
Thermal imaging, Object Detector, Convolutional Neural Networks, YOLO, person detection
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
20-26.
2019.
objavljeno
10.1145/3323933.3324076
Podaci o matičnoj publikaciji
ICCTA 2019 Proceedings of the 2019 5th International Conference on Computer and Technology Applications
Istanbul: The Association for Computing Machinery (ACM)
978-1-4503-7181-0
Podaci o skupu
5th International Conference on Computer and Technology Applications (ICCTA '19)
predavanje
16.04.2019-17.04.2019
Istanbul, Turska
Povezanost rada
Računarstvo, Informacijske i komunikacijske znanosti