Object Detection on Thermal Images: Performance of YOLOv4 Trained on Small Datasets
Maxence Chaverot, Maxime Carré, Michel Jourlin, Abdelaziz Bensrhair, Richard Grisel · ESANN 2021 proceedings · 2021
Thermal sensors are underrepresented in the field of Advanced Driver Assistance Systems whereas their capabilities to acquire images independently of weather or daytime can be very helpful to achieve optimal pedestrian and vehicle detection.This underrepresentation is due to the small amount of available public datasets.This lack of training samples and the difficulties of building such datasets are a real hurdle to the development of an object detector dedicated to thermal images.Thanks to YOLOv4 and its detection performance, we show in this paper that finetuning this neural network requires few samples to achieve satisfying performance, outperforming the results of stateoftheart detectors.