RT Conference Proceedings
T1 Analysis of the Influence of Training Data on Road User Detection
A1 Guindel Gómez, Carlos
A1 Martín Gómez, David
A1 Armingol Moreno, José María
A1 Stiller, Christoph
AB In this paper, we discuss the relevance of training data on modern object detectors used on onboard applications. Whereas modern deep learning techniques require large amounts of data, datasets with typical scenarios for autonomous vehicles are scarce and have a reduced number of samples. We conduct a comprehensive set of experiments to understand the effect of using a combination of two relatively small datasets to train an end-to-end object detector, based on the popular Faster R-CNN and enhanced with orientation estimation capabilities. We also test the adequacy of training models using partially available ground-truth labels, as a consequence of combining datasets aimed at different applications. Data augmentation is also introduced into the training pipeline. Results show a significant performance improvement in our exemplary case as a result of the higher variability of the training samples, thus opening a new way to improve the detection performance independently from the detector architecture.
PB IEEE
SN 978-1-5386-3543-8
YR 2018
FD 2018-09-12
LK https://hdl.handle.net/10016/32744
UL https://hdl.handle.net/10016/32744
LA eng
NO This work was supported by the Spanish Government through the CICYT projects TRA2015-63708-R and TRA2016-78886-C3-1-R, and the Comunidad de Madrid through SEGVAUTO-TRIES (S2013/MIT-2713).
DS e-Archivo
RD 18 jul. 2024