A New Approach to Learning of 3D Characteristic Points for Vehicle Pose Estimation
Ładowanie...
Data
2023
Autorzy
Tytuł czasopisma
ISSN czasopisma
Tytuł tomu
Wydawca
Wydawnictwo Politechniki Łódzkiej
Lodz University of Technology Press
Lodz University of Technology Press
Abstrakt
This article discusses the challenges of estimating the pose of a
vehicle from monocular images in an uncontrolled environment. We propose
a new neural network architecture that learns 3D characteristic points of vehicles
from image crops and coordinates of 2D keypoints on images. To facilitate
supervised training of this network, we pre-process the ApolloCar3D
dataset to obtain labelled 3D characteristic points of different car models.
We evaluate our approach on the ApolloCar3D benchmark and demonstrate
results competitive to state-of-the-art methods.
Opis
Słowa kluczowe
vehicle pose estimation, 3D scene understanding, deep learning, szacowanie pozycji pojazdu, zrozumienie sceny 3D, głębokie uczenie się
Cytowanie
Nowak T., Skrzypczyński P., A New Approach to Learning of 3D Characteristic Points for Vehicle Pose Estimation. W: Progress in Polish Artificial Intelligence Research 4, Wojciechowski A. (Ed.), Lipiński P. (Ed.)., Seria: Monografie Politechniki Łódzkiej Nr. 2437, Wydawnictwo Politechniki Łódzkiej, Łódź 2023, s. 389-394, ISBN 978-83-66741-92-8, doi: 10.34658/9788366741928.61.