A New Approach to Learning of 3D Characteristic Points for Vehicle Pose Estimation
[ 1 ] Wydział Automatyki, Robotyki i Elektrotechniki, Politechnika Poznańska | [ 2 ] Instytut Robotyki i Inteligencji Maszynowej, Wydział Automatyki, Robotyki i Elektrotechniki, Politechnika Poznańska | [ SzD ] doctoral school student | [ P ] employee
[2.2] Automation, electronics, electrical engineering and space technologies[2.3] Information and communication technology
2023
chapter in monograph / paper
english
- vehicle pose estimation
- 3D scene understanding
- deep learning
EN 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.
389 - 394
dla wszystkich w zakresie dozwolonego użytku
open repository
final published version
at the time of publication
20