Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | 2022 IEEE Intelligent Vehicles Symposium (IV) |
| Herausgeber (Verlag) | Institute of Electrical and Electronics Engineers Inc. |
| Seiten | 352-359 |
| Seitenumfang | 8 |
| ISBN (elektronisch) | 9781665488211 |
| Publikationsstatus | Veröffentlicht - 2022 |
| Veranstaltung | 2022 IEEE Intelligent Vehicles Symposium (IV 2022) - Eurocongress Aachen, Aachen, Deutschland Dauer: 5 Juni 2022 → 9 Juni 2022 https://ieeexplore.ieee.org/xpl/conhome/1000397/all-proceedings |
Abstract
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Angewandte Informatik
- Ingenieurwesen (insg.)
- Fahrzeugbau
- Mathematik (insg.)
- Modellierung und Simulation
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
2022 IEEE Intelligent Vehicles Symposium (IV). Institute of Electrical and Electronics Engineers Inc., 2022. S. 352-359.
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Self-Supervised Velocity Estimation for Automotive Radar Object Detection Networks
AU - Niederlohner, Daniel
AU - Ulrich, Michael
AU - Braun, Sascha
AU - Kohler, Daniel
AU - Faion, Florian
AU - Glaser, Claudius
AU - Treptow, Andre
AU - Blume, Holger
N1 - Publisher Copyright: © 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - This paper presents a method to learn the Cartesian velocity of objects using an object detection network on automotive radar data. The proposed method is self-supervised in terms of generating its own training signal for the velocities. Labels are only required for single-frame, oriented bounding boxes (OBBs). Labels for the Cartesian velocities or contiguous sequences, which are expensive to obtain, are not required. The general idea is to pre-train an object detection network without velocities using single-frame OBB labels, and then exploit the network's OBB predictions on unlabelled data for velocity training. In detail, the network's OBB predictions of the unlabelled frames are updated to the timestamp of a labelled frame using the predicted velocities and the distances between the updated OBBs of the unlabelled frame and the OBB predictions of the labelled frame are used to generate a self-supervised training signal for the velocities. The detection network architecture is extended by a module to account for the temporal relation of multiple scans and a module to represent the radars' radial velocity measurements explicitly. A two-step approach of first training only OBB detection, followed by training OBB detection and velocities is used. Further, a pre-training with pseudo-labels generated from radar radial velocity measurements bootstraps the self-supervised method of this paper. Experiments on the publicly available nuScenes dataset show that the proposed method almost reaches the velocity estimation performance of a fully supervised training, but does not require expensive velocity labels. Furthermore, we outperform a baseline method which uses only radial velocity measurements as labels.
AB - This paper presents a method to learn the Cartesian velocity of objects using an object detection network on automotive radar data. The proposed method is self-supervised in terms of generating its own training signal for the velocities. Labels are only required for single-frame, oriented bounding boxes (OBBs). Labels for the Cartesian velocities or contiguous sequences, which are expensive to obtain, are not required. The general idea is to pre-train an object detection network without velocities using single-frame OBB labels, and then exploit the network's OBB predictions on unlabelled data for velocity training. In detail, the network's OBB predictions of the unlabelled frames are updated to the timestamp of a labelled frame using the predicted velocities and the distances between the updated OBBs of the unlabelled frame and the OBB predictions of the labelled frame are used to generate a self-supervised training signal for the velocities. The detection network architecture is extended by a module to account for the temporal relation of multiple scans and a module to represent the radars' radial velocity measurements explicitly. A two-step approach of first training only OBB detection, followed by training OBB detection and velocities is used. Further, a pre-training with pseudo-labels generated from radar radial velocity measurements bootstraps the self-supervised method of this paper. Experiments on the publicly available nuScenes dataset show that the proposed method almost reaches the velocity estimation performance of a fully supervised training, but does not require expensive velocity labels. Furthermore, we outperform a baseline method which uses only radial velocity measurements as labels.
KW - cs.CV
KW - cs.AI
KW - cs.LG
KW - cs.RO
UR - http://www.scopus.com/inward/record.url?scp=85135380595&partnerID=8YFLogxK
U2 - 10.1109/IV51971.2022.9827295
DO - 10.1109/IV51971.2022.9827295
M3 - Conference contribution
SP - 352
EP - 359
BT - 2022 IEEE Intelligent Vehicles Symposium (IV)
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE Intelligent Vehicles Symposium (IV 2022)
Y2 - 5 June 2022 through 9 June 2022
ER -