Details
| Originalsprache | Englisch |
|---|---|
| Seiten (von - bis) | 935-944 |
| Seitenumfang | 10 |
| Fachzeitschrift | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Jahrgang | 10 |
| Ausgabenummer | 1 |
| Publikationsstatus | Veröffentlicht - 5 Dez. 2023 |
| Veranstaltung | 5th Geospatial Week 2023, GSW 2023 - Cairo, Ägypten Dauer: 2 Sept. 2023 → 7 Sept. 2023 |
Abstract
Vehicle reconstruction from single aerial images is an important but challenging task. In this work, we introduce a new framework based on convolutional neural networks (CNN) that performs monocular detection, pose, shape and type estimation for vehicles in UAV imagery, taking advantage of a strong 3D object model. In the final training phase, all components of the model are trained end-to-end. We present a UAV-based dataset for the evaluation of our model and additionally evaluate it on an augmented version of the Hessingheim benchmark dataset. Our method presents encouraging pose and shape estimation results: Based on images of 3 cm GSD, it achieves median errors of up to 5 cm in position and 3◦ in orientation, and RMS errors of ±7 cm and ±24 cm in planimetry and height, respectively, for keypoints describing the car shape.
ASJC Scopus Sachgebiete
- Physik und Astronomie (insg.)
- Instrumentierung
- Umweltwissenschaften (insg.)
- Umweltwissenschaften (sonstige)
- Erdkunde und Planetologie (insg.)
- Erdkunde und Planetologie (sonstige)
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Jahrgang 10, Nr. 1, 05.12.2023, S. 935-944.
Publikation: Beitrag in Fachzeitschrift › Konferenzaufsatz in Fachzeitschrift › Forschung › Peer-Review
}
TY - JOUR
T1 - Vehicle Pose and Shape Estimation in UAV Imagery Using a CNN
AU - El Amrani Abouelassad, S.
AU - Mehltretter, M.
AU - Rottensteiner, F.
N1 - Funding Information: This work was supported by the German Research Foundation (DFG) as a part of the Research Training Group i.c.sens [GRK2159]. Special thanks go to Norbert Haala, Michael Kölle and the entire team of the Hessigheim dataset for providing us with additional data that we used for our evaluation.
PY - 2023/12/5
Y1 - 2023/12/5
N2 - Vehicle reconstruction from single aerial images is an important but challenging task. In this work, we introduce a new framework based on convolutional neural networks (CNN) that performs monocular detection, pose, shape and type estimation for vehicles in UAV imagery, taking advantage of a strong 3D object model. In the final training phase, all components of the model are trained end-to-end. We present a UAV-based dataset for the evaluation of our model and additionally evaluate it on an augmented version of the Hessingheim benchmark dataset. Our method presents encouraging pose and shape estimation results: Based on images of 3 cm GSD, it achieves median errors of up to 5 cm in position and 3◦ in orientation, and RMS errors of ±7 cm and ±24 cm in planimetry and height, respectively, for keypoints describing the car shape.
AB - Vehicle reconstruction from single aerial images is an important but challenging task. In this work, we introduce a new framework based on convolutional neural networks (CNN) that performs monocular detection, pose, shape and type estimation for vehicles in UAV imagery, taking advantage of a strong 3D object model. In the final training phase, all components of the model are trained end-to-end. We present a UAV-based dataset for the evaluation of our model and additionally evaluate it on an augmented version of the Hessingheim benchmark dataset. Our method presents encouraging pose and shape estimation results: Based on images of 3 cm GSD, it achieves median errors of up to 5 cm in position and 3◦ in orientation, and RMS errors of ±7 cm and ±24 cm in planimetry and height, respectively, for keypoints describing the car shape.
KW - autonomous driving
KW - Object detection
KW - object reconstruction
KW - pose estimation
KW - shape estimation
UR - http://www.scopus.com/inward/record.url?scp=85183015158&partnerID=8YFLogxK
U2 - 10.5194/isprs-annals-X-1-W1-2023-935-2023
DO - 10.5194/isprs-annals-X-1-W1-2023-935-2023
M3 - Conference article
AN - SCOPUS:85183015158
VL - 10
SP - 935
EP - 944
JO - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
JF - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
SN - 2194-9042
IS - 1
T2 - 5th Geospatial Week 2023, GSW 2023
Y2 - 2 September 2023 through 7 September 2023
ER -